WO2018059662A1 - Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale - Google Patents

Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale Download PDF

Info

Publication number
WO2018059662A1
WO2018059662A1 PCT/EP2016/072953 EP2016072953W WO2018059662A1 WO 2018059662 A1 WO2018059662 A1 WO 2018059662A1 EP 2016072953 W EP2016072953 W EP 2016072953W WO 2018059662 A1 WO2018059662 A1 WO 2018059662A1
Authority
WO
WIPO (PCT)
Prior art keywords
spectrum
tissue
analysis device
filter
wavelength range
Prior art date
Application number
PCT/EP2016/072953
Other languages
German (de)
English (en)
Inventor
Thomas Engel
Maximilian Fleischer
Alexander Michael Gigler
Ralph Grothmann
Clemens Otte
Remigiusz Pastusiak
Tobias Paust
Elfriede Simon
Evamaria STÜTZ
Stefanie VOGL
Hans-Georg Zimmermann
Original Assignee
Siemens Aktiengesellschaft
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 Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Priority to PCT/EP2016/072953 priority Critical patent/WO2018059662A1/fr
Publication of WO2018059662A1 publication Critical patent/WO2018059662A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J3/2823—Imaging spectrometer
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3554—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for determining moisture content
    • G01N21/3559—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for determining moisture content in sheets, e.g. in paper
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J3/2823—Imaging spectrometer
    • G01J2003/2826—Multispectral imaging, e.g. filter imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J2003/283—Investigating the spectrum computer-interfaced
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J2003/283—Investigating the spectrum computer-interfaced
    • G01J2003/2836—Programming unit, i.e. source and date processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
    • G01J3/28—Investigating the spectrum
    • G01J2003/283—Investigating the spectrum computer-interfaced
    • G01J2003/284—Spectral construction

