WO2022201691A1 - Image diagnosis method, image diagnosis apparatus, and image diagnosis program - Google Patents

Image diagnosis method, image diagnosis apparatus, and image diagnosis program Download PDF

Info

Publication number
WO2022201691A1
WO2022201691A1 PCT/JP2021/047262 JP2021047262W WO2022201691A1 WO 2022201691 A1 WO2022201691 A1 WO 2022201691A1 JP 2021047262 W JP2021047262 W JP 2021047262W WO 2022201691 A1 WO2022201691 A1 WO 2022201691A1
Authority
WO
WIPO (PCT)
Prior art keywords
score
cells
local
cell
obtaining
Prior art date
Application number
PCT/JP2021/047262
Other languages
French (fr)
Japanese (ja)
Inventor
司 松尾
直也 斎藤
Original Assignee
コニカミノルタ株式会社
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 コニカミノルタ株式会社 filed Critical コニカミノルタ株式会社
Priority to JP2023508630A priority Critical patent/JPWO2022201691A1/ja
Publication of WO2022201691A1 publication Critical patent/WO2022201691A1/en

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology
    • C12M1/34—Measuring or testing with condition measuring or sensing means, e.g. colony counters
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
    • C12Q1/04—Determining presence or kind of microorganism; Use of selective media for testing antibiotics or bacteriocides; Compositions containing a chemical indicator therefor
    • C12Q1/06—Quantitative determination
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G01N33/483—Physical analysis of biological material

