EP2666146A1 - Determination by independent component analysis of the efficacy of a treatment - Google Patents

Determination by independent component analysis of the efficacy of a treatment

Info

Publication number
EP2666146A1
EP2666146A1 EP12700498.4A EP12700498A EP2666146A1 EP 2666146 A1 EP2666146 A1 EP 2666146A1 EP 12700498 A EP12700498 A EP 12700498A EP 2666146 A1 EP2666146 A1 EP 2666146A1
Authority
EP
European Patent Office
Prior art keywords
considered
severity
patient
received
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP12700498.4A
Other languages
German (de)
French (fr)
Inventor
Sylvain Mériadec PRIGENT
Xavier Descombes
Josiane Zerubia
Didier Zugaj
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Galderma Research and Development SNC
Institut National de Recherche en Informatique et en Automatique INRIA
Original Assignee
Galderma Research and Development SNC
Institut National de Recherche en Informatique et en Automatique INRIA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Galderma Research and Development SNC, Institut National de Recherche en Informatique et en Automatique INRIA filed Critical Galderma Research and Development SNC
Publication of EP2666146A1 publication Critical patent/EP2666146A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4848—Monitoring or testing the effects of treatment, e.g. of medication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2576/00—Medical imaging apparatus involving image processing or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20216—Image averaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30088—Skin; Dermal

Definitions

  • the technical field of the invention is the statistical classification systems, and more particularly the systems for the statistical classification of hyper-spectral images.
  • the evolution of skin diseases is quantified by dermatologists over an entire treatment period.
  • the degree of impairment is measured on each patient in a group. The measurement is performed clinically by a dermatologist.
  • a statistical treatment of the measurements makes it possible to quantify the effectiveness of the treatment.
  • an operating protocol based on the study over time of the symptoms related to a cutaneous disease expressed in a group of Ne patients is used.
  • Each patient receives a treatment on a first affected skin area and a vehicle on a second skin area affected.
  • the first skin area and the second skin area are selected to have similar area and disease involvement.
  • one cheek receives treatment while the other cheek receives the vehicle, provided that both cheeks have the same attack by a skin disease.
  • a dermatologist estimates the degree to which a patient is affected by the disease, zone by zone, patient by patient. As a result, the quantification of treatment efficacy can be empirical and subject to a certain amount of subjectivity.
  • hyper-spectral imaging In order to improve the observation and quantification of the degree of disease attack while increasing the reproducibility of these steps, hyper-spectral imaging can be used. It is recalled that hyper-spectral imaging consists of acquiring several images at different wavelengths. Indeed, the materials and chemical elements react more or less differently when exposed to radiation of a given wavelength. By scanning the range of radiation, it is possible to differentiate materials involved in the composition of an object by their difference in interaction. This principle can be generalized to a landscape, or to a part of an object.
  • the set of images from the photograph of the same scene at different wavelengths is called the hyper-spectral image or hyper-spectral cube.
  • a hyper-spectral image therefore consists of a set of images, each pixel of which is characteristic of the intensity of the interaction of the scene observed at a particular wavelength.
  • the acquisition of hyper-spectral images can be carried out according to several methods.
  • spectral scan The method of acquiring hyper-spectral images called spectral scan consists of using a CCD type sensor, to make spatial images, and to apply different filters in front of the sensor in order to select a wavelength for each image .
  • Different filter technologies make it possible to meet the needs of such imagers. For example, liquid crystal filters which isolate a wavelength by electrical stimulation of the crystals, or acousto-optic filters which select a wavelength by deforming a prism by means of an electric potential difference ( piezoelectric effect). These two filters have the advantage of not having moving parts which are often a source of fragility in optics.
  • the method of acquiring hyper-spectral images aims to acquire or "image" simultaneously all wavelengths of the spectrum on a CCD type sensor.
  • a prism is placed in front of the sensor. Then, to form the complete hyper-spectral cube, a spatial scan is performed line by line.
  • the so-called time-scan hyper-spectral image acquisition method involves performing an interference measurement, and then reconstructing the spectrum by making a Fast Fourier Transform (FFT) on the interference measurement.
  • FFT Fast Fourier Transform
  • Interference is achieved through a Michelson-type system, which interferes with a ray with itself shifted temporally.
  • the latest method of acquiring hyper-spectral images is to combine spectral and spatial scanning.
  • the CCD sensor is partitioned into blocks. Each block therefore deals with the same region of space but with different wavelengths. Then, a spectral and spatial scan makes it possible to constitute a complete hyper-spectral image.
  • hyper-spectral imaging allows the acquisition of images including information related to the wavelength. The intensity of each pixel as a function of the wavelength is recorded. The application of classification methods to these images distinguishes healthy areas from affected areas.
  • the classification of hyper-spectral images is a particularly active area.
  • Pigment cell res, vol. 17, pp. 618-626, 2004 teach that the L * component or the ITA index calculated with the L * and b * components is used to describe pigmentation.
  • An object of the invention is to generate images having a maximum contrast between images of an area affected by a disease and images of an area spared by the disease.
  • Another object of the invention is to determine a numerical index reflecting the effectiveness of the treatment of a disease.
  • Another object of the invention is an image processing system capable of determining a numerical index reflecting the efficiency of the treatment of a disease.
  • An object of the invention is a method of determining a quantization value of the deviation of the mean value of a di flibution of the severity difference between an initial time and a time after the initial time, the contrast-dependent severity between areas receiving treatment and areas receiving a vehicle.
  • the method includes steps in which:
  • At least one patient acquires, for at least one patient, at an initial time and at least one time after the initial time, at least one hyper-spectral image comprising at least one selected area among a sick area receiving the treatment, an area receiving the treatment, a sick area receiving the vehicle and a healthy area receiving the vehicle,
  • a representative component is determined that maximizes the gap between the healthy zone and the pathological zone
  • the averages are determined on all the images, absolute values of the linear combinations of the spectral bands each corresponding to the representative component of an image, a representative component corrected according to the average of the components is determined for each image.
  • a value of the severity difference is determined as a function of the corrected representative components of the acquired hyper-spectral images, for each patient and for each measurement instant, and
  • the invention has the advantage of providing a unique numerical index to characterize the efficiency of the treatment between two measurement instants automatically and from the only hyper-spectral images of a set of patients, the hyper-spectral images being classified between images of a healthy zone and images of a pathological zone.
  • the value of the severity of the disease can be determined for a patient at a time of measurement, calculated for the images relating to the areas having received the treatment, concerning the patient considered and the moment of measurement considered, realizing the simple difference between the mean value of intensity for the image of the healthy zone having received the treatment and the average intensity for the image of the sick area having received the treatment , and
  • a value of the difference in severity of the disease can be determined between the areas having received the treatment and the zones having received the vehicle for the patient considered at the time of measurement by making the simple difference in the severity of the disease. for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to areas that received the vehicle.
  • a value of the difference in severity of the disease can be determined between the areas having received the treatment and the areas having received the vehicle for the patient considered at the time of measurement by realizing the relative difference in the severity of the disease. for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to areas that received the vehicle.
  • the vehicle can be a placebo.
  • the vehicle may be another treatment.
  • Another object of the invention is an image processing system for determining the severity of a disease comprising a hyper-spectral image acquisition device connected to a processing means, the processing means being connected a data storage means and a human machine interaction device, the processing means being adapted to apply the method defined above.
  • Another object of the invention is the application of the method described above to the determination of the effectiveness of a dermatological treatment.
  • FIG. 1 illustrates the determination method according to the invention
  • the determination method starts with the acquisition 1 of at least one hyper-spectral image comprising a zone among a sick area receiving the treatment, a healthy zone receiving the treatment, a sick area receiving the vehicle and a healthy area receiving the vehicle .
  • These hyper-spectral images are acquired at each moment of measurement and for each patient. In the remainder of the description, it will be considered that four images each comprising an area of interest have been acquired.
  • vehicle By vehicle is meant a composition comprising the same excipients as those corresponding to the treatment but not including the active ingredients acting on the causes of the disease.