Definitions

  • tissue analysis or tissue analysis is becoming increasingly important.
  • a commonly practiced example of such tissue analysis is to determine whether a biological ⁇ MOORISH tissue is tumorous or healthy.
  • an infra red spectrum can be added to the tissue to be analyzed and the tissue based on the recorded spectrum, for example, are classified with ⁇ means of a data-driven analysis as healthy or tumorous.
  • known spectroscopic methods he currently do not usually reach a required for a medical diagnosis, high detection reliability of more than 95%.
  • the specific wavelength range can also be understood as a specific frequency range.
  • the analysis device has a predictive analyzer for deriving an indication of a predefined tissue property from the partial spectrum.
  • the predetermined tissue property can be a tumor infiltration of the tissue in particular.
  • the predictive analyzer is trained by a variety of limited to the wavelength range training spectra on a recognition of the tissue property.
  • the analyzer further comprises an output terminal for outputting the indication.
  • an electromagnetic Spekt ⁇ rum of the fabric is measured and extracted from the spectrum of a restricted to a specific wavelength range partial spectrum. Furthermore, an indication of a predetermined tissue property from the partial spectrum is derived by a predictive analyzer wherein the predictive analyzer is trained with ⁇ means of a plurality of limited to the wavelength range of training spectra to a detection of the tissue property. The specification is then output.
  • a computer program product and a computer-readable storage medium are furthermore provided.
  • the predictive analyzer is used to perform a so-called predictive analysis.
  • predictive analytics include a variety of data-driven analytics. driving machine learning and data mining.
  • the term predictive is not limited in this subject-specific context to a prediction of future events, but generally provides out from a not previously known information, here the given tissue property of a ⁇ with output data to derive here the partial spectrum.
  • Such a predictive analyzer is often referred to as a classifier.
  • An advantage of the invention is to be seen in particular in that, due to the restriction to the wavelength range, a spectral activity of substances which do not reliably correlate with a recognition of the tissue property can be masked out in a targeted manner, and thus recognition reliability can be considerably increased.
  • a predictive analyzer a-priori unknown correlations between a tissue property and a spectral activity of the tissue can be efficiently trained and recognized.
  • the invention can be applied non-invasively and allows rapid tissue analysis.
  • the predictive analyzer may include a data-driven trainable regression model, an artificial neural network, a support vector machine, a neighbor neighbor classifier, a PLSDA (Partial Least Squares
  • the spectrometer may preferably be an infrared spectrometer; in particular a near infrared (NIR) and / or medium infrared (MIR) spectrometer.
  • the spectrometer can also measure a spectrum in visible light.
  • Such spectrometers are usually inexpensive and compatible with commercial optics.
  • the filter may be set so that the wavelength range has no overlap with main spectral bands of water and / or blood.
  • the main spectral bands of the water are in particular at wavelengths of about 970 nm, about 1100 nm and about 1450 nm.
  • the main bands of water or blood correlate in the spectrum with the presence of water or blood in the examined tissue. But the latter usually correlates not reliable with eg the presence ei ⁇ nes tumor. Without filtering out the major bands of water or blood, tumorous tissue from edematous or heavily perfused healthy tissue is often difficult to distinguish.
  • the filter can be adjusted so that the wavelength range is between 1100 nm and 1450 nm.
  • a lower limit of the wavelength range of about 1100 nm, about 1130 nm, about 1160 nm or about 1177 nm and an upper limit of the wavelength range of about 1450 nm, about 1400 nm, about 1355 nm or about 1270 nm be provided.
  • the main bands of what ⁇ sers from the partial spectrum can be omitted in particular, resulting in a tissue detection rate is usually considerably increases.
  • the wavelength range of the limited training spectra can be varied to optimize a tissue recognition rate.
  • a particularly good training success ie a particularly high tissue recognition rate can be achieved if the wavelength range for the detection of tumors from about 1177 nm to about 1355 nm and for the detection of healthy tissue from about 1177 nm to ca 1270 nm.
  • the ⁇ after the wavelength range specific to the to be recognized Tissue property are tuned.
  • the resulting tissue-specific wavelength range, resulting in an optimized tissue recognition rate can then be output to set the filter to that wavelength range.
  • a preprocessor connected between the spectrometer and the filter can be provided for preprocessing the spectrum before it is transmitted to the filter.
  • the training spectra can be preprocessed in the same way as the spectrum by the preprocessor or by another preprocessor.
  • a preprocessor may also be provided between the filter and the predictive analyzer for preprocessing the restricted part spectrum and / or the restricted training spectra before they are transmitted to the predictive analyzer. Preprocessing can in many cases increase a tissue recognition rate.
  • the preprocessor can be set up to carry out a derivative of the spectrum in accordance with the wavelength during the preprocessing of the spectrum, ie to form a differential quotient, and to transmit the derived spectrum to the filter.
  • the derivative can advantageously be combined with a smoothing, for example by forming a moving average, by using a so-called moving Windows and / or by using a so-called Savitzky-Golay filter.
  • the derivation and possibly the smoothing of the spectrum can lead to significantly better detection rates in tissue analysis.
  • the downstream of the derivative filtering interfering in particular caused by the derivation artefacts at the edges of the wavelength range can be specifically hidden. As part of spectrum then limited to the wavelength range Ab ⁇ line of the spectrum is extracted.
  • the spectrometer for spatially resolved measurement of the spectrum and the output terminal for the spatially resolved outputting of the information about the tissue property can be set up. In this way, for example, an image of a tumor and / or a tumorous area of tissue can be visualized.
  • an endoscope or a surgical microscope can be provided with an analysis device according to the invention.
  • an optics of an endoscope or surgical microscope for transmitting optical spectra in general is well suited
  • an endoscope or a surgical microscope can be used in an advantageous manner for targeted detection of Ge ⁇ webespektrums.
  • the figure shows a schematic representation of an inventive analysis device.
  • an analysis device AE for analyzing a biological tissue G and in particular for determining a predetermined tissue property of the tissue G is shown schematically.
  • the tissue G may be eg bone tissue, muscle tissue, connective tissue, an organ or an organ part.
  • ⁇ telnde tissue characterization such as a phenotypic trait ⁇ tissue, tissue findings, a fabric structure, a fabric ⁇ type, a fabric texture, or other anatomical feature and / or its pathological or injury-related change may be predetermined.
  • the tissue property to be detected may be a tumor invasion of the tissue G.
  • the analysis device AE or an inventive procedural ren for operating the analyzing device AE, for example, by one or more processors, an effetsspe ⁇ zifischer integrated circuits (ASIC), digital signal processors (DSP) and / or so-called "field programmable
  • the analysis device AE comprises one or more processors PROC for carrying out all method steps of the analysis device AE and a memory MEM coupled to the processor PROC for storing by the analysis device AE processing data.
  • the analysis device AE has a spectrometer SPM for measuring an electromagnetic spectrum SP of the tissue G.
  • the spectrum SP can here be a reflection spectrum, a transmission spectrum, an absorption spectrum and / or a spectrum based on attenuated total reflection (ATR).
  • ATR attenuated total reflection
