WO2015146164A1 - 放射線照射による皮膚変化予測装置と検証装置 - Google Patents
放射線照射による皮膚変化予測装置と検証装置 Download PDFInfo
- Publication number
- WO2015146164A1 WO2015146164A1 PCT/JP2015/001692 JP2015001692W WO2015146164A1 WO 2015146164 A1 WO2015146164 A1 WO 2015146164A1 JP 2015001692 W JP2015001692 W JP 2015001692W WO 2015146164 A1 WO2015146164 A1 WO 2015146164A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- skin
- change
- unit
- radiation
- image
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/1048—Monitoring, verifying, controlling systems and methods
- A61N5/1071—Monitoring, verifying, controlling systems and methods for verifying the dose delivered by the treatment plan
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1032—Determining colour for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/445—Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/103—Treatment planning systems
-
- 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
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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 present invention provides, for example, a skin change prediction apparatus and a skin change prediction program by radiation irradiation that predict skin changes due to radiation irradiation in advance, and a verification apparatus and verification program for verifying a prediction result and an actual skin change.
- a skin change prediction apparatus and a skin change prediction program by radiation irradiation that predict skin changes due to radiation irradiation in advance and a verification apparatus and verification program for verifying a prediction result and an actual skin change.
- the skin after radiation treatment is inflamed red due to an acute skin reaction in the radiation irradiation area. Therefore, the radiation dose administered to the tumor by radiation therapy is limited by this skin reaction.
- This skin reaction is also closely related to the quality of life (QOL) of the patient after treatment. For this reason, if the skin reaction produced by radiotherapy can be predicted in advance, it is possible to easily determine the radiation dose to be irradiated in the treatment and improve the quality of life of the patient after the treatment.
- Patent Literature 1 a radiation monitoring system for radiotherapy was proposed (see Patent Literature 1). This system is intended to estimate the absorbed dose of radiation that is exposed to a patient undergoing radiation therapy.
- this system is intended to measure the absorbed dose of the actually irradiated radiation, and is not intended to predict the skin reaction due to radiation irradiation in advance.
- the present invention provides a skin change prediction device by radiation irradiation, a verification device, a skin change prediction program by radiation irradiation, and a verification program capable of accurately predicting a skin reaction due to radiation irradiation in advance.
- the present invention relates to a radiation information receiving unit that receives input of radiation information of radiation to be irradiated, a skin image acquisition unit that acquires a skin image obtained by photographing the skin of a living body, and the radiation that is determined by the radiation information.
- Skin change prediction device by radiation irradiation comprising: a change calculation unit that calculates a skin change and obtains a predicted skin image after change from the skin image; and an output unit that outputs the predicted skin image, and verification using the same It is characterized by being an apparatus and these programs.
- a skin change prediction device a verification device, a skin change prediction program by radiation irradiation, and a verification program capable of accurately predicting a skin reaction by radiation irradiation in advance.
- the block diagram which shows the structure of a skin change prediction system. Explanatory drawing of the grade determination by radiation irradiation. Explanatory drawing of skin change.
- the block diagram which shows the structure of a skin change verification system.
- Explanatory drawing which shows the image for verification of an irradiation area
- the skin reaction due to irradiation is generally expressed by the following four grades.
- Grade 1 Mild erythema
- Grade 2 Strong erythema
- Grade 3 Blister
- Bilan Grade 4 Ulcer
- the inventors have studied a method capable of accurately predicting the skin reaction caused by irradiation before the radiation treatment. Initially, paying attention to the fact that the skin becomes red due to the skin reaction, the radiation dose (hereinafter referred to as skin dose) that the skin is exposed to by extracting the R component (red component) from the RGB representation image captured by the camera. We investigated the relationship between skin and skin reaction and examined the creation of skin images after irradiation.
- skin dose the radiation dose that the skin is exposed to by extracting the R component (red component) from the RGB representation image captured by the camera.
- the skin dose does not necessarily correspond to the amount of change in the R component. It was. For this reason, it has been very difficult to separate the components from the skin image obtained by photographing the skin before the radiation irradiation and to accurately create the skin image after the skin reaction by the radiation irradiation.
- the reaction in which the skin is inflamed in red is the result of a biological reaction in which capillaries near the skin surface are expanded to increase blood flow in order to repair damaged cells.
- the inventors focused on the possibility that the hemoglobin flow rate, which is a pigment in blood, and the degree of skin reaction that appears as red inflammation may be correlated.
- the relationship between the skin dose and the skin reaction may be quantitatively grasped.
- Tsumura N, et al . Image-based skin color and texture analysis / synthesis by structuring hemoglobin and melanin informatin.
- the inventors convert the skin image (reflected light) in the RGB expression format obtained by photographing the skin into a biological element expression format expressed by a biological element (absorption component) such as a hemoglobin component, and the hemoglobin component Applying the hemoglobin flow rate change amount corresponding to the skin dose due to the radiation to be irradiated and returning the skin image from the biological element representation format to the RGB representation format, the predicted skin image predicted skin reaction according to the skin dose Created successfully.
- a biological element such as a hemoglobin component
- FIG. 1 is a block diagram showing a configuration of a skin change prediction system 1
- FIG. 2 is an explanatory diagram of grade determination by radiation irradiation
- FIG. 3 is an explanatory diagram of skin change.
- the skin change prediction system 1 includes a camera 2 that is a photographing device, a display input device 3 that is a personal computer, and a skin change prediction device 4 that is a personal computer.
- a camera 2 that is a photographing device
- a display input device 3 that is a personal computer
- a skin change prediction device 4 that is a personal computer.
- Each image in FIG. 3 is originally a color image, but in order to make the difference easily understandable on a patent drawing that is a monochrome image, all of the images have a higher density than the actual one.
- the camera 2 transmits captured image data (skin image color component data) obtained by photographing the skin of a living body to the display input device 3.
- This photographed image data is skin image data in the RGB expression format shown in FIG. 3A (shown in black and white, but is actually a color image).
- the captured image data acquired here needs to have a certain degree of uniformity in the amount of illumination hitting the skin to be imaged as the imaging environment. This uniformity does not need to be exact and may be such that there is no unnatural non-uniformity.
- the color components of the photographed image are the three primary colors of light (RGB expression format), the R component (red), the G component (green), and the B component (blue color), or the three primary colors of colors (SMY expression format).
- Component (cyan), M component (magenta), and Y component (yellow), or C component (cyan), M component (magenta), Y component (yellow), and K component which are four primary colors (CMYK expression format) of printing (Black) and the like, which can be configured with an appropriate component that expresses a color.
- three primary colors of light are used as preferable color components.
- the display input device 3 includes a keyboard that receives operation inputs, an input unit such as a mouse or a touch panel, a display unit such as a liquid crystal display or a CRT monitor that displays an image, a storage unit such as a hard disk that stores data and programs, A CPU, a ROM, and a RAM control unit that perform various operations and calculations in accordance with a program, and a connection interface such as a USB that is connected to an external device such as the camera 2 and the skin change prediction device 4 to transmit and receive data.