Definitions

  • the present invention relates to an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program.
  • HER2 human epidermal growth factor receptor-related 2
  • a specimen slide stained with HER2 protein is prepared.
  • the coloring intensity of each cell is classified into each coloring intensity category.
  • all processes are visually inspected by an inspector, and the summary score is determined by selecting one of four preset levels.
  • Patent Document 1 describes a method for testing HER2.
  • the test method described in Patent Document 1 includes the steps of staining cells in tissue, classifying the stained cells into a plurality of classes, and determining a cancer diagnostic score based on the proportion of the classified cells. have. Unlike the breast cancer examination method based on the HER2 examination guide, the examination method of Patent Document 1 is performed automatically.
  • test method described in Patent Document 1 includes a step of classifying the stained cells into a plurality of classes, so the test results may vary due to changes in the state of the specimen and the imaging conditions. As described above, in the conventional inspection methods, variations in inspection results may occur regardless of the inspection method.
  • An object of the present invention is to provide an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program that are less likely to cause variations in examination results.
  • a diagnostic imaging method includes the steps of obtaining an image of tissue stained with biomarkers or cells, and obtaining or obtaining a local score that scores the characteristics of each cell in the obtained image. a step of dividing the obtained image into a plurality of sections and obtaining a local score obtained by scoring the characteristics of each section; selects the compartments that satisfy a predetermined condition; and scores characteristics of the selected cells or compartments to obtain a tissue summary score.
  • An image diagnostic apparatus includes an input unit for inputting an image of tissue stained with biomarkers or cells, an analysis unit for analyzing the image input by the input unit, and the analysis unit obtains a local score obtained by scoring the characteristics of each cell in the image, or partitions the image into a plurality of sections, obtains a local score obtained by scoring the characteristics of each partition, and select the cell where the local score of the cell satisfies a predetermined condition, or select the compartment where the local score of the compartment satisfies a predetermined condition, and score the properties of the selected cell or compartment to obtain a summary score for the organization.
  • the diagnostic imaging program comprises a computer, a step of obtaining an image of tissue stained with biomarkers or cells, and a local score obtained by scoring the characteristics of each cell in the obtained image.
  • the obtained image is divided into a plurality of sections, and a step of obtaining a local score obtained by scoring the characteristics of each section; The steps of selecting the compartments whose local scores meet predetermined conditions and scoring properties of the selected cells or compartments to obtain a tissue summary score are performed.
  • an image diagnostic method it is possible to provide an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program that are less likely to cause variations in examination results.
  • FIG. 1 is a flow chart for explaining the diagnostic imaging method of this embodiment.
  • 2A to 2C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each cell.
  • 3A to 3C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each partition.
  • 4A to 4C are schematic diagrams for explaining how to set the partitions.
  • FIG. 5 is a schematic diagram for explaining the effect of this embodiment.
  • FIG. 6 is a block diagram of the diagnostic imaging apparatus according to this embodiment.
  • Figures 7A and B are examples analyzed using the present invention.
  • a diagnostic imaging method, diagnostic imaging apparatus, and diagnostic imaging program according to an embodiment of the present invention will be described below.
  • FIG. 1 is a flow chart for explaining an image diagnosis method according to one embodiment of the present invention.
  • 2A to 2C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each cell.
  • 3A to 3C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each partition.
  • 4A to 4C are schematic diagrams for explaining how to set the partitions.
  • the diagnostic imaging method includes the steps of obtaining an image (S110), obtaining a local score (S130), selecting (S140), and obtaining a summary score (S150). Moreover, the diagnostic imaging method may further include, after the step of obtaining the image and before the step of obtaining the local score, the step of excluding cells or compartments for which the local score is not calculated (S120). Furthermore, the diagnostic imaging method may have, after the step of obtaining the summary score, a step of converting the summary score into evaluation values of multiple stages (S160).
  • tissue stained with biomarkers or cells is obtained.
  • tissue includes cultured cells, and tissue collected for pathological diagnosis by needle biopsy or surgical biopsy.
  • a biomarker is appropriately selected depending on the test subject. Examples of biomarkers include proteins such as HER2, Programmed Death 1-Ligand 1 (PD-L1), and nucleic acids such as ribonucleic acid (RNA) and deoxyribonucleic acid (DNA).
  • a method for staining biomarkers or cells is not particularly limited as long as the biomarkers or cells can be stained.
  • Examples of staining methods include biomarker staining and staining for morphological observation.
  • biomarker staining include enzymatic antibody methods using diaminobenzidine (DAB), fluorescent dyes, and fluorescent antibody methods using quantum dots.
  • Examples of staining for morphological observation include staining with hematoxylin, eosin, and 4',6-diamidino-2-phenylindole (DAPI).
  • a digital image is, for example, an image of a stained and sampled tissue photographed with a microscope or a slide scanner.
  • biomarker staining and staining for morphological observation are stains that can be observed in bright field, after taking one image, separate each staining information by color vector information to obtain each image. may If the color vectors of each staining interfere and it is difficult to separate them, or if you want to observe multiple biomarkers, you can stain adjacent sections individually, take multiple images, and combine them to obtain a single image. good too.
  • a local score is obtained by scoring the properties of each cell in the obtained image, or the obtained image is divided into a plurality of sections and the properties of each section are scored.
  • One type of local score may be used, or two or more types may be used.
  • FIG. 2A When obtaining a local score that scores the characteristics of each cell, first extract the cells in the image. Next, a calculation region such as a cell membrane or a cell nucleus for calculating a local score in a cell is set (see FIG. 2A). Note that FIGS. 2A and 2B also show differences in the expression levels of membrane proteins. The expression levels of membrane proteins decrease in the order of thick line, solid line, and dotted line.
  • the calculated area may be set based on the result of staining, or may be set based on the result of calculation.
  • the method of setting based on the calculation result includes, for example, a method of setting a range within a certain distance from the outer edge of the cell nucleus as the calculation region (see FIG. 2B).
  • results of biomarker staining and morphological observation staining described above can be used as the staining information for obtaining the local score.
  • results of biomarker staining include coloring intensity (total value of coloring pixel values, average coloring pixel value, mode of coloring pixel values, median coloring pixel value, coloring intensity above a predetermined threshold) (including the number of pixels) (see FIG. 2C), variation in color development, bias in color development, and frequency distribution of color development intensity.
  • staining results for morphological observation include cell heterogeneity, cell circularity, cell size, color density, cell likelihood obtained by machine learning, and cell number in a compartment.
  • Information for obtaining a local score may be the coloring intensity per cell divided by the result of staining for morphological observation, or the result of biomarker staining may be the staining for morphological observation.
  • the intensity of color development that takes into consideration the results may also be used.
  • the coloring intensity considering the result of staining for morphological observation means, for example, the coloring intensity when the result of staining for morphological observation that satisfies a predetermined condition is excluded from the results of biomarker staining.
  • the obtained image is sectioned (see FIGS. 3A and 3B).
  • the size of the compartment, the shape of the compartment, and the like are not particularly limited.
  • the size of the compartment is the size that contains one or more cells.
  • Examples of compartment shapes include polygons, including squares and rectangles, and circles (see FIG. 4A).
  • Each section may be arranged with a predetermined interval, may be adjacent without a gap, or may partially overlap (see FIGS. 4B and 4C).
  • the setting method of division is not specifically limited, either.
  • the size, shape, and arrangement of the partitions set in advance may be uniformly set, or may be set as appropriate.
  • the number of sections is increased when the density of cells in the image is high, and the number of sections is decreased when the density of cells in the image is low.
  • the partition is then set as the computational region.
  • the coloring intensity of the set calculation area is integrated to obtain a local score obtained by scoring the characteristic of the section (see FIG. 3C).
  • the threshold value for selecting cells or compartments may be a predetermined number of cells or a predetermined number of compartments from the top of the local score by arranging the local score of each cell or the local score of each compartment in order, or the number of cells or compartments from the top of the local score. It may be a predetermined number of cells or a predetermined number of compartments from , or a cell or compartment whose local score is within a predetermined distance.
  • the population selection method for selecting cells or compartments is not particularly limited. For example, the local score of each cell or the local score of each compartment may be arranged in order, and all cells or all compartments may be selected as targets, or may be selected after sampling at arbitrary intervals.
  • tissue summary score In the step of obtaining a tissue summary score (S150), characteristics of selected cells or compartments are scored to obtain a tissue summary score.
  • the tissue summary score can be the maximum, minimum, mean, mode, or median of the local scores of the selected cells or the local scores of the selected compartment. can be a value.
  • the local scores are ordered and the top 10% value of the cells or compartments is the summary score.
  • the local score used in the selection process and the local score used in the process of obtaining the summary score may be the same or different. For example, if both the local score used in the selecting step and the local score used in the step of obtaining the summary score are color intensity, the summary score is calculated only for the cells or compartments whose color intensity satisfies a predetermined condition. do. Further, for example, when the local score used in the selecting step is the number of cells in the compartment and the local score used in the step of obtaining the summary score is the color density, the number of cells in the compartment is A summary score is calculated with only the color density of the plots that meet the conditions.
  • the step of excluding (S120) is optionally performed after the step of obtaining an image (S110) and before the step of obtaining a local score (S130).
  • the excluding step excludes cells or compartments for which no local score is to be calculated.
  • the excluding step may be performed manually or automatically.
  • an automatic exclusion step for example, a method of specifying only the tumor region from the morphological information of hematoxylin staining (H staining) and excluding other regions, a method of removing autofluorescence not derived from biomarkers, etc. included.
  • a manual exclusion step a method is included in which the operator identifies only the tumor region and excludes other regions.
  • regions to be excluded in the excluding step include regions in which no tissue is arranged in the obtained image, regions with poor staining, regions with poor imaging quality, glass regions in invasive cancer regions manually set by the operator, Sections that do not contain the predetermined number of cells are included.
  • the “glass region” means an outer region in which the tissue or section to be analyzed does not exist, or an observation region in which the tissue or section to be analyzed exists only sparsely. . In this case, in the selecting step described above, cells or compartments other than the cells or compartments excluded in the excluding step are selected.
  • the converting step (S160) is optionally performed after the step of obtaining the summary score (S150), and converts the summary score into a multi-level evaluation value.
  • the method of obtaining the reference value used for conversion is not particularly limited.
  • the reference value used for conversion may be a reference value prepared in advance, or may be a reference value obtained by experiment or the like.
  • the reference value can be obtained from the corresponding relationship between the effect of the drug administered for the purpose of acting on the patient's biomarkers and the summary score of the tissue collected from the patient.
  • the reference value can be obtained by, for example, summarizing score average + standard deviation x 3, based on measurement variation of summary scores output for specimen slides using biomarkers as negative controls.
  • biomarker positivity judgment value it is converted into multiple stages like the score in the HER2 test. Alternatively, classify positive and negative based on the reference value of the summary score. Alternatively, a correspondence table is created to indicate which range of summary scores the existing score values belong to. The transformed summary scores are used to determine patient treatment strategies. Alternatively, the results of existing scoring methods are output in parallel to assist the operator (pathologist) in making decisions.
  • scoring by the diagnostic imaging method according to the present embodiment is determined, for example, by the local score in the top 10% of the cumulative frequencies of cells (compartments). As shown in FIG. 5, in the scoring by the diagnostic imaging method according to the present embodiment, in the first analysis, the summary score at the 10% cumulative cell (compartment) frequency is 3.1. On the other hand, in the second analysis, the summary score at the 10% cell (compartment) cumulative frequency is 2.9. As described above, the scoring by the diagnostic imaging method according to the present embodiment is less likely to produce large variations in the analysis results than the analysis results by the scoring by the conventional HER2 examination guide.
  • FIG. 6 is a block diagram of the diagnostic imaging apparatus 100 according to this embodiment. As shown in FIG. 6 , the diagnostic imaging apparatus 100 according to this embodiment has an input unit 110 and an analysis unit 120 . This embodiment has a control unit 130 that controls the input unit 110 and the analysis unit 120 .
  • the input unit 110 is a device that obtains an image of tissue stained with biomarkers or cells.
  • the input unit 110 may obtain an image by taking an image, or may obtain an image by inputting an image acquired outside.
  • the input unit 110 may be an imaging device (camera) for obtaining images of tissues stained with biomarkers or cells, or may be a part of a computer for inputting images obtained externally.
  • the analysis unit 120 is a device for analyzing the obtained image. As described above, the analysis unit 120 obtains a local score that scores the properties of each cell in the obtained image, or divides the obtained image into a plurality of sections and scores the properties of each section.
  • the analysis unit 120 selects the cell whose local score satisfies a predetermined condition, or selects the partition whose local score satisfies a predetermined condition. Further, the analysis unit 120 scores the properties of the selected cells or compartments to obtain a tissue summary score, as described above.
  • the control unit 130 has a CPU (Central Processing Unit), a stored ROM (Read Only Memory), and a RAM (Random Access Memory).
  • the CPU reads an image diagnosis program corresponding to the processing contents from the ROM, develops it in the RAM, and centrally controls the operation of each block of the image diagnosis apparatus 100 in cooperation with the expanded program.
  • various data stored in the storage unit are referenced.
  • the storage unit is, for example, a nonvolatile semiconductor memory (so-called flash memory) or a hard disk drive.
  • the computer is provided with a step of obtaining an image of tissue stained with biomarkers or cells, obtaining a local score that scores the characteristics of each cell in the obtained image, or obtaining a plurality of obtained images and obtaining a local score obtained by scoring the characteristics of each compartment, and selecting a cell whose local score satisfies a predetermined condition, or selecting a compartment whose local score satisfies a predetermined condition and scoring characteristics of selected cells or compartments to obtain a tissue summary score.
  • the control unit 130 transmits and receives various data to and from an external device (for example, a personal computer) connected to a communication network such as LAN (Local Area Network) or WAN (Wide Area Network) via the communication unit. .
  • the control unit 130 receives image data transmitted from an external device, for example, and performs image diagnosis based on this image data (input image data).
  • the communication unit is, for example, a communication control card such as a LAN card.
  • FIG. 5 is a diagram for explaining the effect of the diagnostic imaging method according to this embodiment.
  • the horizontal axis of FIG. 5 indicates the cumulative frequency (%) of cells or compartments, and the vertical axis indicates the local score.
  • the solid line in FIG. 5 indicates the results of the first analysis, and the dotted line indicates the results of the second analysis.
  • the slice used for the first analysis and the slice used for the second analysis are adjacent slices.
  • Scoring by the conventional HER2 test guide is determined by the percentage of cumulative frequencies of cells (compartments) with a local score of 3+. As shown in FIG. 5, in the conventional HER2 test-guided scoring, the summary score is 3+ because there are 10% or more cells (compartments) with a local score of 3+ in the first analysis. On the other hand, in the second analysis, less than 10% of the cells (compartments) have a local score of 3+, resulting in a summary score of 2+. As described above, in the scoring by the conventional HER2 examination guide, even if the tissues in substantially the same state are analyzed, the analysis results may vary greatly.
  • FIG. 7A and B are examples analyzed using the present invention.
  • the horizontal axis of FIG. 7A is the HER2 score per core as determined by a pathologist using DAB-stained serial section slides.
  • the vertical axis in FIG. 7A is the evaluation value for each core analyzed using the present invention.
  • FIG. 7B is a concordance table obtained by calculating a provisional PID score with the minimum score of evaluation values analyzed using the present invention as a cut point for the DAB score.
  • a microarray slide of human breast cancer tissue was used as the specimen.
  • Ductal carcinoma in situ, DAB undeterminable cores, cores with stained cytoplasm, invasive ductal carcinoma undeterminable cores, non-cancerous cores, and detached cores were analyzed in advance by a pathologist out of a total of 208 cores. Excluded as unsuitable core.
  • Evaluation values were calculated by the following method. First, slides were immunostained with primary and biotinylated secondary antibodies and labeled with streptavidin-coated fluorescent nanoparticles. PID particle size was about 130 nm (excitation: 580 nm, fluorescence: 620 nm). Then, it was converted into a highly accurate Whole Slide Image (WSI) by a virtual slide scanner. Next, the obtained WSI was image-divided for each core. Next, for each segmented core image, only the infiltration region annotated by the pathologist was set as the analysis target, and the other masked region was set as the analysis target region.
  • WSI Whole Slide Image
  • the evaluation value for each core was calculated by the following procedure. (1) The fluorescence image was divided into 12 ⁇ m square sections, and among all the sections, only the sections within the analysis target area were targeted, and the fluorescence intensity integrated value within the section was calculated for each section. (2) Among the values for each section calculated in (1), the average value of the sections with the top 10% values is calculated. This was used as the evaluation value for each core.
  • the present invention for example, it is useful for diagnosing cancer such as breast cancer, and diagnosing various other diseases.
  • diagnostic imaging apparatus 110 input unit 120 analysis unit 130 control unit