  • the Spektrome ⁇ ter SPM as operating in the near infrared NIR spectrometer is formed and the measured spectrum SP ent ⁇ speaking a NIR spectrum of the fabric G.
  • the spectrum SP can in this case be, for example, represented by a high-dimensional data vector for each Wavelength or frequency channel of the spectrometer SPM ent ⁇ an intensity value ent.
  • the spectrum SP measured by the spectrometer SPM also includes main spectral bands SPB of water, which are in particular at wavelengths of approximately 970 nm, 1100 nm and 1450 nm.
  • the main spectral bands SPB dominate - as indicated in the figure by two peaks - the spectrum SP due to the frequency of water in the tissue G.
  • the spectrometer SPM transmits the measured spectrum SP to a preprocessor PP of the analysis device AE coupled to the spectrometer SPM.
  • the preprocessor PP is connected between the spectrometer SPM and a filter F and serves to preprocess the spectrum SP before it is transmitted to the filter F.
  • a derivative of the spectrum SP according to the Wel lenide made ie it is determined a differential quotient.
  • the resulting derivative is transmitted by the preprocessor PP as a derived spectrum DSP to the filter F.
  • the derivative can advantageously be combined with a smoothing, for example by forming a moving average, by using a so-called moving Windows and / or by using a so-called Savitzky-Golay filter.
  • the derivation and, if necessary, smoothing of the spectrum SP can lead to significantly better detection rates in tissue analysis.
  • the main spectral bands SPB also form a dominant pattern in the derived spectrum DSP.
  • the filter F coupled to the preprocessor PP serves to extract a partial spectrum PSP restricted to a specific wavelength range WB from the derived spectrum DSP.
  • the specific wavelength range WB can also be understood as a frequency range.
  • the filter F may e.g. be designed as a frequency or wavelength filter as well as an analog or digital filter. In particular, the filter F specific frequency or wavelength channels or certain dimensions of the
  • the specific wavelength range WB extends over a region in which substances of the tissue G which would impair tissue analysis or detection are less spectrally active.
  • the wavelength range WB is selected such that the filter F is set such that the wavelength range WB has no overlap with main spectral bands of water and / or blood.
  • the main spectral bands SPB of the water at approximately 970 nm, approximately 1100 nm and approximately 1450 nm are recessed or masked out by the filter F.
  • a presence of water or blood does not correlate reli ⁇ transmissive in tissues G with a presence of a tumor is, by hiding this Hauptban- which greatly improves reliability of tissue recognition.
  • a lower limit of the wavelength range WB of approximately 1100 nm, approximately 1130 nm or approximately 1160 nm and an upper limit of the wavelength range WB of approximately 1450 nm or approximately 1400 nm can be provided.
  • This optimized Wellenhavenbe ⁇ rich WB extends for the detection of tumors of about 1177 nm to about 1355 nm and for the recognition of healthy tissue of about 1177 nm to about 1270 nm.
  • the Spectrum SP and in the derived spectrum DSP still dominating main spectral bands SPB outside the selected wavelength range WB and are ⁇ truncated by the filtering ⁇ .
  • the partial spectrum PSP extracted by the filter F from the derived spectrum DSP and restricted to the wavelength range WB is normalized by the filter F over the waveband WB, specifically to values between 0 and 1.
  • the normalization can increase the tissue recognition rate.
  • the partial spectrum PSP is then transmitted by the filter F to a predictive analyzer PA coupled to the filter of the analysis device AE.
  • the predictive analyzer PA is used to perform a predictive analysis in order to derive an indication A (G) about the tissue property from the partial spectrum PSP.
  • the specification A (G) characterizing the tissue property can, for example, a Ge ⁇ webetyp, a tissue state, a tumor invasion, a content of a specific substance or other chemical properties sheep ⁇ ten or even physical properties such as pressure, temperature, etc. relate.
  • the indication A (G) may comprise a discrete and / or continuous value.
  • the indication A (G) may be a simple yes / no classification, eg whether the tissue property or a medical finding present or not.
  • a (G) a distinction between tomorous or healthy tissue can be given.
  • the predictive analyzer PA performs a predictive analysis ⁇ method for deriving the indication A (G) from the partial spectrum PSP.
  • Such predictive analysis methods include a variety of statistical and / or data-driven method of predictive modeling, the machine-tional learning and data mining into ⁇ particular, to evaluate the predetermined input ⁇ data therein to recognize patterns or structures and / or around it to derive a priori unknown information or forecasts.
  • the predictive analyzer PA may include a trainable regression model, an artificial neural network, a support vector machine, a k nearest neighbor classifier, a PLSDA (Partial Least Squares Discriminant Analysis) classifier, a decision tree, and / or have a deep learning architecture.
  • PLSDA Partial Least Squares Discriminant Analysis
  • the predictive analyzer PA implements a linear predictive procedural ⁇ reindeer, here specifically a PLSDA method.
  • a linear predictive procedural ⁇ reindeer here specifically a PLSDA method.
  • the latter allows ei ⁇ ne considerable reduction in the number of dimensions to be dissolved Ausireproblems. Studies have shown that often suffice three to seven dimensions to egg ne very reliable indication A (G) from the partial spectrum PSP from ⁇ forward.
  • the predictive analyzer PA is trained beforehand by means of a large number of training spectra TSP (WB) supplied by the predictive analyzer PA to ensure the most reliable possible recognition of the tissue property.
  • the training spectra TSP (WB) supplied by the predictive analyzer PA to ensure the most reliable possible recognition of the tissue property.
  • TSP (WB) are tissue spectra of a plurality of different tissues, wherein the training spectra TSP (WB) pre-processed respectively in sliding ⁇ cher manner as the spectrum SP by a preprocessor, that is derived here and smoothed and ei ⁇ NEN filter for the wavelength range WB restricted and then normalized.
  • the training is to be understood - according to technical terminology - to be a mapping of input parameters of the predictive analyzer PA to one or more target variables, which is optimized according to predefinable criteria during a training phase.
  • a training structure TSR of the predictive analyzer PA which is optimized in accordance with the predetermined criteria is formed.
  • the training structure TSR may include, for example, a network structure of neurons of a neural network, weights of connections between the neurons and / or parameters of a regression model, which were formed by training so that the tissue property is detected as reliably as possible.
  • the wavelength range of the limited training to Spectra TSP can (WB) can be varied in order to identify those waveband WB, a particularly high tissue recognition rate can be achieved by.
  • the trained predictive analyzer PA which has a trained training structure TSR, derives the information A (G) from the transmitted partial spectrum PSP and transmits it to an output terminal T coupled to the predictive analyzer PA, which supplies the information A (G) a user from ⁇ gives.
  • the analysis unit AE can be integrated in a simple manner or in an endoscope or a surgical microscope, on the other ⁇ weitig coupled thereto, in that an optical system of a En ⁇ doskops or a surgical microscope for transmitting optical spectra is generally suitable.
  • an endoscope or a surgical microscope in vorteilhaf ⁇ ter manner for targeted detection of Gewebespekt ⁇ rums can be used by the analyzing means AE.
  • the reliability of tissue analysis can be significantly increased.
  • tumorous can be distinguished from healthy tissue with a high degree of certainty.
  • Likelihood of being less than 5% which in many cases should be sufficient for clinical
  • Another advantage is the fact that the analysis device AE can be applied non-invasively.
  • spectral measurements can be carried out very cost-effective in the near infrared and are compatible with the look of trade ⁇ conventional endoscopes or surgical microscopes.