- a keyboard that receives operation inputs
- an input unit such as a mouse or a touch panel
- a display unit such as a liquid crystal display or a CRT monitor that displays an image
- a storage unit such as a hard disk that stores data and programs
- a CPU, a ROM, and a RAM control unit that perform various operations and calculations in accordance with a program
- a connection interface such as a USB that is connected to an external device such as the camera 2 and the skin change prediction
- the display input device 3 displays a skin dose, an irradiation region, and a test region by displaying a process of transmitting the captured image data received from the camera 2 to the skin change prediction device 4, an input screen including the captured image and the input unit.
- a process of inputting, a process of transmitting the input skin dose, irradiation area, and test area to the skin change prediction apparatus 4 is executed.
- the skin change prediction device 4 includes at least a storage unit that stores a program and data, a CPU that performs various operations and calculations according to the program, and a connection interface such as a USB that connects an external device such as the display input device 3. Yes.
- a skin change prediction program is installed from the recording medium 9 in the storage unit.
- the skin change prediction device 4 may further include an input unit, a display unit, and the like, like the display input device 3.
- the skin change prediction device 4 is also an image processing device that performs image processing.
- the skin change prediction apparatus 4 includes a radiation information reception unit 11 (factor information reception unit), a change amount correspondence data 12, a change amount determination unit 13, and a grade determination unit 14 as processing function units in which the control unit operates according to a program in the storage unit.
- Grade correspondence data 15, grade output unit 16, irradiation region reception unit 17, pre-irradiation skin image acquisition unit 21 (skin image acquisition unit), skin region extraction unit 211, expression format conversion unit 22, image change unit 23, expression format Restoration unit 24, predicted skin image output unit 25, test region image acquisition unit 31, skin region extraction unit 311, principal component analysis unit 32, independent component analysis unit 33, pigment vector suitability determination unit 34, pigment vector determination unit 35, And dye vector standard data 36.
- the expression format conversion unit 22, the change amount determination unit 13, the image change unit 23, and the expression format restoration unit 24 function as a change calculation unit that calculates a skin change due to radiation irradiation.
- the radiation information receiving unit 11 receives input of radiation information (factor information) in the radiation treatment plan by the display input device 3.
- the reception of the radiation information may be executed by an appropriate method such as manually input, input from an information medium such as USB, or received from the treatment planning apparatus via a communication unit.
- the radiation information received at this time requires at least a radiation type and a dose, and further requires a radiation quality depending on the radiation type. Specifically, if the radiation type is X-ray, an input of dose is accepted. If the radiation type is a charged particle beam (heavy ion particles including protons and carbon), input of dose and radiation quality is accepted.
- the dose is expressed as a physically measurable absorbed dose (unit: Gray (Gy), or clinical dose (unit: Gy (RBE)) multiplied by the biological effect ratio (RBE) as an index of clinical effect. It is expressed as the amount of energy applied per unit length of particle (LET or linear energy, unit: keV / micrometer), and the radiation information includes the elapsed time (elapsed days) from the reference date with respect to the timing of radiation irradiation.
- the term “skin dose” is used to indicate a dose if it is an X-ray, and to indicate a dose and a quality if it is a charged particle beam.
- the change amount correspondence data 12 is data in which the skin dose and the change amount of the hemoglobin flow rate are associated with each other.
- This data can be data in an appropriate format such as table data in which numerical values of skin dose and hemoglobin flow rate are associated with each other, or calculation data in which hemoglobin flow rate is calculated when skin dose is input.
- the change correspondence data 12 is created and registered in advance using clinical data in which the amount of hemoglobin in the irradiation region before and after irradiation of the skin dose is measured by a measuring device such as a laser blood flow meter. It is a thing.
- FIG. 2A is a graph plotting measurement results of changes in H (x, y), which is a pixel value of a hemoglobin dye image, and a hemoglobin flow rate (skin blood flow rate).
- H x, y
- hemoglobin flow rate skin blood flow rate
- the error band illustrated by the dotted line in the figure is summed to the square of the error of 15% pixel value caused by the illumination environment, the error of 0.2 ml / min / 100 g caused by blood flow measurement, and the error caused by fitting. It has been calculated.
- the error caused by the blood flow measurement is mainly due to a biological effect due to the heartbeat.
- FIG. 2 (B) is a graph plotting data on the relationship between skin dose and hemoglobin flow rate. This quantitative relationship is an important relationship for quantifying the degree of skin erythema in skin disorders.
- the filled symbol in the graph is data directly measured by a laser blood flow meter, and the hollow symbol is a hemoglobin flow rate (blood flow rate) obtained by converting from a pixel value obtained by image analysis using the relational expression in FIG. ).
- a slope of 0.205 (18) ml / min / 100 g / Gy (RBE) was obtained.
- the correlation coefficient is 0.75 in the case of only laser data, and 0.60 in the case of all data including images, and a correlation is recognized.
- the error band shown by the dotted line in the figure is calculated by summing the error of 0.2 ml / min / 100 g resulting from blood flow measurement and the error due to fitting to the square.
- the slope of change in hemoglobin flow rate (skin blood flow) with respect to the pixel value of the hemoglobin dye image is 0.0139 (20) (ml / min 100 g) ⁇ 1 , and the slope of skin dose with respect to the hemoglobin flow rate. 0.205 (18) ml / min / 100 g / Gy (RBE) is used as the change amount corresponding data 12.
- the pixel value in the hemoglobin dye image can be estimated from the change amount, and conversely, the pixel value change amount in the hemoglobin dye image can be estimated from the skin dose.
- the change amount determination unit 13 determines a change amount for changing the hemoglobin flow rate based on the radiation information acquired from the radiation information reception unit 11 and the change amount correspondence data 12. The determined change amount is transmitted to the image change unit 23.
- the grade determination unit 14 determines a grade based on the radiation information received from the radiation information reception unit 11 via the change amount determination unit 13 and the grade correspondence data 15.
- the grade to be determined at this time is a detailed grade with high accuracy, for example, a conventional four-stage grade is changed to a 40-stage grade that is further increased to 10 times the definition.
- the grade determination unit 14 transmits the determined grade to the grade output unit 16.
- the grade correspondence data 15 is data for associating radiation information with grades, and is data in an appropriate format such as tabular data or an arithmetic expression for obtaining a solution by substituting numerical values of radiation information. It can be.
- FIGS. 2C and 2D are graphs showing the relationship between the hemoglobin flow rate (blood flow rate) that can be calculated from the pixel value change amount and the grade determination, and the first vertical axis (the vertical axis on the left side in the drawing).
- the axis) represents hemoglobin flow (blood flow), and the horizontal axis represents grade.