Abstract

This image diagnosis method comprises: a step for acquiring an image of a biomarker or tissue in which cells are stained; a step for acquiring local scores obtained by scoring features of cells in the acquired image, or acquiring local scores obtained by dividing the acquired image into a plurality of divisions and scoring features of the divisions; a step for selecting cells having a local score satisfying a predetermined condition, or selecting divisions having a local score satisfying a predetermined condition; and a step for acquiring a summary score for the tissue by scoring features of the selected cells or divisions.

Description

画像診断方法、画像診断装置および画像診断プログラムDiagnostic imaging method, diagnostic imaging apparatus and diagnostic imaging program
　本発明は、画像診断方法、画像診断装置および画像診断プログラムに関する。 The present invention relates to an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program.
　がん診断などでは、特定のタンパク質が過剰に発現しているか否かを判定するために、生検した標本スライドに対して所定の条件を満たした細胞を選択した上でその細胞の特徴を数値化することが求められる。 In cancer diagnosis, in order to determine whether or not a specific protein is overexpressed, cells that meet predetermined conditions are selected from a biopsy sample slide, and the characteristics of those cells are evaluated numerically. It is required to be
　例えば、乳がんのＨＥＲ２（ｈｕｍａｎ　Ｅｐｉｄｅｒｍａｌ　Ｇｒｏｗｔｈ　Ｆａｃｔｏｒ　Ｒｅｃｅｐｔｏｒ－ｒｅｌａｔｅｄ　２）検査ガイドによる検査方法では、ＨＥＲ２タンパクを染色した標本スライドを準備する。そして、各細胞の発色強度を発色強度区分毎に分類する。次いで、発色強度区分毎に属する細胞の数（面積）の全体に占める割合が、所定の基準を満たすか否かを判定する。これにより、組織標本全体としての要約スコアを決定する。ＨＥＲ２検査ガイドでは、全ての工程は検査員の目視によって行われ、また、要約スコアはあらかじめ設定された４段階のいずれかを選択する形で決定される。 For example, in an examination method using a HER2 (human epidermal growth factor receptor-related 2) examination guide for breast cancer, a specimen slide stained with HER2 protein is prepared. Then, the coloring intensity of each cell is classified into each coloring intensity category. Next, it is determined whether or not the ratio of the number (area) of cells belonging to each coloring intensity category to the whole satisfies a predetermined criterion. This determines the summary score for the tissue specimen as a whole. In the HER2 inspection guide, all processes are visually inspected by an inspector, and the summary score is determined by selecting one of four preset levels.
　また、特許文献１には、ＨＥＲ２の検査方法が記載されている。特許文献１に記載の検査方法は、組織における細胞を染色する工程と、染色した細胞を複数のクラスに分類する工程と、分類された細胞の割合に基づいてがん診断スコアを決定する工程を有する。特許文献１の検査方法は、乳がんのＨＥＲ２検査ガイドによる検査方法と異なり、自動で行われる。 In addition, Patent Document 1 describes a method for testing HER2. The test method described in Patent Document 1 includes the steps of staining cells in tissue, classifying the stained cells into a plurality of classes, and determining a cancer diagnostic score based on the proportion of the classified cells. have. Unlike the breast cancer examination method based on the HER2 examination guide, the examination method of Patent Document 1 is performed automatically.
米国特許出願公開第２０１４／１１２５６８号明細書U.S. Patent Application Publication No. 2014/112568
　しかしながら、乳がんのＨＥＲ２検査ガイドによる検査方法では、作業者が目視で判定するため、検査環境により検査結果にバラつきが生じることがある。また、特許文献１に記載の検査方法では、染色をした細胞を複数のクラスに分類する工程を有するため、検体の状態や撮像の条件などの変動により検査結果にバラつきが生じることがある。このように、従来の検査方法では、いずれの検査方法でも、検査結果にバラつきが生じてしまうことがあった。 However, in the examination method using the HER2 examination guide for breast cancer, the operator makes a visual judgment, so the examination results may vary depending on the examination environment. In addition, the test method described in Patent Document 1 includes a step of classifying the stained cells into a plurality of classes, so the test results may vary due to changes in the state of the specimen and the imaging conditions. As described above, in the conventional inspection methods, variations in inspection results may occur regardless of the inspection method.
　本発明は、検査結果にバラつきが生じにくい画像診断方法、画像診断装置および画像診断プログラムを提供することである。 An object of the present invention is to provide an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program that are less likely to cause variations in examination results.
　本発明の一実施の形態に係る画像診断方法は、バイオマーカーまたは細胞を染色した組織の画像を得る工程と、得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得る工程と、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する工程と、選定された、前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る工程と、を有する。 A diagnostic imaging method according to an embodiment of the present invention includes the steps of obtaining an image of tissue stained with biomarkers or cells, and obtaining or obtaining a local score that scores the characteristics of each cell in the obtained image. a step of dividing the obtained image into a plurality of sections and obtaining a local score obtained by scoring the characteristics of each section; selects the compartments that satisfy a predetermined condition; and scores characteristics of the selected cells or compartments to obtain a tissue summary score.
　本発明の一実施の形態に係る画像診断装置は、バイオマーカーまたは細胞を染色した組織の画像を入力するための入力部と、前記入力部で入力された画像を解析するための解析部と、を有し、前記解析部は、前記画像における各細胞の特性をスコア化した局所スコアを得るか、または前記画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得て、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定し、選定された前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る。 An image diagnostic apparatus according to an embodiment of the present invention includes an input unit for inputting an image of tissue stained with biomarkers or cells, an analysis unit for analyzing the image input by the input unit, and the analysis unit obtains a local score obtained by scoring the characteristics of each cell in the image, or partitions the image into a plurality of sections, obtains a local score obtained by scoring the characteristics of each partition, and select the cell where the local score of the cell satisfies a predetermined condition, or select the compartment where the local score of the compartment satisfies a predetermined condition, and score the properties of the selected cell or compartment to obtain a summary score for the organization.
　本発明の一実施の形態に係る画像診断プログラムは、コンピュータに、バイオマーカーまたは細胞を染色した組織の画像を得る工程と、得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得る工程と、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する工程と、選定された、前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る工程と、を実行させる。 The diagnostic imaging program according to one embodiment of the present invention comprises a computer, a step of obtaining an image of tissue stained with biomarkers or cells, and a local score obtained by scoring the characteristics of each cell in the obtained image. Alternatively, the obtained image is divided into a plurality of sections, and a step of obtaining a local score obtained by scoring the characteristics of each section; The steps of selecting the compartments whose local scores meet predetermined conditions and scoring properties of the selected cells or compartments to obtain a tissue summary score are performed.
　本発明によれば、検査結果にバラつきが生じにくい画像診断方法、画像診断装置および画像診断プログラムを提供できる。 According to the present invention, it is possible to provide an image diagnostic method, an image diagnostic apparatus, and an image diagnostic program that are less likely to cause variations in examination results.
図１は、本実施の形態の画像診断方法を説明するためのフローチャートである。FIG. 1 is a flow chart for explaining the diagnostic imaging method of this embodiment. 図２Ａ～Ｃは、各細胞の特性をスコア化した局所スコアを得る例を説明するための模式図である。2A to 2C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each cell. 図３Ａ～Ｃは、各区画の特性をスコア化した局所スコアを得る例を説明するための模式図である。3A to 3C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each partition. 図４Ａ～Ｃは、区画の設定方法を説明するための模式図である。4A to 4C are schematic diagrams for explaining how to set the partitions. 図５は、本実施の形態の効果を説明するための模式図である。FIG. 5 is a schematic diagram for explaining the effect of this embodiment. 図６は、本実施の形態にかかる画像診断装置のブロック図である。FIG. 6 is a block diagram of the diagnostic imaging apparatus according to this embodiment. 図７Ａ、Ｂは、本発明を用いて解析した実例である。Figures 7A and B are examples analyzed using the present invention.
　以下、本発明の一実施の形態に係る画像診断方法、画像診断装置および画像診断プログラムについて説明する。 A diagnostic imaging method, diagnostic imaging apparatus, and diagnostic imaging program according to an embodiment of the present invention will be described below.
　（画像診断方法）
　図１は、本発明の一実施の形態に係る画像診断方法を説明するためのフローチャートである。図２Ａ～Ｃは、各細胞の特性をスコア化した局所スコアを得る例を説明するための模式図である。図３Ａ～Ｃは、各区画の特性をスコア化した局所スコアを得る例を説明するための模式図である。図４Ａ～Ｃは、区画の設定方法を説明するための模式図である。 (Image diagnosis method)
FIG. 1 is a flow chart for explaining an image diagnosis method according to one embodiment of the present invention. 2A to 2C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each cell. 3A to 3C are schematic diagrams for explaining an example of obtaining a local score obtained by scoring the characteristics of each partition. 4A to 4C are schematic diagrams for explaining how to set the partitions.