Landscapes

  • Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • General Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Chemical & Material Sciences (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

Selon l'invention, il est prévu un spectromètre (SPM) pour mesurer un spectre électromagnétique (SP) d'un tissu (G) et un filtre (F) pour extraire du spectre (SP) un spectre partiel (PSP) limité à une plage de longueurs d'onde (WB) spécifique. En outre, un analyseur prédictif (PA) sert à déduire une indication (A) sur une propriété de tissu prédéfinie à partir du spectre partiel (PSP). L'analyseur prédictif (PA) est entraîné à l'aide d'une pluralité de spectres d'entraînement (TSP) limités à la plage de longueurs d'onde (WB) pour une détection de la propriété de tissu. Un terminal de sortie (T) est prévu pour fournir l'indication (A) déduite.
PCT/EP2016/072953 2016-09-27 2016-09-27 Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale WO2018059662A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2016/072953 WO2018059662A1 (fr) 2016-09-27 2016-09-27 Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2016/072953 WO2018059662A1 (fr) 2016-09-27 2016-09-27 Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale

Publications (1)

Publication Number Publication Date
WO2018059662A1 true WO2018059662A1 (fr) 2018-04-05

Family

ID=57083279

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2016/072953 WO2018059662A1 (fr) 2016-09-27 2016-09-27 Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale

Country Status (1)

Country Link
WO (1) WO2018059662A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11257213B2 (en) 2018-10-25 2022-02-22 Koninklijke Philips N.V. Tumor boundary reconstruction using hyperspectral imaging