- the second vertical axis (right vertical axis in the figure) in FIG. 2C indicates the amount of change in pixel value
- the second vertical axis (right vertical axis in the figure) in FIG. 2D indicates the skin dose.
- the grade correspondence data 15 when the hemoglobin flow rate (blood flow) increased by 6.4 ml / min / 100 g or more, the grade was determined to be 2 or more. Further, in this embodiment, by using a conversion coefficient with hemoglobin flow rate change (blood flow rate change), a pixel value change amount and a skin dose corresponding to a grade 1/2 boundary line can be calculated, and 0.09 and 32 Gy, respectively. Presumed to be about (RBE). The error in this case is + -20%.
- the threshold for grade determination is not limited to the above numerical values, and can be determined as appropriate. What is important is that, as shown in the graph, each of hemoglobin flow rate (blood flow rate), skin dose, and pixel value change amount is quantitatively associated with a precise grade value 1: 1.
- the grade output unit 16 transmits the grade obtained by the grade determination unit 14 to the display input device 3 and displays it on the display input device 3 as a grade display screen.
- the irradiation region receiving unit 17 receives from the display input device 3 an input of an irradiation region that is irradiated with radiation in the radiation treatment plan in the skin of the living body.
- the irradiation area receiving unit 17 transmits the received irradiation area to the image changing unit 23.
- the pre-irradiation skin image acquisition unit 21 acquires pre-irradiation skin image data obtained by photographing the skin before radiation irradiation from the display input device 3. Since this pre-irradiation skin image data is in the RGB representation format, it can be easily separated into an R component, a G component, and a B component. The pre-irradiation skin image acquisition unit 21 transmits the separable pre-irradiation skin image data to the expression format conversion unit 22.
- the skin region extraction unit 211 extracts a skin region (skin region) from the pre-irradiation skin image data acquired by the pre-irradiation skin image acquisition unit 21.
- the extraction of the skin region is executed by extracting pixels satisfying the skin region condition from the pixels of the pre-irradiation skin image data.
- the skin region condition is a pixel that satisfies all the following conditions in the RGB representation format.
- R represents the concentration of the R component (for example, 0 to 255).
- G represents the concentration of the G component (for example, 0 to 255).
- B represents the concentration of the B component (for example, 0 to 255).
- R_th is a predetermined value, and can be set to 100 to 160, for example, or 10. Note that R_th can be 10 or more, preferably 50 or more, and more preferably 100 or more.
- R_th is preferably 200 or less, and more preferably 160 or less.
- R_ratio1 is a predetermined value, and may be an appropriate value such as 1.1 or 1.0.
- R_ratio1 is preferably 0.5 to 1.5, more preferably 0.9 to 1.2, and still more preferably 1.0 to 1.1.
- R_ratio2 is a predetermined value, and may be an appropriate value such as 1.1 or 1.0.
- R_ratio2 is preferably 0.5 to 1.5, more preferably 0.9 to 1.2, and still more preferably 1.0 to 1.1.
- the photographing conditions for obtaining an appropriate image according to the above-described skin region extraction conditions are (1) bright enough to recognize the skin color, and (2) the skin without unnatural shadows or overexposure. There are only two points: the area is illuminated. If the conditions of these two points can be cleared, the extraction of the skin area is performed satisfactorily. In condition (2), it is more preferable that the skin region is illuminated substantially uniformly.
- the expression format conversion unit 22 converts the acquired pre-irradiation skin image data (extracted skin region) from the RGB expression format to the pigment vector expression format. This conversion is executed by using the dye vector received from the dye vector determination unit 35.
- the pigment vector refers to a hemoglobin vector and a melanin vector in the present embodiment.
- information is separated into three components, a hemoglobin component, a melanin component, and other components. Details of the change of the expression format by the expression format converter 22 will be described later.
- the image changing unit 23 determines the change determined by the change amount determining unit 13 for the irradiation region determined by the irradiation region receiving unit 17 among the hemoglobin components extracted by the expression format conversion unit 22 from the pre-irradiation skin image data. Apply the amount to change the hemoglobin component of the irradiated area. Details of the image changing process by the image changing unit 23 will be described later.
- the expression format restoration unit 24 restores the expression format by converting the image data (skin image biological element component data) of the pigment vector expression format after being changed by the change amount determination unit 13 into the RGB expression format. .
- the representation format restoration unit 24 transmits the restored RGB representation format image data to the predicted skin image output unit 25 as a predicted skin image.
- the predicted skin image output unit 25 transmits the received predicted skin image to the display input device 3 for display.
- the test area image acquisition unit 31 acquires the test area input by the display input device 3.
- This test area is an area where a part of the photographed skin image is selected, and can be an appropriate area, for example, a small area of 100 pixels ⁇ 100 pixels.
- the skin region extraction unit 311 performs the same operation as the skin region extraction unit 211 on the skin image of the test region, and extracts a skin image.
- the skin region extraction unit 311 may not be provided, and the test region image acquisition unit 31 may extract the test region from the skin region extracted by the skin region extraction unit 211.
- the principal component analysis unit 32 performs principal component analysis (a kind of multivariate analysis) on the skin image (skin region extracted) of the test region.
- the principal component analysis unit 32 takes out the coordinate axis (first axis of the first component) of the principal component in the direction with the highest correlation (the direction with the widest distribution), and thereafter, a plane (multidimensional The operation of extracting the n-th axis of the n-th component is repeated in the direction with the highest correlation (the direction with the widest distribution) on the plane at (5).
- the calculated result can express 98% or more by the two axes of the first component (first axis) having the highest correlation and the second component (second axis) orthogonal to the first component.
- (Note) (r 0 , g 0 , b 0 ) indicates a skin color base color.
- r ave , g ave , and b ave indicate average values after subtracting the values of (r 0 , g 0 , b 0 ) from the values of (r, g, b) in the image.
- pc1 is the first component
- pc2 is the second component
- pc3 is the third component.
- R 1 , g 1 , b 1 is a vector representing the first component.
- R 2 , g 2 , b 2 is a vector representing the second component.
- R 3 , g 3 , b 3 is a vector representing the third component.
- Each vector is normalized to 1 and is orthogonal to each other, so that the inner product of each vector is zero.
- the independent component analysis unit 33 performs independent component analysis (a kind of multivariate analysis) on the data expressed by the first component and the second component obtained by the principal component analysis unit 32, and each axis is most independent. Takes two non-orthogonal coordinate axes that result in a distorted state. As for each component of the obtained coordinate axes, one component is a hemoglobin vector, and the other component is a melanin vector.
- independent component analysis a kind of multivariate analysis
- r ave , g ave , and b ave are average values after subtracting the values of (r 0 , g 0 , b 0 ) from the values of (r, g, b) in the image.
- (R h , g h , b h ) represents a hemoglobin vector.
- R m , g m , b m represents a melanin vector.
- h is a coefficient indicating the amount of hemoglobin (hemoglobin coordinates).