　本実施の形態に係る画像診断方法は、画像を得る工程（Ｓ１１０）と、局所スコアを得る工程（Ｓ１３０）と、選定する工程（Ｓ１４０）と、要約スコアを得る工程（Ｓ１５０）と、を有する。また、画像診断方法は、画像を得る工程の後であって、局所スコアを得る工程の前に、局所スコアを算出しない細胞または区画を除外する工程（Ｓ１２０）をさらに有していてもよい。さらに、画像診断方法は、要約スコアを得る工程の後に、要約スコアを複数段階の評価値に変換する工程（Ｓ１６０）を有していてもよい。 The diagnostic imaging method according to the present embodiment includes the steps of obtaining an image (S110), obtaining a local score (S130), selecting (S140), and obtaining a summary score (S150). . Moreover, the diagnostic imaging method may further include, after the step of obtaining the image and before the step of obtaining the local score, the step of excluding cells or compartments for which the local score is not calculated (S120). Furthermore, the diagnostic imaging method may have, after the step of obtaining the summary score, a step of converting the summary score into evaluation values of multiple stages (S160).
　画像を得る工程（Ｓ１１０）では、バイオマーカーまたは細胞を染色した組織の画像を得る。具体的には、画像を得る工程では、採取した組織を染色および標本化し、標本スライドを撮像して、デジタル画像を得る。「組織」とは、培養細胞や、針生検、手術生検により病理診断のために採取した組織を含む。バイオマーカーは、検査対象により適宜選択される。バイオマーカーの例には、ＨＥＲ２、Ｐｒｏｇｒａｍｍｅｄ　ｃｅｌｌ　Ｄｅａｔｈ　１－　Ｌｉｇａｎｄ　１（ＰＤ－Ｌ１）などのたんぱく質、リボ核酸（ＲＮＡ）、デオキシリボ核酸（ＤＮＡ）などの核酸が含まれる。バイオマーカーまたは細胞を染色する方法は、バイオマーカーまたは細胞を染色できれば特に限定されない。染色する方法の例には、バイオマーカー染色、形態観察用の染色が含まれる。バイオマーカー染色の例には、ジアミノベンジジン（ＤＡＢ）を用いた酵素抗体法、蛍光色素、量子ドットを用いた蛍光抗体法が含まれる。形態観察用の染色の例には、ヘマトシキリン、エオジン、４’，６－ｄｉａｍｉｄｉｎｏ－２－ｐｈｅｎｙｌｉｎｄｏｌｅ（ＤＡＰＩ）を用いた染色が含まれる。デジタル画像は、例えば、染色して標本化した組織を、顕微鏡やスライドスキャナで撮影した画像である。バイオマーカー染色と形態観察用染色とがいずれも明視野で観察可能な染色の場合には、一枚の画像を撮影後、色ベクトル情報でそれぞれの染色情報を分離して、それぞれの画像を得てもよい。それぞれの染色の色ベクトルが干渉し分離が難しい場合や、複数のバイオマーカーを観察したい場合は、隣接した切片を個別に染色し複数の画像を撮影し、合成して一枚の画像として得てもよい。 In the step of obtaining an image (S110), an image of tissue stained with biomarkers or cells is obtained. Specifically, in the step of obtaining an image, the collected tissue is stained and mounted, and the specimen slide is imaged to obtain a digital image. The term "tissue" includes cultured cells, and tissue collected for pathological diagnosis by needle biopsy or surgical biopsy. A biomarker is appropriately selected depending on the test subject. Examples of biomarkers include proteins such as HER2, Programmed Death 1-Ligand 1 (PD-L1), and nucleic acids such as ribonucleic acid (RNA) and deoxyribonucleic acid (DNA). A method for staining biomarkers or cells is not particularly limited as long as the biomarkers or cells can be stained. Examples of staining methods include biomarker staining and staining for morphological observation. Examples of biomarker staining include enzymatic antibody methods using diaminobenzidine (DAB), fluorescent dyes, and fluorescent antibody methods using quantum dots. Examples of staining for morphological observation include staining with hematoxylin, eosin, and 4',6-diamidino-2-phenylindole (DAPI). A digital image is, for example, an image of a stained and sampled tissue photographed with a microscope or a slide scanner. When both biomarker staining and staining for morphological observation are stains that can be observed in bright field, after taking one image, separate each staining information by color vector information to obtain each image. may If the color vectors of each staining interfere and it is difficult to separate them, or if you want to observe multiple biomarkers, you can stain adjacent sections individually, take multiple images, and combine them to obtain a single image. good too.
　局所スコアを得る工程（Ｓ１３０）では、得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化する。局所スコアは、１種類でもよいし、２種類以上でもよい。 In the step of obtaining a local score (S130), a local score is obtained by scoring the properties of each cell in the obtained image, or the obtained image is divided into a plurality of sections and the properties of each section are scored. One type of local score may be used, or two or more types may be used.
　各細胞の特性をスコア化した局所スコアを得る場合、まず、画像内の細胞を抽出する。次いで、細胞において局所スコアを算出するための細胞膜、細胞核などの算出領域を設定する（図２Ａ参照）。なお、図２Ａ、Ｂでは、膜タンパク質の発現量の違いも示している。太線、実線、点線の順番に膜タンパク質の発現量が少なくなっている。算出領域は、染色した結果に基づいて設定してもよいし、計算結果に基づいて設定してもよい。計算結果に基づいて設定する方法では、例えば、細胞核の外周縁から一定距離の範囲内を算出領域とする方法が含まれる（図２Ｂ参照）。 When obtaining a local score that scores the characteristics of each cell, first extract the cells in the image. Next, a calculation region such as a cell membrane or a cell nucleus for calculating a local score in a cell is set (see FIG. 2A). Note that FIGS. 2A and 2B also show differences in the expression levels of membrane proteins. The expression levels of membrane proteins decrease in the order of thick line, solid line, and dotted line. The calculated area may be set based on the result of staining, or may be set based on the result of calculation. The method of setting based on the calculation result includes, for example, a method of setting a range within a certain distance from the outer edge of the cell nucleus as the calculation region (see FIG. 2B).
　次いで、細胞の特性を示す局所スコアを得る。局所スコアを得るための染色情報は、上述したバイオマーカー染色、形態観察用の染色の結果を使用できる。バイオマーカー染色の結果の例には、発色強度（発色画素値の合計値、発色画素値の平均値、発色画素値の最頻値、発色画素値の中央値、発色強度が所定の閾値以上の画素数を含む）（図２Ｃ参照）、発色のばらつき、発色の偏り、発色強度の周波数分布が含まれる。形態観察用の染色の結果の例には、細胞の異形度、細胞の円形度、細胞の大きさ、発色濃度、機械学習で得られる細胞の尤度、区画内の細胞数が含まれる。局所スコアを得るための情報は、例えば、バイオマーカー染色の結果を、形態観察用の染色の結果で除した細胞当たりの発色強度としてもよいし、バイオマーカー染色の結果に形態観察用の染色の結果を加味した発色強度でもよい。形態観察用の染色の結果を加味した発色強度とは、例えば、バイオマーカー染色の結果のうち、所定の条件を満たす形態観察用の染色の結果を除外したときの発色強度を意味する。 Next, obtain a local score that indicates the characteristics of the cell. As the staining information for obtaining the local score, the results of biomarker staining and morphological observation staining described above can be used. Examples of results of biomarker staining include coloring intensity (total value of coloring pixel values, average coloring pixel value, mode of coloring pixel values, median coloring pixel value, coloring intensity above a predetermined threshold) (including the number of pixels) (see FIG. 2C), variation in color development, bias in color development, and frequency distribution of color development intensity. Examples of staining results for morphological observation include cell heterogeneity, cell circularity, cell size, color density, cell likelihood obtained by machine learning, and cell number in a compartment. Information for obtaining a local score, for example, the result of biomarker staining, may be the coloring intensity per cell divided by the result of staining for morphological observation, or the result of biomarker staining may be the staining for morphological observation. The intensity of color development that takes into consideration the results may also be used. The coloring intensity considering the result of staining for morphological observation means, for example, the coloring intensity when the result of staining for morphological observation that satisfies a predetermined condition is excluded from the results of biomarker staining.
　各区画の特性をスコア化した局所スコアを得る場合、まず、得られた画像を区画する（図３Ａおよび図３Ｂ参照）。区画の大きさおよび区画の形などは、特に限定されない。例えば、区画の大きさは、細胞が１個以上含まれる大きさである。区画の形の例には、正方形および長方形を含む多角形と、円形とが含まれる（図４Ａ参照）。各区画は、所定の間隔を有して配置されていてもよいし、隙間なく隣接していてもよいし、一部が重複していてもよい（図４Ｂ、Ｃ参照）。また、区画の設定方法も特に限定されない。区画の設定方法は、予め設定された区画の大きさ、形、配置で画一的に設定してもよいし、適宜設定してもよい。例えば、画像における細胞の密度が大きい場合には区画の数を多くしたり、画像における細胞の密度が小さい場合には区画の数を少なくしたりする。次いで、区画を算出領域として設定する。次いで、設定された算出領域の発色強度を積算して、区画の特性をスコア化した局所スコアとする（図３Ｃ参照）。 When obtaining a local score obtained by scoring the characteristics of each section, first, the obtained image is sectioned (see FIGS. 3A and 3B). The size of the compartment, the shape of the compartment, and the like are not particularly limited. For example, the size of the compartment is the size that contains one or more cells. Examples of compartment shapes include polygons, including squares and rectangles, and circles (see FIG. 4A). Each section may be arranged with a predetermined interval, may be adjacent without a gap, or may partially overlap (see FIGS. 4B and 4C). Moreover, the setting method of division is not specifically limited, either. As for the method of setting the partitions, the size, shape, and arrangement of the partitions set in advance may be uniformly set, or may be set as appropriate. For example, the number of sections is increased when the density of cells in the image is high, and the number of sections is decreased when the density of cells in the image is low. The partition is then set as the computational region. Next, the coloring intensity of the set calculation area is integrated to obtain a local score obtained by scoring the characteristic of the section (see FIG. 3C).
　選定する工程（Ｓ１４０）では、細胞の局所スコアが所定の条件を満たす細胞を選定するか、または区画の局所スコアが所定の条件を満たす区画を選定する。細胞または区画の選定するための閾値は、各細胞の局所スコアまたは各区画の局所スコアをそれぞれ順番に並べて、局所スコアの上位から所定の細胞数または所定の区画数でもよいし、局所スコアの下位から所定の細胞数または所定の区画数でもよいし、局所スコアが所定の距離内にある細胞または区画でもよい。細胞または区画を選定するための母集団の選定方法は、特に限定されない。例えば、各細胞の局所スコアまたは各区画の局所スコアをそれぞれ順番に並べて、全ての細胞または全ての区画を対象として選定してもよいし、任意の間隔でサンプリングした後に選定してもよい。 In the selecting step (S140), a cell whose local score satisfies a predetermined condition is selected, or a section whose local score satisfies a predetermined condition is selected. The threshold value for selecting cells or compartments may be a predetermined number of cells or a predetermined number of compartments from the top of the local score by arranging the local score of each cell or the local score of each compartment in order, or the number of cells or compartments from the top of the local score. It may be a predetermined number of cells or a predetermined number of compartments from , or a cell or compartment whose local score is within a predetermined distance. The population selection method for selecting cells or compartments is not particularly limited. For example, the local score of each cell or the local score of each compartment may be arranged in order, and all cells or all compartments may be selected as targets, or may be selected after sampling at arbitrary intervals.