  • the vehicle may also be a placebo or a control solution.
  • the vehicle may be another treatment, that is to say a composition comprising active ingredients and excipients different from the composition of the first treatment.
  • the described method is based on the application of a treatment and a vehicle, it is possible to apply the method to compare a zone receiving a first treatment with a zone receiving a second treatment.
  • the four hyper-spectral images are processed by an independent component analysis method ("Independent Component Analysis” in English, identified by the acronym "ICA").
  • ICA Independent Component Analysis
  • Each image is transformed by the ICA process into an image of the same size and comprising as many independent components that the original image included wavelengths.
  • Each of the independent components is a linear combination of the wavelengths of the original image.
  • a representative component is determined that maximizes the difference between healthy and pathological zones.
  • linear combination For each image, the linear combination of the spectral bands corresponding to the representative component is stored.
  • linear combination is meant the weighting coefficients of each spectral band. It may require variations in coefficients from one patient to another.
  • the average of the solute values of the weighting coefficients involved in the linear combination of the representative component of each patient is averaged. The average of the ab solute values could also be achieved by precarrying outlier or extreme values. Average coefficients are thus obtained.
  • a representative component corrected as a function of the average of the representative components is determined, that is to say as a function of the average coefficients.
  • the determination method comprises a step 2 of determining an average pixel value of the corrected representative component M, for each image.
  • the average intensity on a corrected representative component M of a sick area receiving treatment is noted ⁇ ⁇ ⁇ ⁇
  • the mean intensity on a corrected representative component M of a healthy area receiving the treatment is noted ⁇ ⁇
  • the average intensity on a corrected representative component M of a sick area receiving the vehicle is noted ⁇ ⁇ ⁇ ⁇
  • the average intensity on a corrected representative component M of a healthy zone receiving the vehicle is noted ⁇ ⁇ ⁇
  • Np the total number of pixels per band of the image
  • I (m, M) the intensity of the pixel m of the corrected representative component M.
  • the determination method determines a single value for quantifying a patient's disease from the four intensity averages determined in the previous step.
  • the unique value obtained is the severity O e t .
  • a first normalization is applied between the sick zone and the healthy zone, during a step 3 of the method followed by a second normalization in another step 4 of the method.
  • the first standardization can be done by a simple difference.
  • the first normalization can be achieved by a relative difference.
  • ⁇ ⁇ 11 the average intensity for a healthy zone
  • ⁇ ⁇ the average intensity for a sick area.
  • the first normalization may correspond to the average measurement for the sick area
  • the normalization equation 2 is preferred. These values are determined at each moment of measurement and for each patient.
  • the determination method applies equation 2 by replacing the values ⁇ and ⁇ by the values ⁇ ⁇ and ⁇ ⁇ ⁇ in order to obtain the severity d t eA .
  • the determination method applies equation 3 by replacing the values ⁇ and ⁇ by the values ⁇ ⁇ and ⁇ ⁇ in order to obtain the severity d t eA .
  • the severity d ⁇ by replacing the values ⁇ ⁇ and ⁇ ⁇ ⁇ of equation 6 by the values ⁇ ⁇ and ⁇ ⁇ ⁇ ⁇
  • the determination method applies equation 4 by replacing the values ⁇ and ⁇ with the values ⁇ ⁇ and ⁇ ⁇ in order to obtain the severity d t eA .
  • ⁇ ⁇ ⁇ the mean intensity for a sick area that received the vehicle
  • ⁇ ⁇ the average intensity for a healthy zone that has received the treatment
  • ⁇ ⁇ the mean intensity for a diseased area that received the treatment.
  • a second normalization is applied between the area receiving the treatment and the area receiving the vehicle.
  • the second normalization makes it possible to determine the severity O e t of the patient e at the time of measurement t resulting from the comparison of the treatment and the vehicle. From the severities t eA areas having received treatment and severities t eV areas having received the vehicle, one can determine a severity O e t for e patient to the measurement time t.
  • d t eA the severity of the disease for the patient e at the time t of measurement, calculated for the images relating to the zones having received the treatment
  • d t eV the severity of the disease to the patient e at time t measure, calculated for images relating to areas having received the vehicle.
  • the determination method applies equation 8 to determine the severity O e t for the patient e at the time of measurement t.
  • equation 9 is applied to determine the severity D j for the patient e at the time of measurement t.
  • the distribution of severities e O t between patients is not yet considered.
  • a statistical analysis is necessary.
  • the inventors have ingeniously applied a t-test method to the data characterizing the difference between the treated patient zone and the sick area receiving the vehicle.
  • the t-test is applied to the severity index O e t .
  • Z Wo the quantification of the deviation of the mean value between two distributions
  • X (t) the mean value of X
  • ⁇ ( ⁇ ) the standard deviation of X
  • N e the number of patients in the group
  • t the time of measurement and the time of the reference measurement.
  • the null hypothesis is that the average value of the distribution does not evolve between the time to and the time t.
  • This test is applied to severities e O t obtained after optimizing the gap between healthy and diseased area area, X (t) then being the average value of all patients treated O e severities t at time t, and ⁇ ( ⁇ ) then being the standard deviation of the distribution of severities O e t at time t.
  • the average value of severities O e t can be calculated in several ways known to the skilled person, such as a simple average, on average, a statistical average. In addition, it is possible to remove extreme values, or outliers. In the latter two cases, the standard deviation of the distribution of severities O e t is calculated by separating the same values removed from all the values considered to perform the average.
  • the distribution of severities e O t between patients is not yet considered.
  • a statistical analysis is necessary.
  • the inventors have ingeniously applied a t-test method matched to the data characterizing the difference between the treated patient zone and the sick area receiving the vehicle.
  • the paired t-test is applied to the severity index W e t.
  • the method is called Paired Student Test, or paired t-test.
  • the null hypothesis is that the average value of the distribution does not evolve between time t 0 and time t.
  • This test is applied to severities e O t obtained after optimizing the gap between healthy and diseased area area, X (t) then being the average value of all patients considered the difference D , -D, between time t and time t 0 , and ⁇ ( ⁇ ) then being the standard deviation of the distribution of the difference D, -D, between time t and time t 0 .
  • the value of the difference -Df between the instant t and the instant t 0 can be calculated in several ways known to those skilled in the art, such as for example a simple average, a relative average, a statistical average. In addition, it is possible to remove extreme values, or outliers. In the latter two cases, the standard deviation of the distribution of severities -D, is calculated by discarding the same values removed from the set of values considered to achieve the mean.
  • the determination method thus comprises a step 5 of determining a value Z t t0 (t) of the quantization of the deviation of the mean value of the severity distribution O e t between time to and time t.
  • This value quantification is firstly compared to the null hypothesis for the presence of an effect, and compared to values Z t t0 (t) other treatments to compare the effects, or compared to Z t t0 (t) at other times to determine the evolution over time.
  • the difference between a value of the Student's statistic associated with Z t t0 (t) and the value 0.05 of the null hypothesis is significant, it means that the treated area is evolving more and more distinctly from the nonzero zone. treated. The treatment is then considered effective.
  • the Student statistic is obtained by reading the Student's Law table. For a value of Z on the abscissa, there is a probability on the y-axis.
  • the value Z makes it possible to characterize the effectiveness of the treatment over the total duration of treatment.
  • the value Z also makes it possible to compare the effectiveness of a treatment with the effectiveness of another treatment of the same duration.
  • the hyper-spectral image processing system 10 comprises a hyper-spectral image acquisition device 11 connected to a processing means 12, itself connected to a data storage means 13 and to a data storage device. human machine interaction 14.
  • the acquisition device is capable of producing hyper-spectral images of zones (15, 16) of a patient 17.
  • the zones whose image is acquired are a healthy zone 15 and a sick zone 16.
  • the images are also taken from fractions of these areas that have received treatment or a vehicle.
  • the acquisition is repeated for several subjects and at different measurement times.
  • the data obtained is transmitted to the processing means 12 which processes them in real time or redirects them to the data storage means 13 for delayed processing.
  • the processing means 12 applies the steps of the method for determining a quantization value of the deviation of the mean value of a distribution of the severity difference between an initial instant and a moment after the initial moment, the severity depending on the contrast between areas receiving treatment and areas receiving a vehicle.
  • the results of the processing are displayed via the human-machine interaction device 14.
  • the result can be displayed on one screen, transmitted to another system for further processing, or transmitted by a means of communication. remote electronic communication to or from multiple users.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Theoretical Computer Science (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