- m is a coefficient indicating the amount of melanin (melanin coordinates). The reason why the approximate equal sign is used instead of the equal sign is that the third component is ignored.
- each dye vector is normalized to 1, but there is no orthogonal relationship between the dye vectors.
- equation (1) and (Equation 2) In average r ave, g ave, although clearly denoted that the b ave added to each component, the average value r ave, g ave, the b ave They may be included in R 0 , B 0 , G 0 in the expressions of (Equation 1) and (Equation 2) and expressed in a form that is not visible on the expression. Even in this case, since the mathematical expressions have the same meaning, the RGB representation format can be converted to a biological element representation format using a hemoglobin vector or the like.
- the pigment vector suitability determination unit 34 determines whether or not the obtained pigment vector is appropriate. More specifically, the test region acquired by the test region image acquisition unit 31 is selected as hemoglobin and melanin as the first component and the second component by the principal component analysis unit 32 and separated as independent components by the independent component analysis unit 33. It must be something to give you. In order to determine whether or not such a test area has been input by the operator through the display input device 3, the dye vector appropriateness determination unit 34 determines whether or not the obtained dye vectors are a hemoglobin vector and a melanin vector. Determine.
- the pigment vector determination unit 35 determines the hemoglobin vector and melanin vector transmitted from the independent component analysis unit 33 as the pigment vector if the determination result by the pigment vector appropriateness determination unit 34 is “appropriate”. If the determination result by the dye vector appropriateness determination unit 34 is “inappropriate”, the dye vector determination unit 35 acquires a standard hemoglobin vector and a melanin vector from the dye vector standard data 36, and uses this as a dye vector. decide. The pigment vector determination unit 35 transmits the determined hemoglobin vector and melanin vector to the expression format conversion unit 22. In this embodiment, the dye vector standard data 36 is used if it is inappropriate once. However, the present invention is not limited to this, and the process from acquisition of a test area to determination of suitability may be repeated a plurality of times, and may be repeated a predetermined number of times. If all are inappropriate, the dye vector standard data 36 may be used.
- the pigment vector standard data 36 stores standard pigment vectors (hemoglobin vector and melanin vector) calculated in advance.
- the expression format conversion unit 22 uses the pigment vector obtained by the independent component analysis unit 33 to represent the three components (r, g, b) in the following equation (Equation 3) (h, m, s ) Is linearly transformed (coordinate transformed) into the three components.
- s is a coefficient of the unit vector (shadow vector) of illumination, and corresponds to the information that has been pushed in all the information that cannot be expressed by the pigment vector by hemoglobin and melanin.
- H (x, y), M (x, y), and S (x, y) can be expressed by the following (Equation 5).
- h ave , m ave , and s ave are average values of h, m, and s components.
- the average value can be an appropriate average value such as the average value of the entire image, but is preferably an average value calculated from RGB components only in the region representing the skin. Therefore, in this embodiment, the average value of RGB of the skin region is used.
- Equation 5 H (x, y), m (x, y), and s (x, y) in (Equation 5) are the same as the first component obtained by performing the principal component analysis shown in (Equation 1) described above. Using the two-component principal component vector, the following equation (6) is used.
- the skin image shown in FIG. 3 (A) is converted into the hemoglobin component skin image shown in FIG. 3 (B), the melanin component skin image shown in FIG. 3 (C), and shown in FIG. 3 (D).
- Other components are separated into skin images.
- FIG. 3B is a light red single color scale image
- FIG. 3C is a light ocher single color scale image
- 3 (D) is a light gray single color scale image (gray scale image).
- 3 (B) to 3 (D) is an image when converted without performing skin region extraction.
- the average If skin region extraction is performed on the values r ave , g ave , and b ave , a better hemoglobin component skin image can be obtained (see FIG. 7 described later).
- a pigment component composed of a hemoglobin component and a melanin component is used as a biological element component.
- the present invention is not limited to this, and other components may be used.
- it can be a hemoglobin component, a eumelanin component, a pheomelanin component, a carotene component, or a plurality of these, and the eumelanin component and the pheomelanin component can be combined into a melanin component.
- the biological element component has at least a hemoglobin component.
- the image changing unit 23 increases the change amount (hemoglobin increase amount) determined by the change amount determining unit 13 with respect to the h component in the equation (Equation 3).
- the predicted skin image in FIG. 3E is a monochrome image as a patent drawing, but is actually a color image.
- the example of FIG. 3 (E) shows a predicted skin image when radiation is irradiated to each of the rectangular first irradiation region 41 and the rectangular second irradiation region 42 that partially overlaps the first irradiation region 41. Yes.
- the first irradiation area 41 and the second irradiation area 42 are areas received by the irradiation area receiving unit 17.
- the first irradiation area 41 is displayed darker (red) than the second irradiation area 42 because the skin dose is higher than that of the second irradiation area 42, and the first irradiation area 41 and the second irradiation area 42 are displayed.
- the overlapping overlapping irradiation region 43 is displayed darker (red).
- the display input device 3 and the skin change prediction device 4 are configured as separate devices, but may be configured as a single device. In this case, it can be configured as one computer.
- a display input unit 3 such as a display input unit such as a touch panel monitor or an input unit such as a keyboard or a mouse and a display unit such as a liquid crystal display or a CRT monitor can be used.
- the control unit and the storage unit can be the skin change prediction device 4.
- the display input device 3 and the skin change prediction device 4 can be configured by one computer.
- FIG. 4 is a screen configuration diagram of the grade determination screen 50 that the grade output unit 16 outputs to the display input device 3 and displays.
- the grade determination screen 50 includes a predicted grade value display section 51, a predicted grade scale display section 52, an acute phase score display section 56, and a skin reaction display section 58.
- the predicted grade value display unit 51 displays the grade value determined by the grade determination unit 14. This grade value is a value that can indicate a finer level than the conventional four levels of 1 to 4, and is displayed in, for example, 40 levels from 0.1 to 4.0.
- the detailed stage of this grade value is a stage where it is clear from where to where the conventional four stages enter.
- the grade according to the present invention (hereinafter referred to as a new grade) is 0.1. Up to 1.0 corresponds to the conventional grade 1, the new grade 1.1 to 2.0 corresponds to the conventional grade 2, and the new grade 2.1 to 3.0 corresponds to the conventional grade 3.
- the new grades 3.1 to 4.0 correspond to the conventional grade 4.
- the predicted grade scale display unit 52 indicates a scale that is obtained by finely dividing the conventional grade in accordance with the new grade, and displays a predicted value mark 53 that indicates the scale.
- the predicted value mark 53 includes a predicted value specifying unit 54 that accurately indicates the predicted value, and an error range display unit 55 that indicates a range in which an error can occur from the predicted value.
- the error range display unit 55 has a wide range of reports in which the scales of the predicted grade scale display unit 52 are arranged, and the predicted value mark 53 is provided so as to overlap the inside thereof, so that the median of the predicted value and the error range Can be intuitively recognized.