　組織の要約スコアを得る工程（Ｓ１５０）では、選定された、細胞または区画の特性をスコア化して組織の要約スコアを得る。例えば、組織の要約スコアは、選定された細胞の局所スコアまたは選定された区画の局所スコアの最大値でもよいし、最小値でもよいし、平均値でもよいし、最頻値でもよいし、中央値でもよい。図５の例では、局所スコアを順番に並べて、細胞または区画の上位１０％目の値が要約スコアである。 In the step of obtaining a tissue summary score (S150), characteristics of selected cells or compartments are scored to obtain a tissue summary score. For example, the tissue summary score can be the maximum, minimum, mean, mode, or median of the local scores of the selected cells or the local scores of the selected compartment. can be a value. In the example of FIG. 5, the local scores are ordered and the top 10% value of the cells or compartments is the summary score.
　選定する工程で用いられる局所スコアと、要約スコアを得る工程で用いられる局所スコアとは、同じでもよいし、それぞれ異なっていてもよい。例えば、選定する工程で用いられる局所スコアおよび要約スコアを得る工程で用いられる局所スコアがいずれも発色強度である場合には、発色強度が所定の条件を満たす細胞や区画のみで、要約スコアを算出する。また、例えば、選定する工程で用いられる局所スコアが区画内の細胞の数であり、要約スコアを得る工程で用いられる局所スコアが発色濃度である場合には、区画内の細胞の数が所定の条件を満たす区画の発色濃度のみで、要約スコアを算出する。 The local score used in the selection process and the local score used in the process of obtaining the summary score may be the same or different. For example, if both the local score used in the selecting step and the local score used in the step of obtaining the summary score are color intensity, the summary score is calculated only for the cells or compartments whose color intensity satisfies a predetermined condition. do. Further, for example, when the local score used in the selecting step is the number of cells in the compartment and the local score used in the step of obtaining the summary score is the color density, the number of cells in the compartment is A summary score is calculated with only the color density of the plots that meet the conditions.
　除外する工程（Ｓ１２０）は、画像を得る工程（Ｓ１１０）の後であって、局所スコアを得る工程（Ｓ１３０）の前に任意に行われる。除外する工程では、局所スコアを算出しない細胞または区画を除外する。除外する工程は、手動で行ってもよいし、自動で行ってもよい。自動で除外する工程を行う場合には、例えばヘマトキシリン染色（Ｈ染色）の形態情報から腫瘍領域のみを特定し、他の領域を除外する方法、バイオマーカーに由来しない自家蛍光などを除去する方法が含まれる。また、手動で除外する工程を行う場合には、作業者が腫瘍領域のみを特定し、他の領域を除外する方法が含まれる。除外する工程において除外する領域の例には、得られた画像における組織が配置されていない領域、染色不良な領域、撮像品質が悪い領域、作業者が手動で設定した浸潤癌領域におけるガラス領域、所定の数の細胞が含まれていない区分が含まれる。ここで、「ガラス領域」とは、解析対象となる組織や切片が存在しない外側の領域、または、観察領域であっても、解析対象となる組織や切片がまばらにしか存在しない領域を意味する。この場合、前述した選定する工程では、除外する工程で除外した細胞または区画以外の細胞または区画を対象として、細胞または区画を選定する。 The step of excluding (S120) is optionally performed after the step of obtaining an image (S110) and before the step of obtaining a local score (S130). The excluding step excludes cells or compartments for which no local score is to be calculated. The excluding step may be performed manually or automatically. When performing an automatic exclusion step, for example, a method of specifying only the tumor region from the morphological information of hematoxylin staining (H staining) and excluding other regions, a method of removing autofluorescence not derived from biomarkers, etc. included. Also, when performing a manual exclusion step, a method is included in which the operator identifies only the tumor region and excludes other regions. Examples of regions to be excluded in the excluding step include regions in which no tissue is arranged in the obtained image, regions with poor staining, regions with poor imaging quality, glass regions in invasive cancer regions manually set by the operator, Sections that do not contain the predetermined number of cells are included. Here, the “glass region” means an outer region in which the tissue or section to be analyzed does not exist, or an observation region in which the tissue or section to be analyzed exists only sparsely. . In this case, in the selecting step described above, cells or compartments other than the cells or compartments excluded in the excluding step are selected.
　変換する工程（Ｓ１６０）は、要約スコアを得る工程（Ｓ１５０）の後に任意に行われ、要約スコアを複数段階の評価値に変換する。変換に使用する基準値の求め方は、特に限定されない。変換に使用する基準値は、あらかじめ用意された基準値であってもよいし、実験等で求めた基準値であってもよい。例えば同一検体、連続した切片標本同士で、従来のスコア化（ＨＥＲ２検査、ＰＤ－Ｌ１検査、グリソンスコア、Ｈ－スコア、バイオマーカー陽性度判定値など）の結果と、要約スコアとを比較する実験で求めることができる。または、基準値の求め方は、患者のバイオマーカーに作用させる目的で投与された薬の効き目と、患者から採取した組織の要約スコアとの対応関係から求めることができる。あるいは、基準値の求め方は、バイオマーカーをネガティブコントロールとした標本スライドに対して出力した要約スコアの測定ばらつきを元に、例えば要約スコアの平均値＋標準偏差×３として求めることができる。 The converting step (S160) is optionally performed after the step of obtaining the summary score (S150), and converts the summary score into a multi-level evaluation value. The method of obtaining the reference value used for conversion is not particularly limited. The reference value used for conversion may be a reference value prepared in advance, or may be a reference value obtained by experiment or the like. For example, an experiment comparing the results of conventional scoring (HER2 test, PD-L1 test, Gleason score, H-score, biomarker positivity judgment value, etc.) with the summary score for the same specimen, consecutive section specimens can be found at Alternatively, the reference value can be obtained from the corresponding relationship between the effect of the drug administered for the purpose of acting on the patient's biomarkers and the summary score of the tissue collected from the patient. Alternatively, the reference value can be obtained by, for example, summarizing score average + standard deviation x 3, based on measurement variation of summary scores output for specimen slides using biomarkers as negative controls.
　バイオマーカー陽性度判定値の例では、ＨＥＲ２検査におけるスコアのような複数段階に変換する。あるいは要約スコアの基準値を元に陽性と陰性を区分する。あるいは、既存のスコア値が要約スコアのどの範囲に属するか対応表を作成する。変換された要約スコアは、患者の治療方針の決定に使用される。または、既存のスコアリング法の結果と並列で出力し、作業者（病理学者）の判定を補助する。 In the example of the biomarker positivity judgment value, it is converted into multiple stages like the score in the HER2 test. Alternatively, classify positive and negative based on the reference value of the summary score. Alternatively, a correspondence table is created to indicate which range of summary scores the existing score values belong to. The transformed summary scores are used to determine patient treatment strategies. Alternatively, the results of existing scoring methods are output in parallel to assist the operator (pathologist) in making decisions.
　一方、本実施の形態に係る画像診断方法によるスコアリングは、例えば細胞（区画）の累積度数の上位１０％目の局所スコアで判定する。図５に示されるように、本実施の形態に係る画像診断方法によるスコアリングでは、１回目の解析において、細胞（区画）の累積度数が１０％目の要約スコアは３．１となる。一方、２回目の解析において、細胞（区画）の累積度数が１０％目の要約スコアは２．９となる。このように、本実施の形態に係る画像診断方法によるスコアリングは、従来のＨＥＲ２検査ガイドによるスコアリングによる解析結果と比較して、解析結果に大きなばらつきが生じにくい。 On the other hand, scoring by the diagnostic imaging method according to the present embodiment is determined, for example, by the local score in the top 10% of the cumulative frequencies of cells (compartments). As shown in FIG. 5, in the scoring by the diagnostic imaging method according to the present embodiment, in the first analysis, the summary score at the 10% cumulative cell (compartment) frequency is 3.1. On the other hand, in the second analysis, the summary score at the 10% cell (compartment) cumulative frequency is 2.9. As described above, the scoring by the diagnostic imaging method according to the present embodiment is less likely to produce large variations in the analysis results than the analysis results by the scoring by the conventional HER2 examination guide.
　（画像診断装置および画像診断プログラム）
　図６は、本実施の形態にかかる画像診断装置１００のブロック図である。図６に示されるように、本実施の形態にかかる画像診断装置１００は、入力部１１０と、解析部１２０とを有する。本実施の形態では、入力部１１０と、解析部１２０とを制御する制御部１３０を有している。 (Diagnostic imaging device and diagnostic imaging program)
FIG. 6 is a block diagram of the diagnostic imaging apparatus 100 according to this embodiment. As shown in FIG. 6 , the diagnostic imaging apparatus 100 according to this embodiment has an input unit 110 and an analysis unit 120 . This embodiment has a control unit 130 that controls the input unit 110 and the analysis unit 120 .
　入力部１１０は、バイオマーカーまたは細胞を染色した組織の画像を得る装置である。入力部１１０は、撮像することにより、画像を得てもよいし、外部で取得した画像を入力して、画像を得てもよい。入力部１１０は、バイオマーカーまたは細胞を染色した組織の画像を得るための撮像装置（カメラ）でもよいし、外部で取得した画像を入力するためのコンピュータの一部でもよい。解析部１２０は、得られた画像を解析するための装置である。解析部１２０は、上述したように、得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化する。また、解析部１２０は、上述したように、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する。さらに、解析部１２０は、上述したように、選定された前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る。 The input unit 110 is a device that obtains an image of tissue stained with biomarkers or cells. The input unit 110 may obtain an image by taking an image, or may obtain an image by inputting an image acquired outside. The input unit 110 may be an imaging device (camera) for obtaining images of tissues stained with biomarkers or cells, or may be a part of a computer for inputting images obtained externally. The analysis unit 120 is a device for analyzing the obtained image. As described above, the analysis unit 120 obtains a local score that scores the properties of each cell in the obtained image, or divides the obtained image into a plurality of sections and scores the properties of each section. In addition, as described above, the analysis unit 120 selects the cell whose local score satisfies a predetermined condition, or selects the partition whose local score satisfies a predetermined condition. Further, the analysis unit 120 scores the properties of the selected cells or compartments to obtain a tissue summary score, as described above.