Method of determining a value for quantifying the deviation from the mean value of a distribution of the divergence in severity between an initial instant and a later instant subsequent to the initial instant, the severity depending on the contrast between zones receiving a treatment and zones receiving a vehicle, comprising steps in the course of which: at least one hyper-spectral image comprising at least one zone from among a diseased zone receiving the treatment, a healthy zone receiving the treatment, a diseased zone receiving the vehicle and a healthy zone receiving the vehicle is acquired, for at least one patient, at an initial instant and at at least one later instant subsequent to the initial instant, a decomposition of the hyper-spectral images into independent components is determined, a representative component maximizing the divergence between healthy zone and pathological zone is determined, for each image, from among the independent components, a representative component corrected as a function of the mean of the representative components is determined for each image, a value of the divergence in severity is determined as a function of the corrected representative components of the hyper-spectral images acquired, for each patient and for each measurement instant, and a value for quantifying the deviation from the mean value between a distribution of the divergence in severity at the initial instant and a distribution of the divergence in severity at a later instant subsequent to the initial instant is determined as a function of the value of the divergence in severity for each patient at the initial instant and at the later instant.

Description

DETERMINATION PAR ANALYSE EN COMPOSANTES INDEPENDANTES DE L'EFFICACITE D'UN TRAITEMENT  DETERMINATION BY INDEPENDENT COMPONENT ANALYSIS OF THE EFFECTIVENESS OF A TREATMENT
L'invention a pour domaine technique les systèmes de classement statistique, et plus particulièrement les systèmes de classement statistique d'images hyper-spectrales. The technical field of the invention is the statistical classification systems, and more particularly the systems for the statistical classification of hyper-spectral images.
Lors de phases d'essais cliniques, l'évolution des maladies de peau est quantifiée par des dermatologues sur toute une période de traitement. Dans une première phase, le degré d'atteinte par la maladie est mesuré sur chaque patient d'un groupe. La mesure est réalisée cliniquement par un dermatologue. Dans une seconde phase, un traitement statistique des mesures permet de quantifier l'efficacité du traitement.  In clinical trial phases, the evolution of skin diseases is quantified by dermatologists over an entire treatment period. In a first phase, the degree of impairment is measured on each patient in a group. The measurement is performed clinically by a dermatologist. In a second phase, a statistical treatment of the measurements makes it possible to quantify the effectiveness of the treatment.
En pratique, on utilise un protocole opératoire reposant sur l'étude au cours du temps des symptômes liés à une maladie cutanée exprimés dans un groupe de Ne patients. Chaque patient reçoit un traitement sur une première zone de peau atteinte et un véhicule sur une seconde zone de peau atteinte. La première zone de peau et la deuxième zone de peau sont choisies de façon à présenter une superficie et une atteinte par la maladie similaires. Dans le cas d'une maladie touchant la face, une joue reçoit le traitement tandis que l'autre joue reçoit le véhicule, sous condition que les deux joues présentent la même atteinte par une maladie cutanée.  In practice, an operating protocol based on the study over time of the symptoms related to a cutaneous disease expressed in a group of Ne patients is used. Each patient receives a treatment on a first affected skin area and a vehicle on a second skin area affected. The first skin area and the second skin area are selected to have similar area and disease involvement. In the case of a disease affecting the face, one cheek receives treatment while the other cheek receives the vehicle, provided that both cheeks have the same attack by a skin disease.
Un dermatologue estime ainsi le degré d'atteinte d'un patient par la maladie, zone par zone, patient par patient. De ce fait, la quantification de l'efficacité du traitement peut être empirique et soumise à une certaine part de subjectivité.  A dermatologist estimates the degree to which a patient is affected by the disease, zone by zone, patient by patient. As a result, the quantification of treatment efficacy can be empirical and subject to a certain amount of subjectivity.
Afin d'améliorer l'observation et la quantification du degré d'atteinte par une maladie tout en augmentant la reproductibilité de ces étapes, on peut utiliser l'imagerie hyper-spectrale. On rappelle que l'imagerie hyper-spectrale consiste à acquérir plusieurs images sous des longueurs d'onde différentes. En effet, les matériaux et éléments chimiques réagissent plus ou moins différemment lors de l'exposition à un rayonnement d'une longueur d'onde donnée. En balayant la gamme des rayonnements, il est possible de différencier des matériaux intervenant dans la composition d'un objet de part leur différence d'interaction. Ce principe peut être généralisé à un paysage, ou à une partie d'un objet. In order to improve the observation and quantification of the degree of disease attack while increasing the reproducibility of these steps, hyper-spectral imaging can be used. It is recalled that hyper-spectral imaging consists of acquiring several images at different wavelengths. Indeed, the materials and chemical elements react more or less differently when exposed to radiation of a given wavelength. By scanning the range of radiation, it is possible to differentiate materials involved in the composition of an object by their difference in interaction. This principle can be generalized to a landscape, or to a part of an object.
L'ensemble des images issues de la photographie d'une même scène à des longueurs d'onde différentes est appelé image hyper- spectrale ou cube hyper-spectral.  The set of images from the photograph of the same scene at different wavelengths is called the hyper-spectral image or hyper-spectral cube.
Une image hyper-spectrale est donc constituée d'un ensemble d'images dont chaque pixel est caractéristique de l'intensité de l'interaction de la scène observée à une longueur d'onde particulière. En connaissant les profils d'interaction des matériaux avec différents rayonnements, il est possible de déterminer les matériaux présents. Le terme matériau doit être compris dans un sens large, visant aussi bien les matières solides, liquides et gazeuses, et aussi bien les éléments chimiques purs que les assemblages complexes en molécules ou macromolécules.  A hyper-spectral image therefore consists of a set of images, each pixel of which is characteristic of the intensity of the interaction of the scene observed at a particular wavelength. By knowing the interaction profiles of the materials with different radiations, it is possible to determine the materials present. The term material must be understood in a broad sense, covering both solid, liquid and gaseous materials, and both pure chemical elements and complex assemblies in molecules or macromolecules.
L'acquisition d'images hyper-spectrales peut être réalisée selon plusieurs méthodes.  The acquisition of hyper-spectral images can be carried out according to several methods.
La méthode d'acquisition d'images hyper-spectrales dite de scan spectral consiste à utiliser un capteur de type CCD, pour réaliser des images spatiales, et à appliquer des filtres différents devant le capteur afin de sélectionner une longueur d'onde pour chaque image. Différentes technologies de filtres permettent de répondre aux besoins de tels imageurs. On peut, par exemple, citer les filtres à cristaux liquides qui isolent une longueur d'onde par stimulation électrique des cristaux, ou les filtres acousto-optique qui sélectionnent une longueur d'onde en déformant un prisme grâce à une différence de potentiel électrique (effet de piézo-électricité). Ces deux filtres présentent l'avantage de ne pas avoir de parties mobiles qui sont souvent source de fragilité en optique.  The method of acquiring hyper-spectral images called spectral scan consists of using a CCD type sensor, to make spatial images, and to apply different filters in front of the sensor in order to select a wavelength for each image . Different filter technologies make it possible to meet the needs of such imagers. For example, liquid crystal filters which isolate a wavelength by electrical stimulation of the crystals, or acousto-optic filters which select a wavelength by deforming a prism by means of an electric potential difference ( piezoelectric effect). These two filters have the advantage of not having moving parts which are often a source of fragility in optics.
La méthode d'acquisition d'images hyper-spectrales dite de scan spatial vise à acquérir ou « imager » simultanément toutes les longueurs d'ondes du spectre sur un capteur de type CCD. Pour réaliser la décomposition du spectre, un prisme est placé devant le capteur. Ensuite, pour constituer le cube hyper-spectral complet, on réalise un balayage spatial ligne par ligne. The method of acquiring hyper-spectral images called spatial scan aims to acquire or "image" simultaneously all wavelengths of the spectrum on a CCD type sensor. To realize the decomposition of the spectrum, a prism is placed in front of the sensor. Then, to form the complete hyper-spectral cube, a spatial scan is performed line by line.
La méthode d'acquisition d'images hyper-spectrales dite de scan temporel consiste à réaliser une mesure d'interférence, puis de reconstituer le spectre en faisant une transformée de Fourrier rapide (acronyme anglais : FFT) sur la mesure d'interférence. L'interférence est réalisée grâce à un système de type Michelson, qui fait interférer un rayon avec lui-même décalé temporellement.  The so-called time-scan hyper-spectral image acquisition method involves performing an interference measurement, and then reconstructing the spectrum by making a Fast Fourier Transform (FFT) on the interference measurement. Interference is achieved through a Michelson-type system, which interferes with a ray with itself shifted temporally.
La dernière méthode d'acquisition d'images hyper-spectrales vise à combiner le scan spectral et le scan spatial. Ainsi, le capteur CCD est partitionné sous forme de blocs. Chaque bloc traite donc la même région de l'espace mais avec des longueurs d'ondes différentes. Puis, un balayage spectral et spatial permet de constituer une image hyper-spectrale complète.  The latest method of acquiring hyper-spectral images is to combine spectral and spatial scanning. Thus, the CCD sensor is partitioned into blocks. Each block therefore deals with the same region of space but with different wavelengths. Then, a spectral and spatial scan makes it possible to constitute a complete hyper-spectral image.
Appliquée aux études dermatologiques, l'imagerie hyper- spectrale permet l'acquisition d'images comprenant une information liée à la longueur d'onde. L'intensité de chaque pixel en fonction de la longueur d'onde est enregistrée. L'application de méthodes de classification à ces images permet de distinguer les zones saines et des zones atteintes. On peut citer les travaux de P. Comon, "Independent component analysis: a new concept?," Signal Processing, Elsevier, vol. 36, pp. 287-314, 1994 concernant une méthode d'analyse en composante indépendantes permettant la classification de signaux.  Applied to dermatological studies, hyper-spectral imaging allows the acquisition of images including information related to the wavelength. The intensity of each pixel as a function of the wavelength is recorded. The application of classification methods to these images distinguishes healthy areas from affected areas. We can cite the work of P. Comon, "Independent component analysis: a new concept ?," Signal Processing, Elsevier, vol. 36, pp. 287-314, 1994 concerning an independent component analysis method for the classification of signals.
La classification d'images hyper-spectrales relève d'un domaine particulièrement actif. Plusieurs algorithmes existent pour traiter et classer les images hyper-spectrales obtenues sur la peau.  The classification of hyper-spectral images is a particularly active area. Several algorithms exist to process and classify the hyper-spectral images obtained on the skin.