- the error displayed on the error range display unit 55 can be determined by an appropriate method such as setting a predetermined range or obtaining it by calculation each time.
- an error for example, 15% depending on the imaging environment is added to an error (for example, 15%) of the hemoglobin amount measured by a laser blood flow meter (for example, 10% to 15%). 18% to 21%).
- the acute phase score display unit 56 indicates conventional grades 1 to 4, and the skin reaction display unit 58 displays “slight erythema”, “strong erythema”, “water bubbles,” skin reactions corresponding to the conventional grades 1 to 4. “Billan” and “ulcer” are displayed according to the grade.
- the acute phase score display unit 56 and the skin reaction display unit 58 perform a differentiated display 58 such as displaying the grade portion where the predicted new grade is located in color. As a result, it is possible to easily grasp which grade corresponds to the conventional grade.
- FIG. 5 is a block diagram showing a configuration of a skin change verification system 10 in which a verification device 6 is added to the skin change prediction system 1 described so far.
- the verification device 6 includes a predicted skin image acquisition unit 61, a post-irradiation skin image acquisition unit 62, a comparison verification unit 63, and a verification result output unit 64.
- the verification device 6 includes a storage unit that stores at least a program and data, a CPU that performs various operations and calculations according to the program, and a connection interface such as a USB that connects an external device such as the skin change prediction device 4. .
- a verification program is installed from the recording medium 9 in the storage unit of the verification device 6.
- the verification device 6 may be hardware different from the skin change prediction device 4, but may be configured by mounting the function on the same hardware as the skin change prediction device 4.
- the predicted skin image acquisition unit 61 acquires a predicted skin image from the predicted skin image output unit 25 (see FIG. 1) of the skin change prediction device 4.
- the post-irradiation skin image acquisition unit 62 acquires the post-irradiation skin image obtained by photographing the skin with the camera 2 after the radiation irradiation via the display input unit 3.
- the comparison verification unit 63 compares the predicted skin image received from the predicted skin image acquisition unit 61 with the post-irradiation skin image received from the post-irradiation skin image acquisition unit 62, and the suitability of the irradiation region and skin change for the radiation irradiation plan To verify. Specifically, the degree of coincidence between the region where the skin reaction is caused by the radiation irradiation and the irradiation region in the radiation irradiation plan is calculated, and the suitability is determined based on whether or not the degree of coincidence is within a predetermined range.
- the predicted skin image received from the predicted skin image acquisition unit 61 is an image predicted based on radiation information and the like planned by a separate treatment planning apparatus. For this reason, there is no need for the radiation information regarding the treatment plan at this time, but a configuration in which the radiation information is obtained and compared in more detail may be employed.
- the degree of coincidence between the degree of color difference from the surrounding skin due to the skin reaction and the degree of color change due to the radiation treatment plan is calculated, and the suitability is determined by whether or not the degree of coincidence is within a predetermined range.
- the color change coincidence is calculated by directly comparing the predicted skin image and the post-irradiation skin image, or by converting into the color vector expression by the above-described expression format conversion unit 22 and comparing only the hemoglobin component. For example, an appropriate configuration can be adopted.
- the verification result output unit 64 outputs the suitability determination and the matching degree, which are the results verified by the comparison verification unit 63, to the display input device 3 for display. At this time, the verification result output unit 64 also displays a verification image described next with reference to FIG. Each image in FIG. 6 is originally a color image, but in order to make the difference easy to understand on a patent drawing that is a monochrome image, all the images have a higher density than the actual one.
- FIG. 6 is an explanatory diagram showing an image for verification of an irradiation area.
- FIG. 6A is a skin dose distribution image showing the skin dose distribution calculated from the treatment plan. In the illustrated example, a prescription dose of 12.5 Gy (RBE) per gate is irradiated from two directions, and the skin dose 22 Gy (RBE) of the portion where the dual gate irradiation overlaps is 100%.
- FIG. 6B is a post-irradiation skin image photographed after irradiation according to the treatment plan shown in FIG. In this post-irradiation skin image, the rectangular white frame portion in FIG.
- FIG. 6C is a hemoglobin pigment image obtained by pigment decomposition of the skin image after irradiation.
- FIG. 6A is a skin dose distribution image showing the skin dose distribution calculated from the treatment plan. In the illustrated example, a prescription dose of 12.5 Gy (RBE) per gate is irradiated from two directions, and the skin dose 22 Gy (RBE) of the portion where the
- FIG. 6D is an explanatory diagram for explaining an irradiation region in FIGS. 6A to 6C.
- the irradiation of the present embodiment there are a first irradiation region 71, a second irradiation region 75, and an overlapping irradiation region 73 that is an overlapping portion of the first irradiation region 71 and the second irradiation region 75. Yes.
- the verification result output unit 64 by outputting each image shown in FIGS. 6A to 6C by the verification result output unit 64, the skin dose distribution image in the treatment plan of FIG. 6A and FIG. It is possible to verify whether or not appropriate irradiation was achieved as planned by comparing the hemoglobin dye images after treatment.
- the comparison verification part 63 and the verification result output part 64 are the predicted skin image estimated from the skin dose distribution image (refer FIG. 6 (A)) in a treatment plan, and the skin image after irradiation (the hemoglobin pigment image of FIG. 6 (C)). ) Are displayed side by side on the display / input device 3, and it is possible to receive the propriety that is finally determined by the visual judgment of the doctor and input to the display / input device 3. In this case, the result of verification by the comparison verification unit 63 can be displayed on the display input device 3, and the final determination can be left to the doctor. It is also possible to have a configuration left to the doctor.
- the skin change prediction apparatus 4 can display clearly the change of the skin after irradiation with a predicted skin image. For this reason, the operator can grasp
- the skin change prediction device 4 can output a more detailed grade value than before. For this reason, even if it is grade 2, for example, the operator can grasp clearly whether it is grade 2 close to grade 1 or grade 2 close to grade 3. Therefore, it is possible to easily realize that the operator optimally adjusts the skin dose before treatment by looking at the predicted grade value.
- the skin change predicting device 4 can quantitatively output an accurate grade value. For this reason, the grade value can be used as a common measure of communication between doctors. And the skin change prediction apparatus 4 can implement
- the skin change prediction apparatus 4 displays the conventional grade and the new grade side by side on the grade determination screen 50, a doctor who is accustomed to the conventional grade can use the new grade without a sense of incongruity.
- the skin change predicting device 4 can be displayed in a form that is easy for the doctor to understand intuitively.
- the skin change prediction device 4 creates a predicted skin image by regarding the skin change due to radiation irradiation as a change in relative amount with respect to the original skin image. For this reason, the operator is not required to be strict about the shooting environment and can easily use the skin change predicting device 4.