　制御部１３０は、ＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）と、格納されているＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）と、ＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）とを有する。ＣＰＵは、ＲＯＭから処理内容に応じた画像診断プログラムを読み出してＲＡＭに展開し、展開したプログラムと協働して画像診断装置１００の各ブロックの動作を集中制御する。このとき、記憶部に格納されている各種データが参照される。記憶部は、例えば不揮発性の半導体メモリ（いわゆるフラッシュメモリ）やハードディスクドライブである。制御部１３０には、コンピュータに、バイオマーカーまたは細胞を染色した組織の画像を得る工程と、得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得る工程と、細胞の局所スコアが所定の条件を満たす細胞を選定するか、または区画の局所スコアが所定の条件を満たす区画を選定する工程と、選定された、細胞または区画の特性をスコア化して組織の要約スコアを得る工程と、を実行させる画像診断プログラムが含まれている。 The control unit 130 has a CPU (Central Processing Unit), a stored ROM (Read Only Memory), and a RAM (Random Access Memory). The CPU reads an image diagnosis program corresponding to the processing contents from the ROM, develops it in the RAM, and centrally controls the operation of each block of the image diagnosis apparatus 100 in cooperation with the expanded program. At this time, various data stored in the storage unit are referenced. The storage unit is, for example, a nonvolatile semiconductor memory (so-called flash memory) or a hard disk drive. In the control unit 130, the computer is provided with a step of obtaining an image of tissue stained with biomarkers or cells, obtaining a local score that scores the characteristics of each cell in the obtained image, or obtaining a plurality of obtained images and obtaining a local score obtained by scoring the characteristics of each compartment, and selecting a cell whose local score satisfies a predetermined condition, or selecting a compartment whose local score satisfies a predetermined condition and scoring characteristics of selected cells or compartments to obtain a tissue summary score.
　制御部１３０は、通信部を介して、ＬＡＮ（Ｌｏｃａｌ　Ａｒｅａ　Ｎｅｔｗｏｒｋ）、ＷＡＮ（Ｗｉｄｅ　Ａｒｅａ　Ｎｅｔｗｏｒｋ）などの通信ネットワークに接続された外部の装置（例えばパーソナルコンピューター）との間で各種データの送受信を行う。制御部１３０は、例えば外部の装置から送信された画像データを受信し、この画像データ（入力画像データ）に基づいて画像診断を行う。通信部は、例えばＬＡＮカードなどの通信制御カードである。 The control unit 130 transmits and receives various data to and from an external device (for example, a personal computer) connected to a communication network such as LAN (Local Area Network) or WAN (Wide Area Network) via the communication unit. . The control unit 130 receives image data transmitted from an external device, for example, and performs image diagnosis based on this image data (input image data). The communication unit is, for example, a communication control card such as a LAN card.
　（効果）
　図５は、本実施の形態に係る画像診断方法の効果を説明するための図である。図５の横軸は、細胞または区画の累積度数（％）を示しており、縦軸は、局所スコアを示している。図５の実線は１回目の解析の結果を示しており、点線は２回目の解析の結果を示している。１回目の解析に使用した切片と、２回目の解析に使用した切片とは、隣接した切片である。ここでは、従来のＨＥＲ２検査ガイドによるスコアリングと、本実施の形態に係る画像診断方法よるスコアリングとについて比較する。 (effect)
FIG. 5 is a diagram for explaining the effect of the diagnostic imaging method according to this embodiment. The horizontal axis of FIG. 5 indicates the cumulative frequency (%) of cells or compartments, and the vertical axis indicates the local score. The solid line in FIG. 5 indicates the results of the first analysis, and the dotted line indicates the results of the second analysis. The slice used for the first analysis and the slice used for the second analysis are adjacent slices. Here, the scoring by the conventional HER2 examination guide and the scoring by the diagnostic imaging method according to the present embodiment will be compared.
　従来のＨＥＲ２検査ガイドによるスコアリングは、局所スコアが３＋の細胞（区画）が累積度数で何％あるかにより判定する。図５に示されるように、従来のＨＥＲ２検査ガイドによるスコアリングでは、１回目の解析において、局所スコアが３＋の細胞（区画）が１０％以上存在するため、要約スコアは３＋となる。一方、２回目の解析において、局所スコアが３＋の細胞（区画）が１０％未満存在するため、要約スコアは２＋となる。このように、従来のＨＥＲ２検査ガイドによるスコアリングでは、ほぼ同じ状態の組織を解析しても、解析結果に大きなバラツキが生じることがある。 Scoring by the conventional HER2 test guide is determined by the percentage of cumulative frequencies of cells (compartments) with a local score of 3+. As shown in FIG. 5, in the conventional HER2 test-guided scoring, the summary score is 3+ because there are 10% or more cells (compartments) with a local score of 3+ in the first analysis. On the other hand, in the second analysis, less than 10% of the cells (compartments) have a local score of 3+, resulting in a summary score of 2+. As described above, in the scoring by the conventional HER2 examination guide, even if the tissues in substantially the same state are analyzed, the analysis results may vary greatly.
　以下、実施例により本発明をさらに詳細に述べるが、本発明はこれらの実施例に限定されるものではない。 The present invention will be described in more detail below with reference to examples, but the present invention is not limited to these examples.
　図７Ａ、Ｂは、本発明を用いて解析した実例である。図７Ａの横軸は、ＤＡＢ染色した連続切片スライドを用いて、病理医により判定されたコア毎のＨＥＲ２スコアである。図７Ａの縦軸は、本発明を用いて解析されたコア毎の評価値である。図７Ｂは、ＤＡＢスコアに対して、本発明を用いて解析された評価値の最小スコアをカットポイントとして、暫定のＰＩＤスコアを算出しコンコーダンス表である。 　Figures 7A and B are examples analyzed using the present invention. The horizontal axis of FIG. 7A is the HER2 score per core as determined by a pathologist using DAB-stained serial section slides. The vertical axis in FIG. 7A is the evaluation value for each core analyzed using the present invention. FIG. 7B is a concordance table obtained by calculating a provisional PID score with the minimum score of evaluation values analyzed using the present invention as a cut point for the DAB score.
　検体は、ヒト乳がん組織のｍｉｃｒｏａｒｒａｙ　ｓｌｉｄｅを使用した。なお、Ｄｕｃｔａｌ　ｃａｒｃｉｎｏｍａ　ｉｎ　ｓｉｔｕ、ＤＡＢ判定不可コア、細胞質が染色されたコア、浸潤性乳管がん判定不能コア、非がんコア、剥がれたコアは、全２０８コアのうち、あらかじめ病理医により解析不適コアとして除外している。 A microarray slide of human breast cancer tissue was used as the specimen. Ductal carcinoma in situ, DAB undeterminable cores, cores with stained cytoplasm, invasive ductal carcinoma undeterminable cores, non-cancerous cores, and detached cores were analyzed in advance by a pathologist out of a total of 208 cores. Excluded as unsuitable core.
　評価値は、以下の方法で算出した。
　まず、スライドを、一次抗体とビオチン化された二次抗体で免疫染色し、ストレプトアビジンでコーティングされた蛍光ナノ粒子で標識した。ＰＩＤの粒子サイズは、約１３０ｎｍ（励起：５８０ｎｍ、蛍光：６２０ｎｍ）であった。次いで、バーチャルスライドスキャナにより、高精度のＷｈｏｌｅ　Ｓｌｉｄｅ　Ｉｍａｇｅ（ＷＳＩ）に変換した。次いで、得られたＷＳＩを、コア毎に画像分割した。次いで、分割された各コア画像に対して、病理医がアノテーションした浸潤領域のみを解析対象とし、それ以外をマスクする領域を、解析対象領域として設定した。 Evaluation values were calculated by the following method.
First, slides were immunostained with primary and biotinylated secondary antibodies and labeled with streptavidin-coated fluorescent nanoparticles. PID particle size was about 130 nm (excitation: 580 nm, fluorescence: 620 nm). Then, it was converted into a highly accurate Whole Slide Image (WSI) by a virtual slide scanner. Next, the obtained WSI was image-divided for each core. Next, for each segmented core image, only the infiltration region annotated by the pathologist was set as the analysis target, and the other masked region was set as the analysis target region.
　コア毎の評価値は、以下の手順で算出した。
　（１）蛍光画像を１２μｍ四方の区画に分割し、全区画のうち、解析対象領域内となっている区画のみを対象として、区画毎に区画内蛍光強度積算値を計算した。
　（２）（１）で算出した区画毎の値のうち、値が上位１０％までの区画の平均値を算出する。これをコア毎の評価値とした。 The evaluation value for each core was calculated by the following procedure.
(1) The fluorescence image was divided into 12 μm square sections, and among all the sections, only the sections within the analysis target area were targeted, and the fluorescence intensity integrated value within the section was calculated for each section.
(2) Among the values for each section calculated in (1), the average value of the sections with the top 10% values is calculated. This was used as the evaluation value for each core.
　（結果）
　ＨＥＲ２　３＋／２＋では、ＤＡＢスコア（病理医判定）とＰＩＤスコアとは、はほぼ一致していることがわかった。ＨＥＲ２　１＋／０について大きな乖離は見られなかった。以上より、ＰＩＤ染色されたスライドを本発明法でスコアリングすることで、ＨＥＲ２低発現領域（ＤＡＢ法で陰性と判定された組織）においても抗原が検出できることが示された。 (result)
In HER2 3+/2+, it was found that the DAB score (pathologist-determined) and the PID score were in close agreement. No significant divergence was seen for HER2 1+/0. From the above, it was demonstrated that antigens can be detected even in HER2 low expression regions (tissues determined as negative by the DAB method) by scoring PID-stained slides by the method of the present invention.
　本出願は、２０２１年３月２３日出願の特願２０２１－０４８９１７に基づく優先権を主張する。当該出願明細書および図面に記載された内容は、すべて本願明細書に援用される。 This application claims priority based on Japanese Patent Application No. 2021-048917 filed on March 23, 2021. All contents described in the specification and drawings are incorporated herein by reference.
　本発明によれば、例えば、乳がんなどのがん診断、その他各種疾病の診断などに有用である。 According to the present invention, for example, it is useful for diagnosing cancer such as breast cancer, and diagnosing various other diseases.
　１００　画像診断装置
　１１０　入力部
　１２０　解析部
　１３０　制御部 100 diagnostic imaging apparatus 110 input unit 120 analysis unit 130 control unit