I.L. Weatherall et B.D. Coombs, "Skin color measurements in terms of CIELAB color space value," Journal of Investigative Dermatology, vol. 99, pp. 468-473, 1992 enseignent le traitement d'images couleurs par la décomposition CIEL*a*b.  HE. Weatherall and B.D. Coombs, "Skin color measurements in terms of CIELAB color space value," Journal of Investigative Dermatology, vol. 99, pp. 468-473, 1992 teach the treatment of color images by the decomposition CIEL * a * b.
G. N. Stamatas et al., "Non-invasive measurements of skin pigmentation in situ." Pigment cell res, vol. 17, pp. 618-626, 2004 enseignent que la composante L* ou l'index ITA calculé avec les composantes L* et b* permet de décrire la pigmentation. GN Stamatas et al., "Non-invasive measurements of skin pigmentation in situ." Pigment cell res, vol. 17, pp. 618-626, 2004 teach that the L * component or the ITA index calculated with the L * and b * components is used to describe pigmentation.
G. N. Stamatas et al., "In vivo measurement of skin erythema and pigmentation: new means of implementation of diffuse réflectance spectroscopy with a commercial instrument," British Journal of Dermatology, vol. 159, pp. 683-690, 2008 décrivent la séparation des contributions de la mélanine et de l'hémoglobine dans une image hyper-spectrale sur la base de l'étude empirique de leurs absorptions respectives.  G.N. Stamatas et al., "In vivo measurement of skin erythema and pigmentation: new ways of implementing diffuse reflectance spectroscopy with a commercial instrument," British Journal of Dermatology, vol. 159, pp. 683-690, 2008 describe the separation of the contributions of melanin and hemoglobin in a hyper-spectral image based on the empirical study of their respective absorptions.
S. Prigent et al., "Spectral analysis and unsupervised SVM classification for skin hyper-pigmentation classification," IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (Whispers), Reykjavik, Islande, Juin 2010 et S. Prigent et al., "Multi-spectral image analysis for skin pigmentation classification," Proc. IEEE International Conférence on Image Processing (ICIP), Hong-Kong, Chine, Septembre 2010 décrivent des méthodes de classification de zones saines et de zones malades à partir d'images hyper-spectrales.  S. Prigent et al., "Spectral analysis and unsupervised SVM classification for skin hyper-pigmentation classification," IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (Whispers), Reykjavik, Iceland, June 2010 and S. Prigent and al., "Multi-spectral image analysis for skin pigmentation classification," Proc. IEEE International Conference on Image Processing (ICIP), Hong Kong, China, September 2010 describes methods for classifying healthy areas and diseased areas from hyper-spectral images.
En procédant à l'acquisition d'autres images hyper-spectrales à différents instants, il est possible d'ajouter une information temporelle. Il devient alors possible d'observer l'évolution d'une maladie dermatologique au cours du temps. Enfin, en procédant à l'analyse statistique des résultats d'un panel d'individus, il est possible de déterminer l'efficacité d'un traitement sur la maladie observée et ceci plus particulièrement, dans les désordres pigmentaires, l'acné, la rosacée, ou le psoriasis. Cette détermination peut être étendue aux images hyper-spectrales de phanères, notamment de phanères atteints de mycoses comme par exemple l'onychomycose. Par phanères, on entend les ongles et les cheveux. Parmi les phanères, on s'intéresse plus particulièrement aux ongles.  By acquiring other hyper-spectral images at different times, it is possible to add temporal information. It then becomes possible to observe the evolution of a dermatological disease over time. Finally, by performing a statistical analysis of the results of a panel of individuals, it is possible to determine the effectiveness of a treatment on the observed disease and this more particularly, in the pigment disorders, acne, rosacea, or psoriasis. This determination can be extended to hyper-spectral images of superficial body growths, especially appendages with fungal infections, such as onychomycosis. By dander, we mean the nails and hair. Among the dander, we are particularly interested in nails.
Un effet notable n'est reconnu à l'heure actuelle qu'à l'issue d'une étude statistique sur un large panel de patients. Afin de traiter les données issues des différentes images à différents instants pour les différents patients, il est nécessaire de di sposer d' un système de traitement des images performant. A notable effect is currently recognized only after a statistical study on a large panel of patients. In order to process data from different images at different times for different patients, it is necessary to distribute a powerful image processing system.
Un but de l ' invention est de générer des images présentant un contraste maximum entre des images d' une zone atteinte par une maladie et des images d' une zone épargnée par la maladie.  An object of the invention is to generate images having a maximum contrast between images of an area affected by a disease and images of an area spared by the disease.
Un autre but de l ' invention est de déterminer un indice numérique reflétant l ' efficacité du traitement d'une maladie.  Another object of the invention is to determine a numerical index reflecting the effectiveness of the treatment of a disease.
Un autre but de l ' invention est un système de traitement d' images apte à déterminer un indice numérique reflétant l' effi cacité du traitement d' une maladie.  Another object of the invention is an image processing system capable of determining a numerical index reflecting the efficiency of the treatment of a disease.
Un obj et de l ' invention est un procédé de détermination d' une valeur de quantification de la déviation de la valeur moyenne d 'une di stribution de l ' écart de sévérité entre un instant initial et un instant postérieur à l ' instant initial, la sévérité dépendant du contraste entre des zones recevant un traitement et des zones recevant un véhicule . Le procédé comprend des étapes au cours desquelles :  An object of the invention is a method of determining a quantization value of the deviation of the mean value of a di flibution of the severity difference between an initial time and a time after the initial time, the contrast-dependent severity between areas receiving treatment and areas receiving a vehicle. The method includes steps in which:
on acquiert, pour au moins un patient, à un instant initial et à au moins un instant postérieur à l ' instant initial, au moins une image hyper-spectrale comprenant au moins une zone choi sie parmi une zone malade recevant le traitement, une zone saine recevant le traitement, une zone malade recevant le véhicule et une zone saine recevant le véhicule,  at least one patient acquires, for at least one patient, at an initial time and at least one time after the initial time, at least one hyper-spectral image comprising at least one selected area among a sick area receiving the treatment, an area receiving the treatment, a sick area receiving the vehicle and a healthy area receiving the vehicle,
on détermine une décomposition en composantes indépendantes des images hyper-spectrales,  a decomposition into independent components of the hyper-spectral images is determined,
on détermine, pour chaque image, parmi les composantes indépendantes, une composante représentative maximi sant l ' écart entre zone saine et zone pathologique,  for each image, among the independent components, a representative component is determined that maximizes the gap between the healthy zone and the pathological zone,
on mémori se, pour chaque image, la combinai son linéaire des bandes spectrales correspondant à la composante représentative,  for each image, we note the linear combination of the spectral bands corresponding to the representative component,
on détermine la moyenne sur toutes les images, des valeurs ab solues des combinai sons linéaires des bandes spectrales correspondant chacune à la composante représentative d' une image, on détermine, pour chaque image, une composante représentative corrigée en fonction de la moyenne des composantes représentatives, on détermine une valeur de l'écart de sévérité en fonction des composantes représentatives corrigées des images hyper- spectrales acquises, pour chaque patient et pour chaque instant de mesure, et the averages are determined on all the images, absolute values of the linear combinations of the spectral bands each corresponding to the representative component of an image, a representative component corrected according to the average of the components is determined for each image. representative, a value of the severity difference is determined as a function of the corrected representative components of the acquired hyper-spectral images, for each patient and for each measurement instant, and
on détermine une valeur de quantification de la déviation de la valeur moyenne entre une distribution de l'écart de sévérité à l'instant initial et une distribution de l'écart de sévérité à un instant postérieur à l'instant initial en fonction de la valeur de l'écart de sévérité pour chaque patient à l'instant initial et à l'instant postérieur.  determining a quantization value of the deviation of the mean value between a severity difference distribution at the initial time and a distribution of the severity difference at a time subsequent to the initial time as a function of the value the severity difference for each patient at the initial time and the posterior moment.
L'invention présente l'avantage de fournir un indice numérique unique pour caractériser l'efficacité du traitement entre deux instants de mesure de façon automatique et à partir des seules images hyper- spectrales d'un ensemble de patients, les images hyper-spectrales étant classées entre images d'une zone saine et images d'une zone pathologique.  The invention has the advantage of providing a unique numerical index to characterize the efficiency of the treatment between two measurement instants automatically and from the only hyper-spectral images of a set of patients, the hyper-spectral images being classified between images of a healthy zone and images of a pathological zone.
On peut déterminer une valeur de l'écart de sévérité pour un instant de mesure,  We can determine a value of the difference of severity for a moment of measurement,
en déterminant, pour chacune des images acquises, une moyenne d'intensité égale à la valeur moyenne des pixels pour la composante représentative corrigée,  by determining, for each of the images acquired, an intensity average equal to the average value of the pixels for the corrected representative component,
en déterminant une valeur de la sévérité de la maladie pour un patient à un instant de mesure, calculée pour les images relatives aux zones ayant reçues le traitement concernant le patient et l'instant de mesure considéré,  by determining a value of the severity of the disease for a patient at a time of measurement, calculated for the images relating to the zones having received the treatment concerning the patient and the moment of measurement considered,
en déterminant une valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, et  determining a value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the instant of measurement considered, and
en déterminant une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour un patient à un instant de mesure.  determining a value of the difference in severity of the disease between the areas having received the treatment and the areas having received the vehicle for a patient at a time of measurement.
On peut déterminer la valeur de la sévérité de la maladie pour un patient à un instant de mesure, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence simple de la valeur moyenne d'intensité pour l'image de la zone saine ayant reçu le traitement et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et The value of the severity of the disease can be determined for a patient at a time of measurement, calculated for the images relating to the areas having received the treatment, concerning the patient considered and the moment of measurement considered, realizing the simple difference between the mean value of intensity for the image of the healthy zone having received the treatment and the average intensity for the image of the sick area having received the treatment , and
on peut déterminer la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence simple de la moyenne d'intensité pour l'image de la zone saine ayant reçu le véhicule et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule.  it is possible to determine the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the moment of measurement considered, by carrying out the simple difference of the average of intensity for the image of the healthy zone having received the vehicle and the average of intensity for the image of the sick zone having received the vehicle.