- the skin change prediction device 4 does not require a special photographing environment such as polarized illumination, and is sufficient if there is no unnatural unevenness in illumination (or natural light). For this reason, the skin image image
- the verification device 6 can compare and verify the predicted skin image predicted by the skin change prediction device 4 and the post-irradiation skin image after the actual irradiation. Thereby, the operator can easily confirm whether or not the radiotherapy as planned has been performed. Further, when the error between the predicted skin image and the post-irradiation skin image is large, it can be used to investigate the cause and increase the prediction accuracy.
- FIG. 7A is a photographed image taken after irradiation, and when a hemoglobin dye image is obtained without extracting a skin region from this, a hemoglobin dye image shown in FIG. 7B is obtained.
- a highly accurate hemoglobin dye image shown in FIG. 7D can be obtained from the photographed image shown in FIG. 7A and 7C are the same captured image.
- each image in FIG. 7 is originally a color image, but in order to make the difference easy to understand on the patent drawing as a monochrome image, all of the images have a higher density than the actual one.
- conversion can be realized by using an average value of pixels in the RGB representation format for conversion between the RGB representation format and the dye vector representation format.
- the average value is not an average value of the entire image but an average value calculated from the RGB pixel values of only the skin region, so that the amount of hemoglobin can be accurately estimated without being affected by the lighting environment or the shooting environment. Can do. That is, it is possible to prevent the influence of the background color and the color of the clothes, and anyone can easily use it under gentle shooting conditions. Moreover, even a captured image that has been captured in the past and is not intended to be analyzed can be accurately analyzed to estimate the amount of hemoglobin.
- the present invention is not limited only to the configuration of the above-described embodiment, and many embodiments can be obtained.
- the hemoglobin vector and the melanin vector are used as the pigment vector, the melanin component may be combined as other components to be the hemoglobin vector and others. Even in this case, since it is sufficient to change the image only to the hemoglobin component, it is possible to appropriately create a predicted image of the skin change due to the irradiation of the skin dose.
- the present invention is not limited to changes in the skin due to the influence of radiation, but may be used for quantification of symptoms of erythema caused by other factors and prediction of erythema. In this case, in addition to being used for prediction, it can be used for accurate grasping by current quantification and accurate information transmission between doctors.
- the present invention can be used in industries that predict the effects of radiation on the skin, industries that verify the appropriateness of prediction, and industries that quantify the effects of skin erythema.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dentistry (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dermatology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Urology & Nephrology (AREA)
- Quality & Reliability (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
Description
グレード1:軽い紅斑
グレード2:強い紅斑
グレード3:水泡、糜爛(ビラン)
グレード4:潰瘍
以下、この発明の一実施形態を図面と共に説明する。
図2(A)は、ヘモグロビン色素画像の画素値であるH(x,y)とヘモグロビン流量(皮膚血流量)の変化量の測定結果をプロットしたグラフである。全データに対して原点を通る直線でフィットすると、傾きは0.0139(20)(ml/min100g)-1であった。相関係数は0.74であり、両者の間に相関があると言える。なお図中に点線で図示するエラーバンドに、照明環境に起因する15%の画素値の誤差、血流量測定に起因する0.2ml/min/100gの誤差、そしてフィットによる誤差を二乗和して算出されている。血流量測定に起因する誤差とは主には心拍による生体的な効果が原因である。
照射領域受付部17は、生体の皮膚のうち放射線治療計画において放射線を照射する照射領域の入力を表示入力装置3から受け付ける。照射領域受付部17は、受け付けた照射領域を画像変化部23へ送信する。
<皮膚領域条件>
R>R_th
G/R>R_ratio1
B/R>R_ratio2
(注)RはR成分の濃度(例えば0~255)を示す。
GはG成分の濃度(例えば0~255)を示す。
BはB成分の濃度(例えば0~255)を示す。
R_thは所定値であり、例えば100~160とする、あるいは10とすることができる。なお、R_thは、10以上とすることができ、50以上とすることが好ましく、100以上とすることがより好ましい。また、R_thは、200以下とすることが好ましく、160以下とすることがより好ましい。
R_ratio1は所定値であり、例えば1.1とする、あるいは1.0とする等、適宜の値とすることができる。なお、R_ratio1は、0.5~1.5とすることが好ましく、0.9~1.2とすることがより好ましく、1.0~1.1とすることがさらに好ましい。
R_ratio2は所定値であり、例えば1.1とする、あるいは1.0とする等、適宜の値とすることができる。なお、R_ratio2は、0.5~1.5とすることが好ましく、0.9~1.2とすることがより好ましく、1.0~1.1とすることがさらに好ましい。
rave、gave、baveは、画像中の(r,g,b)の値から(r0,g0,b0)の値を減算した後の値の平均値を示す。
pc1は第一成分、pc2は第二成分、pc3は第三成分を示す。
(r1,g1,b1)は、第一成分を表すベクトルである。
(r2,g2,b2)は、第二成分を表すベクトルである。
(r3,g3,b3)は、第三成分を表すベクトルである。
なお、各ベクトルは1に規格化されており、互いに直交しているためにお互いの内積はゼロとなる。
(rh,gh,bh)は、ヘモグロビンベクトルを表す。
(rm,gm,bm)は、メラニンベクトルを表す。
hは、ヘモグロビン量(ヘモグロビン座標)を示す係数である。
mは、メラニン量(メラニン座標)を示す係数である。