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
FABELO HIMAR ET AL: "HELICoiD project: a new use of hyperspectral imaging for brain cancer detection in real-time during neurosurgical operations", SPIE - INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING. PROCEEDINGS, S P I E - INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING, US, vol. 9860, 10 May 2016 (2016-05-10), pages 986002 - 986002, XP060068374, ISSN: 0277-786X, ISBN: 978-1-5106-0753-8, DOI: 10.1117/12.2223075 *
FOCA GIORGIA ET AL: "Classification of pig fat samples from different subcutaneous layers by means of fast and non-destructive analytical techniques", FOOD RESEARCH INTERNATIONAL, ELSEVIER, AMSTERDAM, NL, vol. 52, no. 1, 18 March 2013 (2013-03-18), pages 185 - 197, XP028530797, ISSN: 0963-9969, DOI: 10.1016/J.FOODRES.2013.03.022 *
LU GUOLAN ET AL: "Medical hyperspectral imaging: a review", INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING, SPIE, PO BOX 10 BELLINGHAM WA 98227-0010 USA, vol. 19, no. 1, 1 January 2014 (2014-01-01), pages 10901, XP060047195, ISSN: 1083-3668, [retrieved on 20140120], DOI: 10.1117/1.JBO.19.1.010901 *
MARENA MANLEY: "Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials", CHEMICAL SOCIETY REVIEWS., vol. 43, no. 24, 1 January 2014 (2014-01-01), GB, pages 8200 - 8214, XP055378134, ISSN: 0306-0012, DOI: 10.1039/C4CS00062E *
PU HONGBIN ET AL: "Selection of feature wavelengths for developing multispectral imaging systems for quality, safety and authenticity of muscle foods-a review", TRENDS IN FOOD SCIENCE AND TECHNOLOGY, ELSEVIER SCIENCE PUBLISHERS, GB, vol. 45, no. 1, 3 June 2015 (2015-06-03), pages 86 - 104, XP029258280, ISSN: 0924-2244, DOI: 10.1016/J.TIFS.2015.05.006 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11257213B2 (en) 2018-10-25 2022-02-22 Koninklijke Philips N.V. Tumor boundary reconstruction using hyperspectral imaging

Similar Documents

Publication Publication Date Title
DE69637163T2 (de) Diagnose von zervix-praekanzerosen mittels raman- und fluoreszenz-spektroskopie
DE60114036T2 (de) Verfahren zur charakterisierung von spektrometern
DE60035899T2 (de) Klassifizierung and charakterisierung von gewebe durch merkmale bezüglich adiposegewebe
DE69027168T2 (de) Verfahren zum Vorhersagen der Eigenschaften biologischer Materie, unter Verwendung der Spektrumanalyse im Nah-Infrarot
EP3481275A1 (fr) Procédé et dispositif pour déterminer un degré de détérioration des cheveux et procédé pour déterminer un moyen pour traiter les cheveux spécifique à l'utilisateur
JP2004526141A (ja) 組織から得た広帯域弾性散乱スペクトルを処理する方法
EP2199791B1 (fr) Méthode pour evaluer l'hémolyse dans les érythrocytes et dispositif associé
EP3668375A1 (fr) Système et procédé pour déterminer un état des cheveux
EP3540632A1 (fr) Procédé et appareil d'analyse destinés à la classification des échantillons tissulaires
DE60308864T2 (de) Verfahren der Resonanz-Spektroskopie für die Analyse von statistischen Eigenschaften von Proben
WO2018059662A1 (fr) Sélection de longueur d'onde dans la classification de tissus par imagerie hyperspectrale
DE102019113283B4 (de) Vorrichtung zur Abbildungserzeugung von Hautläsionen
WO2018050802A1 (fr) Procédé de classification de spectres d'objets à contenu d'information complexe
Wang Raman spectroscopic characterization and analysis of agricultural and biological systems
EP3707496B1 (fr) Identification d'au moins une caractéristique spectrale dans un spectre d'un échantillon pour analyse de constituants
EP2635882B1 (fr) Procédé de détermination de constituants chimiques de substances solides ou liquides par spectroscopie thz
EP3126819B1 (fr) Dispositif et procédé servant à analyser un échantillon afin de diagnostiquer une tumeur de la prostate
EP3359954A1 (fr) Dispositif et procédé pour déceler et/ou évaluer des états pathologiques
AT505523B1 (de) Verfahren und anordnung zur status-erfassung von hautgewebe
EP3488281B1 (fr) Détermination d'un type de tissu animal ou humain
WO2018059668A1 (fr) Dispositif d'analyse et procédé pour l'analyse d'un tissu biologique
DE102014105994A1 (de) Verfahren zur Erkennung von Signalmustern in spektroskopisch erzeugten Datensätzen
EP1219919B1 (fr) Procédé, dispositif et système pour la détermination des grandeurs d' un processus
DE60126600T2 (de) Analyseverfahren für stoffmischungen
DE19638839A1 (de) Verfahren zur Bestimmung der Entstehungszeit von Hämatomen

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16777625

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16777625

Country of ref document: EP

Kind code of ref document: A1