On peut déterminer la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence relative de la moyenne d'intensité pour l'image de la zone saine ayant reçu le traitement et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et  It is possible to determine the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment, concerning the patient considered and the instant of measurement considered, by carrying out the relative difference of the intensity average for the image of the healthy zone having received the treatment and the average intensity for the image of the sick area having received the treatment, and
on peut déterminer la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence relative de la moyenne d'intensité pour l'image de la zone saine ayant reçu le véhicule et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule.  it is possible to determine the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the moment of measurement considered, by carrying out the relative difference of the intensity average for the image of the healthy zone having received the vehicle and the average intensity for the image of the sick zone having received the vehicle.
On peut déterminer la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, comme étant égale à la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et  It is possible to determine the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment, concerning the patient considered and the instant of measurement considered, as being equal. the average intensity for the image of the diseased area that received the treatment, and
on peut déterminer la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, comme étant égale à la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule. it is possible to determine the value of the severity of the disease for the patient considered at the moment of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the moment of measurement considered as being equal to the average intensity for the image of the sick area having received the vehicle.
On peut déterminer une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour le patient considéré à l'instant de mesure considéré en réalisant la différence simple de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement et la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule.  A value of the difference in severity of the disease can be determined between the areas having received the treatment and the zones having received the vehicle for the patient considered at the time of measurement by making the simple difference in the severity of the disease. for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to areas that received the vehicle.
On peut déterminer une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour le patient considéré à l'instant de mesure considéré en réalisant la différence relative de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement et la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule.  A value of the difference in severity of the disease can be determined between the areas having received the treatment and the areas having received the vehicle for the patient considered at the time of measurement by realizing the relative difference in the severity of the disease. for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to areas that received the vehicle.
Le véhicule peut être un placebo.  The vehicle can be a placebo.
Le véhicule peut être un autre traitement.  The vehicle may be another treatment.
Un autre objet de l'invention est un système de traitement d'image pour la détermination de la sévérité d'une maladie comprenant un dispositif d'acquisition d'images hyper-spectrales connecté à un moyen de traitement, le moyen de traitement étant connecté à un moyen de stockage de données et à un dispositif d'interaction homme machine, le moyen de traitement étant apte à appliquer le procédé défini ci-dessus.  Another object of the invention is an image processing system for determining the severity of a disease comprising a hyper-spectral image acquisition device connected to a processing means, the processing means being connected a data storage means and a human machine interaction device, the processing means being adapted to apply the method defined above.
Un autre objet de l'invention est l'application du procédé décrit ci-dessus à la détermination de l'efficacité d'un traitement dermatologique. D'autres buts, caractéristiques et avantages apparaîtront à la lecture de la description suivante donnée uniquement en tant qu'exemple non limitatif et faite en référence aux figures annexées sur lesquelles : Another object of the invention is the application of the method described above to the determination of the effectiveness of a dermatological treatment. Other objects, features and advantages will appear on reading the following description given solely as a non-limitative example and with reference to the appended figures in which:
- la figure 1 illustre le procédé de détermination selon l'invention, et  FIG. 1 illustrates the determination method according to the invention, and
- la figure 2 illustre le système de traitement d'image associé. Le procédé de détermination débute par l'acquisition 1 d'au moins une image hyper-spectrale comprenant une zone parmi une zone malade recevant le traitement, une zone saine recevant le traitement, une zone malade recevant le véhicule et une zone saine recevant le véhicule. Ces images hyper-spectrales sont acquises à chaque instant de mesure et pour chaque patient. Dans la suite de la description, on considérera que l'on a procédé à l'acquisition de quatre images comprenant chacune une zone d'intérêt.  - Figure 2 illustrates the associated image processing system. The determination method starts with the acquisition 1 of at least one hyper-spectral image comprising a zone among a sick area receiving the treatment, a healthy zone receiving the treatment, a sick area receiving the vehicle and a healthy area receiving the vehicle . These hyper-spectral images are acquired at each moment of measurement and for each patient. In the remainder of the description, it will be considered that four images each comprising an area of interest have been acquired.
Toutefois, il est possible d'avoir au moins deux zones d'intérêt réparties sur une image. L'image peut alors être scindée en autant de sous-images que de zones d'intérêt présentes sur l'image initiale. Dans ce cas, on prendra soin d'obtenir des sous-images de même nombre de pixels. On prendra également soin de redimensionner les images hyper-spectrales n'ayant pas bénéficié d'un découpage en sous-images à une taille d'image présentant le même nombre de pixels que les sous- images.  However, it is possible to have at least two areas of interest spread over an image. The image can then be split into as many sub-images as areas of interest present on the initial image. In this case, care should be taken to obtain sub-images of the same number of pixels. Care will also be taken to resize hyper-spectral images that have not undergone sub-image splitting to an image size having the same number of pixels as sub-images.
L'homme du métier sera ainsi capable d'adapter le procédé décrit ci-après au cas où au moins une image comprend plusieurs zones d'intérêt en insérant une étape de création d'une sous-image par zone d'intérêt et de redimensionnement des images ne subissant pas de découpage. Dans tous les cas, quatre images hyper-spectrales correspondant chacune à une zone d'intérêt sont fournies au procédé.  Those skilled in the art will thus be able to adapt the method described below in the case where at least one image comprises several areas of interest by inserting a step of creating a sub-image by zone of interest and resizing. images not undergoing cutting. In all cases, four hyper-spectral images each corresponding to an area of interest are provided to the process.
Par véhicule, on entend une composition comprenant les mêmes excipients que ceux correspondant au traitement mais ne comprenant pas les principes actifs agissant sur les causes de la maladie, Le véhicule peut également être un placebo ou une solution de contrôle. Le véhicule peut être un autre traitement c'est-à-dire une composition comprenant des principes actifs et des excipients différents de la composition du premier traitement. By vehicle is meant a composition comprising the same excipients as those corresponding to the treatment but not including the active ingredients acting on the causes of the disease. The vehicle may also be a placebo or a control solution. The vehicle may be another treatment, that is to say a composition comprising active ingredients and excipients different from the composition of the first treatment.
Bi en que le procédé décrit soit fondé sur l ' application d' un traitement et d' un véhicule, il est possible d' appliquer le procédé afin de comparer une zone recevant un premier traitement à une zone recevant un deuxième traitement.  In that the described method is based on the application of a treatment and a vehicle, it is possible to apply the method to compare a zone receiving a first treatment with a zone receiving a second treatment.
Les quatre images hyper-spectrales sont traitées par un procédé d' analyse en composantes indépendantes (« Indépendant Component Analysis » en langue anglai se, identifié par l ' acronyme « ICA ») . Chaque image est transformée par le procédé ICA en une image de même taille et comprenant autant de composantes indépendantes que l ' image d' origine comprenait de longueurs d' onde. Chacune des composantes indépendantes est i ssue d ' une combinaison linéaire des longueurs d' ondes de l ' image d' origine.  The four hyper-spectral images are processed by an independent component analysis method ("Independent Component Analysis" in English, identified by the acronym "ICA"). Each image is transformed by the ICA process into an image of the same size and comprising as many independent components that the original image included wavelengths. Each of the independent components is a linear combination of the wavelengths of the original image.
On détermine, pour chaque image, parmi les composantes indépendantes, une composante représentative maximi sant l ' écart entre zone saine et zone pathologique.  For each image, among the independent components, a representative component is determined that maximizes the difference between healthy and pathological zones.
On mémorise, pour chaque image, la combinaison linéaire des bandes spectrales correspondant à la composante représentative. Par combinai son linéaire, on entend les coefficients de pondération de chaque bande spectrale. Il peut exi ster des variations de coefficients d' un patient à un autre. Afin d' obtenir une référence, on réali se la moyenne des valeurs ab solues des coeffici ents de pondérations entrant dans la combinaison linéaire de la composante représentative de chaque patient. On pourrait également réali ser la moyenne des valeurs ab solues en écartant préalablement les valeurs aberrantes ou extrêmes. On obtient ainsi des coefficients moyens.  For each image, the linear combination of the spectral bands corresponding to the representative component is stored. By linear combination is meant the weighting coefficients of each spectral band. It may require variations in coefficients from one patient to another. In order to obtain a reference, the average of the solute values of the weighting coefficients involved in the linear combination of the representative component of each patient is averaged. The average of the ab solute values could also be achieved by precarrying outlier or extreme values. Average coefficients are thus obtained.
On détermine, pour chaque image, une composante représentative corrigée en fonction de la moyenne des composantes représentatives, c' est-a-dire en fonction des coefficients moyens.  For each image, a representative component corrected as a function of the average of the representative components is determined, that is to say as a function of the average coefficients.
L ' extension spatiale de la maladie n' est pas pri se en compte. Ainsi, le procédé de détermination comprend une étape 2 de détermination d'une valeur moyenne des pixels de la composante représentative corrigée M, pour chaque image. The spatial extension of the disease is not taken into account. Thus, the determination method comprises a step 2 of determining an average pixel value of the corrected representative component M, for each image.