なお、等号ではなく近似等号を使っているのは、第三成分を無視したためである。また、各色素ベクトルは1に規格化されているが、色素ベクトル同士に直交関係はない。
また、上記(数1)および(数2)では平均値rave、gave、baveを各成分に加算することを明確に表記しているが、平均値rave、gave、baveを(数1)及び(数2)の数式におけるR0,B0,G0に含ませて表現上は見えない形に表現してもよい。この場合でも、同じ意味の数式であるから、RGB表現形式をヘモグロビンベクトル等が用いられた生体要素表現形式に変換することができる。
表現形式変換部22は、独立成分分析部33で得られた色素ベクトルを用いて、(r,g,b)の三成分を、次の(数3)の式に示す(h,m,s)の三成分に線形変換(座標変換)する。
(x、y)の関数になっていない箇所は定数であることを意味している。
画像変化部23は、上記(数3)の式におけるh成分に対して、変化量決定部13で決定された変化量(ヘモグロビン増加量)を増加させる。
このようにして画像変化させた後に各成分を合成し元のRGB表現形式に復元すると、図3(E)に示す予測皮膚画像が得られる。図3(E)の予測皮膚画像は、特許図面としてモノクロ画像になっているが、実際にはカラー画像である。この図3(E)の例は、四角形の第1照射領域41と、この第1照射領域41と一部重なる四角形の第2照射領域42にそれぞれ放射線を照射した場合の予測皮膚画像を示している。この第1照射領域41と第2照射領域42は、照射領域受付部17で受け付けた領域である。第1照射領域41は、第2照射領域42よりも皮膚線量が多いために第2照射領域42よりも濃く(赤く)表示されており、かつ、第1照射領域41と第2照射領域42が重なっている重複照射領域43はさらに濃く(赤く)表示されている。
予測値マーク53は、予測値を正確に示す予測値明示部54と、この予測値から誤差が生じ得る範囲を示す誤差範囲表示部55とを備えている。この誤差範囲表示部55が予測グレード目盛表示部52の目盛の並ぶ報告に幅をもっており、その内側で重なるように予測値マーク53が設けられていることで、予測値の中央値と誤差の範囲を直観的にわかりやすく認識できる。誤差範囲表示部55で表示される誤差は、予め定めた一定の範囲とする、あるいは、その都度演算で求めるなど、適宜の方法によって定めることができる。予め定めた一定の範囲とする場合は、例えば、レーザー血流計によって測定するヘモグロビン量の誤差(例えば10%~15%)に撮影環境に依存する誤差(例えば15%)を加味した誤差(例えば18%~21%)とすることができる。
検証装置6は、予測皮膚画像取得部61と、照射後皮膚画像取得部62と、比較検証部63と、検証結果出力部64とを備えている。検証装置6は、少なくともプログラムおよびデータを記憶する記憶部と、前記プログラムに従って各種動作や演算を行うCPUと、皮膚変化予測装置4等の外部機器を接続するUSB等の接続インターフェースとを備えている。検証装置6の記憶部には、記録媒体9から検証プログラムがインストールされている。この検証装置6は、皮膚変化予測装置4と別のハードウェアとしても良いが、皮膚変化予測装置4と同じハードウェアに機能を搭載して構成してもよい。
また、皮膚変化予測装置4は、放射線照射後の皮膚の変化を予測皮膚画像で明瞭に表示することができる。このため、操作者は、放射線治療を行う前に、どの程度の皮膚変化が生じるかを目視で分かり易く把握することができる。
また、この平均値を、画像全体の平均値ではなく皮膚領域のみのRGB画素値から算出した平均値とすることで、照明環境や撮影環境の影響を受けずに精度よくヘモグロビン量を推定することができる。すなわち、背景色や衣服の色による影響を防止することができ、ゆるやかな撮影条件で誰でも容易に利用することができる。また、過去に撮影した撮影画像で解析を意図していない撮影画像であっても、精度よく解析してヘモグロビン量を推定することができる。
例えば、色素ベクトルとしてヘモグロビンベクトルとメラニンベクトルを用いたが、メラニン成分をその他成分としてまとめてヘモグロビンベクトルとその他としてもよい。この場合でも、ヘモグロビン成分のみに画像変化を行えば良いため、皮膚線量の照射による皮膚変化の予測画像を適切に作成することができる。
6…検証装置
11…放射線情報受付部
13…変化量決定部
14…グレード判定部
21…照射前皮膚画像取得部
22…表現形式変換部
23…画像変化部
24…表現形式復元部
25…予測皮膚画像出力部
61…予測皮膚画像取得部
62…照射後皮膚画像取得部
63…比較検証部
211,311…皮膚領域抽出部
Claims (8)
- 照射予定の放射線の放射線情報の入力を受け付ける放射線情報受付部と、
生体の皮膚を撮影した皮膚画像を取得する皮膚画像取得部と、
前記放射線情報により定まる放射線を照射したことによる前記皮膚の変化を演算して前記皮膚画像から変化後の予測皮膚画像を得る変化演算部と、
前記予測皮膚画像を出力する出力部とを備えた
放射線照射による皮膚変化予測装置。 - 前記変化演算部は、
前記皮膚画像を、元の色成分による表現形式である皮膚画像色成分データから生体要素成分による表現形式である皮膚画像生体要素成分データに変換する表現形式変換部と、
一部の前記皮膚画像生体要素成分データが前記放射線情報で定められる放射線照射によって変化する変化量を決定する変化量決定部と、
前記変化量に応じて前記一部の皮膚画像生体要素成分データを変化させる変化部と、
変化後の画像を元のカラー画像の表現形式に復元する表現形式復元部とを有する
請求項1記載の放射線照射による皮膚変化予測装置。 - 前記変化量決定部により決定した変化量に基づいて、前記従来グレードの区分単位よりも細かい新グレードでのグレード値を算出するグレード値算出部を備えた
請求項1または2記載の放射線照射による皮膚変化予測装置。 - 前記皮膚画像取得部で得た皮膚画像から皮膚領域を抽出する皮膚領域抽出部を備え、
前記変化演算部は、前記皮膚領域の皮膚画像を用いた演算により変化後の予測皮膚画像を得る構成である
請求項1、2、または3記載の放射線照射による皮膚変化予測装置。 - 請求項1から4のいずれか一つに記載の放射線照射による皮膚変化予測装置から前記予測皮膚画像を取得する予測皮膚画像取得部と、
放射線照射後に皮膚が撮影された照射後皮膚画像を取得する照射後皮膚画像取得部と、
前記予測皮膚画像と前記放射後皮膚画像とに基づいて放射線照射が適切に行われたか否かを検証する検証部とを備えた
検証装置。 - コンピュータを、
照射予定の放射線の放射線情報の入力を受け付ける放射線情報受付部と、
生体の皮膚を撮影した皮膚画像を取得する皮膚画像取得部と、
前記放射線情報により定まる放射線を照射したことによる前記皮膚の変化を演算して前記皮膚画像から変化後の予測皮膚画像を得る変化演算部と、
前記予測皮膚画像を出力する出力部
として機能させる
放射線照射による皮膚変化予測プログラム。 - コンピュータを、
請求項6記載の放射線照射による皮膚変化予測プログラムから前記予測皮膚画像を取得する予測皮膚画像取得部と、
放射線照射後に皮膚が撮影された照射後皮膚画像を取得する照射後皮膚画像取得部と、
前記予測皮膚画像と前記放射後皮膚画像とに基づいて放射線照射が適切に行われたか否かを検証する検証部として機能させる
検証プログラム。 - 生体の皮膚の変化要因となる要因情報を要因情報受付部により受け付け、
前記生体の皮膚を撮影した皮膚画像を皮膚画像取得部により取得し、
前記要因情報により定まる要因が生じたことによる前記皮膚の変化を変化演算部により演算して前記皮膚画像から変化後の予測皮膚画像を得、
前記予測皮膚画像を出力部により出力する
皮膚変化予測方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/129,749 US10315052B2 (en) | 2014-03-28 | 2015-03-25 | Prediction device for skin change from radiation exposure, and verification device |
EP15768286.5A EP3124077B1 (en) | 2014-03-28 | 2015-03-25 | Prediction device for skin change from radiation exposure, and verification device |
JP2016510041A JP6448142B2 (ja) | 2014-03-28 | 2015-03-25 | 放射線照射による皮膚変化予測装置と検証装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014068506 | 2014-03-28 | ||
JP2014-068506 | 2014-03-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015146164A1 true WO2015146164A1 (ja) | 2015-10-01 |
Family
ID=54194708
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2015/001692 WO2015146164A1 (ja) | 2014-03-28 | 2015-03-25 | 放射線照射による皮膚変化予測装置と検証装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US10315052B2 (ja) |
EP (1) | EP3124077B1 (ja) |
JP (1) | JP6448142B2 (ja) |
WO (1) | WO2015146164A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019078327A1 (ja) * | 2017-10-20 | 2019-04-25 | パナソニック株式会社 | 炎症の評価システム、評価方法、プログラム、及び非一時的記録媒体 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111034153B (zh) * | 2017-07-31 | 2022-12-23 | 株式会社理光 | 通信系统,分散处理系统,分布式处理方法和记录介质 |
EP4151276A1 (en) * | 2021-09-20 | 2023-03-22 | Koninklijke Philips N.V. | Monitoring and detection of cutaneous reactions caused by radiotherapy |
CN114209288A (zh) * | 2022-01-14 | 2022-03-22 | 平安普惠企业管理有限公司 | 皮肤状态预测方法、皮肤状态预测装置、设备及存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10244013A (ja) * | 1997-03-04 | 1998-09-14 | Technol Res Assoc Of Medical & Welfare Apparatus | 三次元画像処理方法 |