Claims (10)

  1. 　バイオマーカーまたは細胞を染色した組織の画像を得る工程と、
    　得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得る工程と、
    　前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する工程と、
    　選定された、前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る工程と、
    　を有する、画像診断方法。     obtaining an image of the tissue stained for biomarkers or cells;
    Obtaining a local score that scores the characteristics of each cell in the obtained image, or partitioning the obtained image into a plurality of sections and obtaining a local score that scores the characteristics of each partition;
    selecting the cell where the local score of the cell satisfies a predetermined condition, or selecting the compartment where the local score of the compartment satisfies a predetermined condition;
    scoring characteristics of the selected cells or compartments to obtain a tissue summary score;
    A diagnostic imaging method comprising:
  2. 　前記画像を得る工程の後であって、前記局所スコアを得る工程の前に、前記局所スコアを算出しない前記細胞または前記区画を除外する工程をさらに有する、請求項１に記載の画像診断方法。 The diagnostic imaging method according to claim 1, further comprising, after the step of obtaining the image and before the step of obtaining the local score, the step of excluding the cells or the compartments for which the local score is not calculated.
  3. 　前記除外する工程では、所定の数の前記細胞が含まれていない前記区画を除外する、請求項２に記載の画像診断方法。 The diagnostic imaging method according to claim 2, wherein the excluding step excludes the compartments that do not contain a predetermined number of the cells.
  4. 　前記選定する工程では、前記局所スコアが上位または下位から一定範囲の前記細胞または前記区画を選定するか、前記局所スコアが所定の範囲である前記細胞または前記区画を選定する、請求項１～３のいずれか一項に記載の画像診断方法。 Claims 1 to 3, wherein in the selecting step, the cells or the compartments with the local scores in a certain range from the top or the bottom are selected, or the cells or the compartments with the local scores within a predetermined range are selected. The diagnostic imaging method according to any one of .
  5. 　前記選定する工程では、前記局所スコアが所定の範囲内にある前記細胞または前記区画から、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する、請求項１～３のいずれか一項に記載の画像診断方法。 In the selecting step, from the cells or the compartments whose local scores are within a predetermined range, select the cells whose local scores satisfy a predetermined condition, or select the cells where the local scores of the compartments meet a predetermined condition. The diagnostic imaging method according to any one of claims 1 to 3, wherein said section satisfying a predetermined condition is selected.
  6. 　前記局所スコアを得る工程では、前記細胞または前記区画のどちらか一方について、２種類の前記局所スコアを算出し、
    　前記選定する工程では、２種類の前記局所スコアのうち、一方の前記局所スコアを用いて前記細胞または前記区画を選定し、
    　前記要約スコアを得る工程では、他方の前記局所スコアを用いて前記細胞または前記区画の特性をスコア化した組織の前記局所スコアを算出する、
    　請求項１～３のいずれか一項に記載の画像診断方法。     In the step of obtaining the local score, for either the cell or the compartment, two types of the local score are calculated;
    In the selecting step, one of the two types of local scores is used to select the cell or the compartment,
    In obtaining the summary score, calculating the local score of the tissue scored for the properties of the cell or the compartment using the other local score;
    The diagnostic imaging method according to any one of claims 1 to 3.
  7. 　前記選定する工程では、全ての前記細胞または全ての前記区画から、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定するか、または任意に選択した複数の前記細胞または複数の前記区画から、前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する、請求項１～６のいずれか一項に記載の画像診断方法。 In the selecting step, from all of the cells or all of the compartments, select the cells in which the local score of the cell satisfies a predetermined condition, or the cells in which the local score of the compartment satisfies a predetermined condition. Select a compartment, or select the cell where the local score of the cell satisfies a predetermined condition from the arbitrarily selected plurality of cells or the plurality of compartments, or select the cell where the local score of the compartment meets a predetermined condition The diagnostic imaging method according to any one of claims 1 to 6, wherein the section that satisfies the condition of
  8. 　前記要約スコアを得る工程の後に、前記要約スコアを複数段階の評価値に変換する工程をさらに有する、請求項１～７のいずれか一項に記載の画像診断方法。 The diagnostic imaging method according to any one of claims 1 to 7, further comprising, after the step of obtaining the summary score, the step of converting the summary score into a multi-stage evaluation value.
  9. 　バイオマーカーまたは細胞を染色した組織の画像を入力するための入力部と、
    　前記入力部で入力された画像を解析するための解析部と、を有し、
    　前記解析部は、
    　前記画像における各細胞の特性をスコア化した局所スコアを得るか、または前記画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得て、
    　前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定し、
    　選定された前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る、
    　画像診断装置。     an input unit for inputting an image of tissue stained for biomarkers or cells;
    an analysis unit for analyzing the image input by the input unit;
    The analysis unit is
    Obtaining a local score that scores the characteristics of each cell in the image, or partitioning the image into a plurality of sections and obtaining a local score that scores the characteristics of each partition,
    selecting the cell where the local score of the cell satisfies a predetermined condition, or selecting the compartment where the local score of the compartment satisfies a predetermined condition;
    Scoring properties of the selected cells or compartments to obtain a tissue summary score;
    diagnostic imaging equipment.
  10. 　コンピュータに、
    　バイオマーカーまたは細胞を染色した組織の画像を得る工程と、
    　得られた画像における各細胞の特性をスコア化した局所スコアを得るか、または得られた画像を複数に区画化し、各区画の特性をスコア化した局所スコアを得る工程と、
    　前記細胞の前記局所スコアが所定の条件を満たす前記細胞を選定するか、または前記区画の前記局所スコアが所定の条件を満たす前記区画を選定する工程と、
    　選定された、前記細胞または前記区画の特性をスコア化して組織の要約スコアを得る工程と、
    　を実行させる、画像診断プログラム。     to the computer,
    obtaining an image of the tissue stained for biomarkers or cells;
    Obtaining a local score that scores the characteristics of each cell in the obtained image, or partitioning the obtained image into a plurality of sections and obtaining a local score that scores the characteristics of each partition;
    selecting the cell where the local score of the cell satisfies a predetermined condition, or selecting the compartment where the local score of the compartment satisfies a predetermined condition;
    scoring characteristics of the selected cells or compartments to obtain a tissue summary score;
    diagnostic imaging program.
PCT/JP2021/047262 2021-03-23 2021-12-21 Image diagnosis method, image diagnosis apparatus, and image diagnosis program WO2022201691A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2023508630A JPWO2022201691A1 (en) 2021-03-23 2021-12-21