A l'issue de cette étape, on obtient donc quatre valeurs moyennes (μΜΐιΥ, μΜΡ Υ, μΜΐιΑ, et μΜΡ Α) correspondant chacune à une des images reçues lors de l'étape précédente. Ces valeurs sont déterminées à chaque instant de mesure et pour chaque patient. At the end of this step, we thus obtain four average values (μΜΐι Υ , μΜ Ρ Υ , μΜΐι Α , and μΜ Ρ Α ) each corresponding to one of the images received in the previous step. These values are determined at each moment of measurement and for each patient.
La moyenne d'intensité sur une composante représentative corrigée M d'une zone malade recevant le traitement est notée μΜΡ Α·The average intensity on a corrected representative component M of a sick area receiving treatment is noted μΜ Ρ Α ·
La moyenne d'intensité sur une composante représentative corrigée M d'une zone saine recevant le traitement est notée Μΐ The mean intensity on a corrected representative component M of a healthy area receiving the treatment is noted Μ ΐ
La moyenne d'intensité sur une composante représentative corrigée M d'une zone malade recevant le véhicule est notée μΜΡ Υ·The average intensity on a corrected representative component M of a sick area receiving the vehicle is noted μΜ Ρ Υ ·
La moyenne d'intensité sur une composante représentative corrigée M d'une zone saine recevant le véhicule est notée μΜΐιΥ· The average intensity on a corrected representative component M of a healthy zone receiving the vehicle is noted μΜΐι Υ ·
Une moyenne d'intensité notée μΜ peut être déterminée par l'équation suivante : An average of intensity noted μΜ can be determined by the following equation:
Avec (Moy(I))M= l'intensité moyenne relative à la composante représentative corrigée M  With (Moy (I)) M = the mean intensity relative to the corrected representative component M
Nb : le nombre total de bandes  Nb: the total number of bands
Np : le nombre total de pixels par bande de l'image  Np: the total number of pixels per band of the image
I(m,M) : l'intensité du pixel m de la composante représentative corrigée M.  I (m, M): the intensity of the pixel m of the corrected representative component M.
Le procédé de détermination détermine ensuite une valeur unique pour quantifier la maladie d'un patient à partir des quatre moyennes d'intensité déterminées à l'étape précédente. La valeur unique obtenue est la sévérité Oe t . Pour obtenir la sévérité Dj, on réalise une première normalisation appliquée entre la zone malade et la zone saine, au cours d'une étape 3 du procédé suivie d'une deuxième normalisation au cours d'une autre étape 4 du procédé. The determination method then determines a single value for quantifying a patient's disease from the four intensity averages determined in the previous step. The unique value obtained is the severity O e t . To obtain the severity D j , a first normalization is applied between the sick zone and the healthy zone, during a step 3 of the method followed by a second normalization in another step 4 of the method.
La première normalisation peut être réalisée par une simple différence.  The first standardization can be done by a simple difference.
dt = "Mh -μΜρ (Eq- 2) Alternativement, la première normalisation peut être réalisée par une différence relative.dt = "Mh -μ Μρ (Eq- 2 ) Alternatively, the first normalization can be achieved by a relative difference.
avec with
d( : la sévérité de la maladie pour le patient e à l'instant t de mesure d ( : the severity of the disease for the patient e at time t
μΜ11 : la moyenne d'intensité pour une zone saine, μ Μ11 : the average intensity for a healthy zone,
μΜρ : la moyenne d'intensité pour une zone malade. μ Μρ : the average intensity for a sick area.
Selon une autre alternative, la première normalisation peut correspondre à la mesure moyenne pour la zone malade  According to another alternative, the first normalization may correspond to the average measurement for the sick area
= μΜρ (Eq- 4)= μ Μρ (Eq- 4 )
Les mesures μΜ11 et μΜρ étant homogènes, l'équation de normalisation 2 est préférée. Ces valeurs sont déterminées à chaque instant de mesure et pour chaque patient. Since the measurements μ Μ11 and μ Μρ are homogeneous, the normalization equation 2 is preferred. These values are determined at each moment of measurement and for each patient.
A l'issue de cette étape, on obtient une sévérité de zones ayant reçues le traitement dt eA si les valeurs iMh et μΜΡ sont remplacées par les valeurs μΜΐιΑ et μΜΡ Α relatives aux moyennes d'intensité pour des zones traitées. De même, on obtient une sévérité de zones ayant reçues le véhicule dt eV si les valeurs iMh et μΜΡ sont remplacées par les valeurs μΜΐιΥ et μΜΡ Υ relatives aux moyennes d'intensité pour des zones ayant reçues le véhicule. After this step, one obtains a severity zones have received the treatment t e A if the IMH values and μΜ Ρ are replaced by the values μΜΐι Α and μΜ Ρ Α on average intensity for the treated areas. Similarly, one obtains a severity zones having received the vehicle t eV if the IMH values and μΜ Ρ are replaced by the values μΜΐι Υ and μΜ Ρ Υ on medium intensity for areas having received the vehicle.
Le procédé de détermination applique l'équation 2 en remplaçant les valeurs μΜΐι et μΜρ par les valeurs μΜΐιΑ et μΜΡ Α afin d'obtenir la sévérité dt eA. The determination method applies equation 2 by replacing the values μΜΐι and μΜρ by the values μΜΐι Α and μΜ Ρ Α in order to obtain the severity d t eA .
d^A = (d^A = (μΜ11 -μΜρ)Α = -μΜΡ (Eq.5)d ^ A = (d ^ A = (μ Μ11- μ Μρ ) Α = -μΜ Ρ (Eq.5)
Par analogie, on obtient la sévérité dt eV en remplaçant les valeurs μΜΐι et μΜρ de l'équation 5 par les valeurs μΜΐιΥ et μΜΡ Υ· By analogy, the severity of t eV is obtained by replacing μΜΐι μΜρ and values of the equation 5 by the values μΜΐι Υ and μΜ Ρ Υ ·
Alternativement, le procédé de détermination applique l'équation 3 en remplaçant les valeurs μΜΐι et μΜρ par les valeurs μΜΐιΑ et μΜρΑ afin d'obtenir la sévérité dt eA. Par analogie, on obtient la sévérité d^' en remplaçant les valeurs μΜΐιΑ et μΜΡ Α de l'équation 6 par les valeurs μΜΐιΥ et μΜΡ Υ· Alternatively, the determination method applies equation 3 by replacing the values μΜΐι and μΜρ by the values μΜΐι Α and μΜρ Α in order to obtain the severity d t eA . By analogy, we obtain the severity d ^ 'by replacing the values μΜΐι Α and μΜ Ρ Α of equation 6 by the values μΜΐι Υ and μΜ Ρ Υ ·
Alternativement, le procédé de détermination applique l'équation 4 en remplaçant les valeurs μΜΐι et μΜρ par les valeurs μΜΐιΑ et μΜρΑ afin d'obtenir la sévérité dt eA. Alternatively, the determination method applies equation 4 by replacing the values μΜΐι and μΜρ with the values μΜΐι Α and μΜρ Α in order to obtain the severity d t eA .
d^>A = (d*)A = μ^ (Eq.7)d ^ > A = (d * ) A = μ ^ (Eq.7)
Par analogie, on obtient la sévérité d^v en remplaçant la valeur μΜρΑ de l'équation 7 par la valeur μΜΡ Υ· Avec By analogy, we obtain the severity d ^ v by replacing the value μΜρ Α of equation 7 by the value μΜ Ρ Υ · With
: la moyenne d'intensité pour une zone saine ayant reçu le véhicule,  : the average intensity for a healthy area that has received the vehicle,
μ^ρ : la moyenne d'intensité pour une zone malade ayant reçu le véhicule, μ ^ ρ : the mean intensity for a sick area that received the vehicle,
μ^ : la moyenne d'intensité pour une zone saine ayant reçu le traitement,  μ ^: the average intensity for a healthy zone that has received the treatment,
μ^ : la moyenne d'intensité pour une zone malade ayant reçu le traitement.  μ ^: the mean intensity for a diseased area that received the treatment.
Pour les raisons évoquées en regard des équations Eq. 2, Eq. 3 et Eq.4 la normalisation préférée ici est celle relative à l'équation Eq. 5.  For the reasons mentioned with regard to equations Eq. 2, Eq. 3 and Eq.4 the preferred standardization here is that relative to equation Eq. 5.
Pour obtenir la sévérité Oe t à partir des deux sévérités dt eA et dt eV, une deuxième normalisation est appliquée entre la zone recevant le traitement et la zone recevant le véhicule. For the O e t severity from both severities eA t and t eV, a second normalization is applied between the area receiving the treatment and the area receiving the vehicle.
La deuxième normalisation permet de déterminer la sévérité Oe t du patient e à l'instant de mesure t issue de la comparaison du traitement et du véhicule. A partir des sévérités dt eA de zones ayant reçues le traitement et des sévérités dt eV de zones ayant reçues le véhicule, on peut déterminer une sévérité Oe t pour le patient e à l'instant de mesure t. The second normalization makes it possible to determine the severity O e t of the patient e at the time of measurement t resulting from the comparison of the treatment and the vehicle. From the severities t eA areas having received treatment and severities t eV areas having received the vehicle, one can determine a severity O e t for e patient to the measurement time t.
=dt eA-dt eV (Eq. 8) Alternativement, on peut déterminer une sévérité Oe t pour le patient e à l'instant de mesure t d'après l'équation suivante : avec = d t eA -d t eV (Eq 8) Alternatively, one can determine a severity O e t for the patient e at the time of measurement t according to the following equation: with
dt eA : la sévérité de la maladie pour le patient e à l'instant t de mesure, calculée pour les images relatives aux zones ayant reçues le traitement, d t eA : the severity of the disease for the patient e at the time t of measurement, calculated for the images relating to the zones having received the treatment,
dt eV : la sévérité de la maladie pour le patient e à l'instant t de mesure, calculée pour les images relatives aux zones ayant reçues le véhicule. d t eV: the severity of the disease to the patient e at time t measure, calculated for images relating to areas having received the vehicle.
Le procédé de détermination applique l'équation 8 afin de déterminer la sévérité Oe t pour le patient e à l'instant de mesure t.The determination method applies equation 8 to determine the severity O e t for the patient e at the time of measurement t.
Alternativement, l'équation 9 est appliquée pour déterminer la sévérité Dj pour le patient e à l'instant de mesure t. Alternatively, equation 9 is applied to determine the severity D j for the patient e at the time of measurement t.
Pour les raisons évoquées en regard des équations Eq.2, Eq.3, et Eq.4 la normalisation préférée ici est celle relative à l'équation Eq. 8. Ces valeurs sont déterminées à chaque instant de mesure et pour chaque patient.  For the reasons mentioned with regard to the equations Eq.2, Eq.3, and Eq.4, the preferred standardization here is that relating to the equation Eq. 8. These values are determined at each moment of measurement and for each patient.
A ce stade, la répartition des sévérités Oe t entre les différents patients n'est pas encore prise en compte. Afin d'en tenir compte, une analyse statistique est nécessaire. Pour cela, les inventeurs ont appliqué de façon ingénieuse une méthode de t-test aux données caractérisant l'écart entre la zone malade traitée et la zone malade recevant le véhicule. En d'autres termes, le t-test est appliqué à l'indice de sévérité Oe t. At this stage, the distribution of severities e O t between patients is not yet considered. In order to take this into account, a statistical analysis is necessary. For this, the inventors have ingeniously applied a t-test method to the data characterizing the difference between the treated patient zone and the sick area receiving the vehicle. In other words, the t-test is applied to the severity index O e t .
Le t-test est notamment décrit dans l'ouvrage de A. M. Mood, F. A. Graybill, et D. C. Boes, « Introduction to the theory of statistics », McGraw-Hill, 1974. Cet ouvrage divulgue une méthode de caractérisation de la déviation de la valeur moyenne entre deux distributions. La méthode est appelée test de Student (« Student test » en langue anglaise), ou t-test. The t-test is described in particular in AM Mood, FA Graybill, and DC Boes, "Introduction to the Theory of Statistics," McGraw-Hill, 1974. This book discloses a method of characterizing the deviation of the value average between two distributions. The method is called Student Test, or t-test.