JP2002200050A (ja) * | 2000-12-28 | 2002-07-16 | Kao Corp | 肌色測定装置および肌色診断装置ならびに顔画像処理装置 |
JP2009523049A (ja) * | 2006-01-12 | 2009-06-18 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | ラジオロジーにおける患者皮膚線量の改良された表示 |
JP2012055510A (ja) * | 2010-09-09 | 2012-03-22 | Mitsubishi Electric Corp | 皮膚線量表示装置及び皮膚線量表示方法 |
WO2013024534A1 (ja) * | 2011-08-17 | 2013-02-21 | 三菱電機株式会社 | 皮膚線量評価支援装置及び治療計画装置 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6259078B2 (ja) * | 2013-06-27 | 2018-01-10 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | 外照射療法における皮膚火傷のリアルタイム定量化 |
-
2015
- 2015-03-25 WO PCT/JP2015/001692 patent/WO2015146164A1/ja active Application Filing
- 2015-03-25 US US15/129,749 patent/US10315052B2/en not_active Expired - Fee Related
- 2015-03-25 JP JP2016510041A patent/JP6448142B2/ja not_active Expired - Fee Related
- 2015-03-25 EP EP15768286.5A patent/EP3124077B1/en not_active Not-in-force
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10244013A (ja) * | 1997-03-04 | 1998-09-14 | Technol Res Assoc Of Medical & Welfare Apparatus | 三次元画像処理方法 |
JP2002200050A (ja) * | 2000-12-28 | 2002-07-16 | Kao Corp | 肌色測定装置および肌色診断装置ならびに顔画像処理装置 |
JP2009523049A (ja) * | 2006-01-12 | 2009-06-18 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | ラジオロジーにおける患者皮膚線量の改良された表示 |
JP2012055510A (ja) * | 2010-09-09 | 2012-03-22 | Mitsubishi Electric Corp | 皮膚線量表示装置及び皮膚線量表示方法 |
WO2013024534A1 (ja) * | 2011-08-17 | 2013-02-21 | 三菱電機株式会社 | 皮膚線量評価支援装置及び治療計画装置 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019078327A1 (ja) * | 2017-10-20 | 2019-04-25 | パナソニック株式会社 | 炎症の評価システム、評価方法、プログラム、及び非一時的記録媒体 |
JPWO2019078327A1 (ja) * | 2017-10-20 | 2020-10-22 | パナソニック株式会社 | 炎症の評価システム、評価方法、プログラム、及び非一時的記録媒体 |
Also Published As
Publication number | Publication date |
---|---|
EP3124077B1 (en) | 2019-02-27 |
JPWO2015146164A1 (ja) | 2017-04-13 |
US10315052B2 (en) | 2019-06-11 |
US20170128748A1 (en) | 2017-05-11 |
EP3124077A1 (en) | 2017-02-01 |
JP6448142B2 (ja) | 2019-01-09 |
EP3124077A4 (en) | 2017-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11452455B2 (en) | Skin reflectance and oiliness measurement | |
Pauchard et al. | Quality control for bone quality parameters affected by subject motion in high-resolution peripheral quantitative computed tomography | |
JP6448142B2 (ja) | 放射線照射による皮膚変化予測装置と検証装置 | |
US10638968B2 (en) | Skin gloss evaluation device, skin gloss evaluation method, and skin gloss evaluation program | |
CN103914852B (zh) | 基于cuda的dicom医学影像动态非线性调窗方法 | |
CN104122078B (zh) | 一种近眼显示光学镜头像质的评价方法 | |
Saha et al. | A robust method for measuring trabecular bone orientation anisotropy at in vivo resolution using tensor scale | |
CN108257132A (zh) | 一种基于机器学习的ct图像质量评估的方法 | |
Valentinitsch et al. | Regional analysis of age-related local bone loss in the spine of a healthy population using 3D voxel-based modeling | |
JP2016528932A (ja) | 肺の測定 | |
Vickress et al. | Representing the dosimetric impact of deformable image registration errors | |
EP3082105B1 (en) | Image processing apparatus, image processing system, image processing method, and program | |
Nightingale et al. | Frugal 3D scanning using smartphones provides an accessible framework for capturing the external ear | |
Foolad et al. | The use of facial modeling and analysis to objectively quantify facial redness | |
Palmer et al. | Cliniface: phenotypic visualisation and analysis using non-rigid registration of 3D facial images | |
US20210345942A1 (en) | Method and Device for Determining Nature or Extent of Skin Disorder | |
US10964062B2 (en) | Skin evaluation device, skin evaluation method, and skin evaluation program | |
Marcal et al. | Evaluation of the Menzies method potential for automatic dermoscopic image analysis. | |
US20150071519A1 (en) | Method and imaging apparatus to automatically display and/or measure bone variations in medical image data | |
Houser et al. | Shadow analysis via the C+ K Visioline: A technical note | |
KR20200109486A (ko) | Dxa영상을 활용한 골밀도 분포도 평가 및 이를 이용한 골절 예측 방법 | |
Qaq et al. | Sex estimation using lateral cephalograms: a statistical analysis | |
EP2980757B1 (en) | Quantification and imaging methods of the echo-texture feature | |
US20220301687A1 (en) | Uncertainty maps for deep learning eletrical properties tomography | |
Guha et al. | Continuum finite element analysis generalizes in vivo trabecular bone microstructural strength measures between two CT scanners with different image resolution |
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: 15768286 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016510041 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15129749 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2015768286 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2015768286 Country of ref document: EP |