Avec ZWo(t) la quantification de la déviation de la valeur moyenne entre deux distributions, X(t) la valeur moyenne de X, σ(ΐ) l'écart type de X, Ne le nombre de patients dans le groupe, t l'instant de mesure et to l'instant de la mesure de référence. L'hypothèse nulle est que la valeur moyenne de la distribution n'évolue pas entre le temps to et le temps t. L'hypothèse nulle est rejetée si la quantification de la déviation Zt t0(t) entre le temps to et le temps t a une probabilité (obtenue suivant la loi de Student) inférieure à la valeur p=0,05. With Z Wo (t) the quantification of the deviation of the mean value between two distributions, X (t) the mean value of X, σ (ΐ) the standard deviation of X, N e the number of patients in the group, t the time of measurement and the time of the reference measurement. The null hypothesis is that the average value of the distribution does not evolve between the time to and the time t. The null hypothesis is rejected if the quantification of the deviation Z t t0 (t) between the time to and the time ta a probability (obtained according to the law of Student) lower than the value p = 0,05.
Par ailleurs, plus basse est la valeur de la quantification de la déviation, plus grande est l'écart entre les valeurs moyennes des deux distributions entre l'instant t et l'instant t0. On the other hand, the lower the value of the quantization of the deviation, the greater the difference between the average values of the two distributions between the instant t and the instant t 0 .
Ce test est donc appliqué aux sévérités Oe t obtenues à l'issue de l'optimisation de l'écart entre zone saine et zone malade, X (t) étant alors la valeur moyenne sur l'ensemble des patients considérés des sévérités Oe t à l'instant t, et σ'(ΐ) étant alors l'écart type de la distribution des sévérités Oe t à l'instant t. This test is applied to severities e O t obtained after optimizing the gap between healthy and diseased area area, X (t) then being the average value of all patients treated O e severities t at time t, and σ (ΐ) then being the standard deviation of the distribution of severities O e t at time t.
La valeur moyenne des sévérités Oe t peut être calculée de plusieurs façons connues de l'homme du métier, comme par exemple une moyenne simple, une moyenne relative, une moyenne statistique. De plus, il est possible de retirer les valeurs extrêmes, ou les valeurs aberrantes. Dans ces deux derniers cas, l'écart type de la distribution des sévérités Oe t est calculé en écartant les mêmes valeurs retirées de l'ensemble des valeurs considérées pour réaliser la moyenne. The average value of severities O e t can be calculated in several ways known to the skilled person, such as a simple average, on average, a statistical average. In addition, it is possible to remove extreme values, or outliers. In the latter two cases, the standard deviation of the distribution of severities O e t is calculated by separating the same values removed from all the values considered to perform the average.
Alternativement, on considère un t-test apparié défini de la façon décrite ci-après. Une fois la valeur optimisée λ déterminée, la valeur de la sévérité Oe t correspondant à la valeur optimisée λ est à nouveau déterminée pour chaque instant de mesure et pour chaque patient, et utilisée pour les étapes ultérieures du procédé. Alternatively, a paired t-test defined as described hereinafter is considered. Once the optimized value λ has been determined, the value of the severity O e t corresponding to the optimized value λ is again determined for each measurement instant and for each patient, and used for the subsequent steps of the method.
A ce stade, la répartition des sévérités Oe t entre les différents patients n'est pas encore prise en compte. Afin d'en tenir compte, une analyse statistique est nécessaire. Pour cela, les inventeurs ont appliqué de façon ingénieuse une méthode de t-test apparié aux données caractérisant l'écart entre la zone malade traitée et la zone malade recevant le véhicule. En d'autres termes, le t-test apparié est appliqué à l'indice de sévérité Oe t. La méthode est appelée test de Student apparié (« Paired Student test » en langue anglaise), ou t-test apparié. At this stage, the distribution of severities e O t between patients is not yet considered. In order to take this into account, a statistical analysis is necessary. For this, the inventors have ingeniously applied a t-test method matched to the data characterizing the difference between the treated patient zone and the sick area receiving the vehicle. In other words, the paired t-test is applied to the severity index W e t. The method is called Paired Student Test, or paired t-test.
ZUo(t) = _¾¾r (Eq. 13) Z Uo (t) = _¾¾r (Eq.13)
Avec ZWo(t) la quantification de la déviation de la valeur moyenne entre la distribution X et une distribution normale standardisée N(0,1), X(t) la valeur moyenne de X, σ(ΐ) l'écart type deWith Z Wo (t) the quantification of the deviation of the mean value between the X distribution and a standardized normal distribution N (0,1), X (t) the mean value of X, σ (ΐ) the standard deviation of
X, Ne le nombre de patients dans le groupe, t l'instant de mesure et t0 l'instant de la mesure de référence. L'hypothèse nulle est que la valeur moyenne de la distribution n'évolue pas entre le temps t0 et le temps t. L'hypothèse nulle est rejetée si la quantification de la déviation Zt t0(t) entre le temps t0 et le temps t a une probabilité (obtenue suivant la loi de Student) inférieure à la valeur p=0,05. X, N e the number of patients in the group, t the time of measurement and t 0 the time of the reference measurement. The null hypothesis is that the average value of the distribution does not evolve between time t 0 and time t. The null hypothesis is rejected if the quantification of the deviation Z t t0 (t) between the time t 0 and the time ta a probability (obtained according to the law of Student) lower than the value p = 0.05.
Par ailleurs, plus basse est la valeur de la quantification de la déviation, plus grande est l'écart entre X et N(0,1).  On the other hand, the lower the value of the quantization of the deviation, the greater the difference between X and N (0,1).
Ce test est donc appliqué aux sévérités Oe t obtenues à l'issue de l'optimisation de l'écart entre zone saine et zone malade, X(t) étant alors la valeur moyenne sur l'ensemble des patients considérés de la différence D, -D, entre l'instant t et l'instant t0, et σ(ΐ) étant alors l'écart type de la distribution de la différence D, -D, entre l'instant t et l'instant t0. This test is applied to severities e O t obtained after optimizing the gap between healthy and diseased area area, X (t) then being the average value of all patients considered the difference D , -D, between time t and time t 0 , and σ (ΐ) then being the standard deviation of the distribution of the difference D, -D, between time t and time t 0 .
La valeur de la différence -Df entre l'instant t et l'instant t0 peut être calculée de plusieurs façons connues de l'homme du métier, comme par exemple une moyenne simple, une moyenne relative, une moyenne statistique. De plus, il est possible de retirer les valeurs extrêmes, ou les valeurs aberrantes. Dans ces deux derniers cas, l'écart type de la distribution des sévérités -D, est calculé en écartant les mêmes valeurs retirées de l'ensemble des valeurs considérées pour réaliser la moyenne. The value of the difference -Df between the instant t and the instant t 0 can be calculated in several ways known to those skilled in the art, such as for example a simple average, a relative average, a statistical average. In addition, it is possible to remove extreme values, or outliers. In the latter two cases, the standard deviation of the distribution of severities -D, is calculated by discarding the same values removed from the set of values considered to achieve the mean.
Le procédé de détermination comprend ainsi une étape 5 de détermination d'une valeur Zt t0(t) de la quantification de la déviation de la valeur moyenne de la distribution des sévérité Oe t entre le temps to et le temps t. Cette valeur de quantification sera d'une part comparée à l'hypothèse nulle pour déterminer la présence d'un effet, puis comparée à des valeurs Zt t0(t) d'autres traitements pour en comparer les effets, ou comparée à des Zt t0(t) à d'autres instants afin de déterminer l'évolution dans le temps. The determination method thus comprises a step 5 of determining a value Z t t0 (t) of the quantization of the deviation of the mean value of the severity distribution O e t between time to and time t. This value quantification is firstly compared to the null hypothesis for the presence of an effect, and compared to values Z t t0 (t) other treatments to compare the effects, or compared to Z t t0 (t) at other times to determine the evolution over time.
Si l'écart entre une valeur de la statistique de Student associée à Zt t0(t) et la valeur 0,05 de l'hypothèse nulle est important, cela signifie que la zone traitée évolue de plus en plus distinctement de la zone non traitée. Le traitement est alors considéré comme efficace. La statistique de Student est obtenue par lecture de la table de la loi de Student. Pour une valeur de Z en abscisse, correspond une probabilité en ordonnée. If the difference between a value of the Student's statistic associated with Z t t0 (t) and the value 0.05 of the null hypothesis is significant, it means that the treated area is evolving more and more distinctly from the nonzero zone. treated. The treatment is then considered effective. The Student statistic is obtained by reading the Student's Law table. For a value of Z on the abscissa, there is a probability on the y-axis.
La valeur Z permet de caractériser l'efficacité du traitement sur la durée totale de traitement. La valeur Z permet également de comparer l'efficacité d'un traitement à l'efficacité d'un autre traitement de même durée.  The value Z makes it possible to characterize the effectiveness of the treatment over the total duration of treatment. The value Z also makes it possible to compare the effectiveness of a treatment with the effectiveness of another treatment of the same duration.
Le système de traitement d'images hyper-spectrales 10 comprend un dispositif d'acquisition d'images hyper-spectrales 11 connecté à un moyen de traitement 12, lui-même connecté à un moyen de stockage de données 13 et à un dispositif d'interaction homme machine 14.  The hyper-spectral image processing system 10 comprises a hyper-spectral image acquisition device 11 connected to a processing means 12, itself connected to a data storage means 13 and to a data storage device. human machine interaction 14.
Le dispositif d'acquisition est apte à réaliser des images hyper- spectrales de zones (15,16) d'un patient 17. Les zones dont l'image est acquise sont une zone saine 15 et une zone malade 16. Les images sont également prises sur des fractions de ces zones ayant reçues un traitement ou un véhicule. L'acquisition est répétée pour plusieurs sujets et à des instants de mesure différents. Les données obtenues sont transmises au moyen de traitement 12 qui les traite en temps réel ou les redirige vers le moyen de stockage de données 13 pour un traitement différé.  The acquisition device is capable of producing hyper-spectral images of zones (15, 16) of a patient 17. The zones whose image is acquired are a healthy zone 15 and a sick zone 16. The images are also taken from fractions of these areas that have received treatment or a vehicle. The acquisition is repeated for several subjects and at different measurement times. The data obtained is transmitted to the processing means 12 which processes them in real time or redirects them to the data storage means 13 for delayed processing.
Le moyen de traitement 12 applique les étapes du procédé de détermination d'une valeur de quantification de la déviation de la valeur moyenne d'une distribution de l'écart de sévérité entre un instant initial et un instant postérieur à l'instant initial, la sévérité dépendant du contraste entre des zones recevant un traitement et des zones recevant un véhicule. The processing means 12 applies the steps of the method for determining a quantization value of the deviation of the mean value of a distribution of the severity difference between an initial instant and a moment after the initial moment, the severity depending on the contrast between areas receiving treatment and areas receiving a vehicle.
Les résultats du traitement sont affichées par l'intermédiaire du dispositif d'interaction homme machine 14. Le résultat peut être affiché sur un écran, transmis à un autre système pour être l'objet d'un autre traitement, ou transmis par un moyen de communication électronique distant à ou plusieurs utilisateurs.  The results of the processing are displayed via the human-machine interaction device 14. The result can be displayed on one screen, transmitted to another system for further processing, or transmitted by a means of communication. remote electronic communication to or from multiple users.

Claims

REVENDICATIONS
1 . Procédé de détermination d' une valeur de quantification de la déviation de la valeur moyenne d 'une di stribution de l ' écart de sévérité entre un instant initial et un instant postérieur à l ' instant initial, la sévérité dépendant du contraste entre des zones recevant un traitement et des zones recevant un véhicule, comprenant des étapes au cours desquelles : 1. A method of determining a quantization value of the deviation of the mean value of a di flibution of the severity difference between an initial time and a time after the initial time, the contrast - dependent severity between zones receiving a treatment and areas receiving a vehicle, including steps in which:
on acquiert, pour au moins un patient, à un instant initial et à au moins un instant postérieur à l ' instant initial, au moins une image hyper-spectrale comprenant au moins une zone parmi une zone malade recevant le traitement, une zone saine recevant le traitement, une zone malade recevant le véhicule et une zone saine recevant le véhicule, on détermine une décomposition en composantes indépendantes des images hyper-spectrales,  for at least one patient, at least one hyperspectral image comprising at least one of a diseased area receiving the treatment, a healthy receiving zone, is acquired for at least one patient at an initial time and at least one time after the initial time. the treatment, a sick area receiving the vehicle and a healthy area receiving the vehicle, a decomposition into independent components of the hyper-spectral images is determined,
on détermine, pour chaque image, parmi les composantes indépendantes, une composante représentative maximi sant l ' écart entre zone saine et zone pathologique,  for each image, among the independent components, a representative component is determined that maximizes the gap between the healthy zone and the pathological zone,
on mémori se, pour chaque image, la combinai son linéaire des bandes spectrales correspondant à la composante représentative,  for each image, we note the linear combination of the spectral bands corresponding to the representative component,
on détermine la moyenne sur toutes les images, des valeurs ab solues des combinai sons linéaires des bandes spectrales correspondant chacune à la composante représentative d' une image, on détermine, pour chaque image, une composante représentative corrigée en fonction de la moyenne des composantes représentatives,  the averages are determined on all the images, absolute values of the linear combinations of the spectral bands each corresponding to the representative component of an image, a representative component is determined for each image, corrected as a function of the average of the representative components. ,
on détermine une valeur de l ' écart de sévérité en fonction des composantes représentatives corrigées des images hyper-spectrales acqui ses, pour chaque patient et pour chaque instant de mesure, et  a value of the severity difference is determined according to the corrected representative components of the acquired hyper-spectral images, for each patient and for each measurement instant, and
on détermine une valeur de quantification de la déviation de la valeur moyenne entre une di stribution de l ' écart de sévérité à l ' instant initial et une di stribution de l ' écart de sévérité à un instant postérieur à l'instant initial en fonction de la valeur de l'écart de sévérité pour chaque patient à l'instant initial et à l'instant postérieur. a quantization value of the deviation of the average value between a di flibution of the severity difference at the initial time and a di flibution of the severity difference at a later instant is determined. at the initial time according to the value of the severity difference for each patient at the initial time and the posterior moment.
2. Procédé selon la revendication 1, dans lequel on détermine une valeur de quantification de la déviation de la valeur moyenne entre une distribution de l'écart de sévérité à l'instant initial et une distribution de l'écart de sévérité à un instant postérieur à l'instant initial en appliquant un test de Student ou un test de Student apparié aux valeurs optimisées de la valeur de l'écart de sévérité pour chaque patient à l'instant initial et à l'instant postérieur.  2. Method according to claim 1, wherein a quantization value of the deviation of the average value between a distribution of the severity difference at the initial instant and a distribution of the difference in severity at a later instant is determined. at the initial time by applying a paired Student or Student t test to the optimized values of the severity difference for each patient at the initial and the later time.
3. Procédé selon l'une quelconque des revendications précédentes, dans lequel on détermine une valeur de l'écart de sévérité pour un instant de mesure  3. Method according to any one of the preceding claims, wherein a value of the difference in severity for a measurement instant is determined.
en déterminant, pour chacune des images acquises, une moyenne d'intensité égale à la valeur moyenne des pixels pour la composante représentative corrigée,  by determining, for each of the images acquired, an intensity average equal to the average value of the pixels for the corrected representative component,
en déterminant une valeur de la sévérité de la maladie pour un patient à un instant de mesure, calculée pour les images relatives aux zones ayant reçues le traitement concernant le patient et l'instant de mesure considéré,  by determining a value of the severity of the disease for a patient at a time of measurement, calculated for the images relating to the zones having received the treatment concerning the patient and the moment of measurement considered,
en déterminant une valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, et  determining a value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the instant of measurement considered, and
en déterminant une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour un patient à un instant de mesure.  determining a value of the difference in severity of the disease between the areas having received the treatment and the areas having received the vehicle for a patient at a time of measurement.
4. Procédé selon l'une quelconque des revendications précédentes, dans lequel on détermine la valeur de la sévérité de la maladie pour un patient à un instant de mesure, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence simple de la moyenne d'intensité pour l'image de la zone saine ayant reçu le traitement et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et on détermine la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence simple de la moyenne d'intensité pour l'image de la zone saine ayant reçu le véhicule et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule. 4. A method according to any one of the preceding claims, wherein the value of the severity of the disease for a patient is determined at a measurement instant, calculated for the images relating to the areas having received the treatment, concerning the patient considered and the instant of measurement considered, realizing the simple difference of the intensity average for the image of the healthy zone having received the treatment and the average intensity for the image of the sick area having received the treatment, and the value of the severity of the disease is determined for the patient considered at the moment of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the instant of measurement considered, making the difference simple of the average of intensity for the image of the healthy zone having received the vehicle and the average of intensity for the image of the sick zone having received the vehicle.
5. Procédé selon l'une quelconque des revendications 1 à 3, dans lequel on détermine la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence relative de la moyenne d'intensité pour l'image de la zone saine ayant reçu le traitement et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et  5. Method according to any one of claims 1 to 3, wherein the value of the severity of the disease is determined for the patient considered at the time of measurement considered, calculated for the images relating to the zones having received the treatment, concerning the patient considered and the moment of measurement considered, realizing the relative difference of the intensity average for the image of the healthy zone having received the treatment and the average intensity for the image of the sick area having received the treatment, and
on détermine la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, en réalisant la différence relative de la moyenne d'intensité pour l'image de la zone saine ayant reçu le véhicule et de la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule.  the value of the severity of the disease is determined for the patient considered at the moment of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the instant of measurement considered, making the difference relative of the intensity average for the image of the healthy zone which has received the vehicle and the average intensity for the image of the sick zone which has received the vehicle.
6. Procédé selon l'une quelconque des revendications 1 à 3, dans lequel on détermine la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement, concernant le patient considéré et l'instant de mesure considéré, comme étant égale à la moyenne d'intensité pour l'image de la zone malade ayant reçu le traitement, et  6. Method according to any one of claims 1 to 3, wherein the value of the severity of the disease is determined for the patient considered at the moment of measurement considered, calculated for the images relating to the zones having received the treatment, concerning the patient considered and the moment of measurement considered, being equal to the average intensity for the image of the sick area having received the treatment, and
on détermine la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule, concernant le patient considéré et l'instant de mesure considéré, comme étant égale à la moyenne d'intensité pour l'image de la zone malade ayant reçu le véhicule. the value of the severity of the disease is determined for the patient considered at the moment of measurement considered, calculated for the images relating to the zones having received the vehicle, concerning the patient considered and the instant of measurement considered, being equal to the average intensity for the image of the diseased area that received the vehicle.
7. Procédé selon l'une des quelconque des revendications 4 à 6, dans lequel on détermine une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour le patient considéré à l'instant de mesure considéré en réalisant la différence simple de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement et la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule.  The method according to any one of claims 4 to 6, wherein a value of the difference in severity of the disease is determined between the areas having received the treatment and the areas having received the vehicle for the patient under consideration. measurement instant considered by realizing the simple difference in the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the areas having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the areas having received the vehicle.
8. Procédé selon l'une quelconque des revendications 4 à 6, dans lequel on détermine une valeur de l'écart de sévérité de la maladie entre les zones ayant reçues le traitement et les zones ayant reçues le véhicule pour le patient considéré à l'instant de mesure considéré en réalisant la différence relative de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le traitement et la valeur de la sévérité de la maladie pour le patient considéré à l'instant de mesure considéré, calculée pour les images relatives aux zones ayant reçues le véhicule.  A method according to any one of claims 4 to 6, wherein a value of the difference in severity of the disease is determined between the areas having received treatment and the areas having received the vehicle for the patient considered at measurement instant considered by realizing the relative difference in the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the areas having received the treatment and the value of the severity of the disease for the patient considered at the time of measurement considered, calculated for the images relating to the areas having received the vehicle.
9. Procédé selon l'une quelconque des revendications 1 à 8, dans lequel le véhicule est un placebo.  The method of any one of claims 1 to 8, wherein the vehicle is a placebo.
10. Procédé selon l'une quelconque des revendications 1 à 8, dans lequel le véhicule est un autre traitement.  The method of any one of claims 1 to 8, wherein the vehicle is another treatment.
11. Système de traitement d'image pour la détermination de la sévérité d'une maladie caractérisé par le fait qu'il comprend un dispositif d'acquisition d'images hyper-spectrales (11) connecté à un moyen de traitement (12), le moyen de traitement (12) étant connecté à un moyen de stockage de données (13) et à un dispositif d'interaction homme machine (14), le moyen de traitement (12) étant apte à appliquer le procédé tel que revendiqué dans les revendications 1 à 10. An image processing system for determining the severity of a disease characterized in that it comprises a hyper-spectral image acquisition device (11) connected to a processing means (12), the processing means (12) being connected to a data storage means (13) and to a human machine interaction device (14), the processing means (12) being adapted to apply the method as claimed in the Claims 1 to 10.
12. Application du procédé de détermination selon les revendications 1 à 10, à la détermination de l'efficacité d'un traitement thérapeutique. 12. Application of the determination method according to claims 1 to 10, for determining the effectiveness of a therapeutic treatment.
EP12700498.4A 2011-01-20 2012-01-20 Determination by independent component analysis of the efficacy of a treatment Withdrawn EP2666146A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1150459A FR2970802B1 (en) 2011-01-20 2011-01-20 METHOD FOR DETERMINING BY INDEPENDENT COMPONENT ANALYSIS THE EFFICIENCY OF A PROCESSING AND ASSOCIATED IMAGE PROCESSING SYSTEM
PCT/EP2012/050864 WO2012098227A1 (en) 2011-01-20 2012-01-20 Determination by independent component analysis of the efficacy of a treatment

Publications (1)

Publication Number Publication Date
EP2666146A1 true EP2666146A1 (en) 2013-11-27

Family

ID=44262469

Family Applications (1)

Application Number Title Priority Date Filing Date
EP12700498.4A Withdrawn EP2666146A1 (en) 2011-01-20 2012-01-20 Determination by independent component analysis of the efficacy of a treatment

Country Status (5)

Country Link
US (1) US20130345542A1 (en)
EP (1) EP2666146A1 (en)
CA (1) CA2824911A1 (en)
FR (1) FR2970802B1 (en)
WO (1) WO2012098227A1 (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004021050A2 (en) * 2002-08-29 2004-03-11 Kestrel Corporation Hyperspectral imaging of the human retina
US7321791B2 (en) * 2003-09-23 2008-01-22 Cambridge Research And Instrumentation, Inc. Spectral imaging of deep tissue
US8224425B2 (en) * 2005-04-04 2012-07-17 Hypermed Imaging, Inc. Hyperspectral imaging in diabetes and peripheral vascular disease
US7689016B2 (en) * 2005-05-27 2010-03-30 Stoecker & Associates, A Subsidiary Of The Dermatology Center, Llc Automatic detection of critical dermoscopy features for malignant melanoma diagnosis

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2012098227A1 *

Also Published As

Publication number Publication date
US20130345542A1 (en) 2013-12-26
WO2012098227A1 (en) 2012-07-26
FR2970802A1 (en) 2012-07-27
CA2824911A1 (en) 2012-07-26
FR2970802B1 (en) 2013-02-08

Similar Documents

Publication Publication Date Title
EP1932118B2 (en) Method and apparatus for characterizing skin blemishes and method for assessing the anti-aging effect of a cosmetic product
JP5656162B2 (en) Method and apparatus for characterizing skin defects, and methods for evaluating the effectiveness of cosmetic agents, skin agents, or treatments for skin defects using agents
USRE47921E1 (en) Reflectance imaging and analysis for evaluating tissue pigmentation
FR2952216A1 (en) METHOD AND APPARATUS FOR ANALYZING HYPER-SPECTRAL IMAGES
US20190239752A1 (en) Hyperspectral imaging system and method of using the same
WO2013098512A1 (en) Method and device for detecting and quantifying cutaneous signs on an area of skin
FR2944899A1 (en) PROCESS AND APPARATUS FOR CHARACTERIZING PIGMENTARY TASKS AND METHOD OF ASSESSING THE EFFECT OF TREATING A PIGMENT TASK WITH A COSMETIC PRODUCT
WO2018153762A1 (en) Method, device and program for determining at least one cerebral network involved in carrying out a given process
WO2012098225A1 (en) Determination of the efficacy of a treatment
US10478071B2 (en) Medical imaging
CA2778676A1 (en) Device and method for adjusting the raised pattern of hyper-spectral images
WO2012098227A1 (en) Determination by independent component analysis of the efficacy of a treatment
Bratchenko et al. In vivo hyperspectral analysis of skin hemoglobin and melanin content for neoplasia detection
Lorencs et al. Melanoma-nevus discrimination based on image statistics in few spectral channels
FR2997536A1 (en) Method for estimation of differential index of severity of e.g. pathology, expressing cutaneous deterioration, involves determining differential index of severity among index of severity linked to contrast and cutaneous deterioration
FR3048800A1 (en) IMAGE PROCESSING METHOD
Sharma et al. SKIN TEXTURE RECOGNITION THROUGH IMAGE PROCESSING.
Magotra et al. HYPERSPECTRAL BIOMEDICAL IMAGER
Świtoński et al. Individual features of the skin spectra,"
Kamimura et al. Evaluation and analysis for spectral reflectance imaging of human skin
FR2944425A1 (en) Stimulus or cosmetic treatment pigmentation or action evaluating method for distribution of melanin in lucinol on three-dimensional human skin model, involves generating information representing action of stimulus/treatment based on result

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20130716

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

RIN1 Information on inventor provided before grant (corrected)

Inventor name: ZUGAJ, DIDIER

Inventor name: PRIGENT, SYLVAIN MERIADEC

Inventor name: DESCOMBES, XAVIER

Inventor name: ZERUBIA, JOSIANE

DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20140307