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-048917 2021-03-23
JP2021048917 2021-03-23

Publications (1)

Publication Number Publication Date
WO2022201691A1 true WO2022201691A1 (en) 2022-09-29

Family

ID=83396723

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/047262 WO2022201691A1 (en) 2021-03-23 2021-12-21 Image diagnosis method, image diagnosis apparatus, and image diagnosis program

Country Status (2)

Country Link
JP (1) JPWO2022201691A1 (en)
WO (1) WO2022201691A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011179924A (en) * 2010-02-26 2011-09-15 Olympus Corp Microscope system, specimen observation method, and program
JP2016001179A (en) * 2005-05-13 2016-01-07 トリパス イメージング インコーポレイテッド Image analysis method based on chromogen separation
JP2020201271A (en) * 2015-10-23 2020-12-17 ノバルティス・エイジーＮｏｖａｒｔｉｓ ＡＧ Method of determining score representative of spatial proximity between cells from sample comprising tumor tissue
JP2021006037A (en) * 2014-09-03 2021-01-21 ヴェンタナ メディカル システムズ， インク． System and method for calculating immune score

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016001179A (en) * 2005-05-13 2016-01-07 トリパス イメージング インコーポレイテッド Image analysis method based on chromogen separation
JP2011179924A (en) * 2010-02-26 2011-09-15 Olympus Corp Microscope system, specimen observation method, and program
JP2021006037A (en) * 2014-09-03 2021-01-21 ヴェンタナ メディカル システムズ， インク． System and method for calculating immune score
JP2020201271A (en) * 2015-10-23 2020-12-17 ノバルティス・エイジーＮｏｖａｒｔｉｓ ＡＧ Method of determining score representative of spatial proximity between cells from sample comprising tumor tissue

Also Published As

Publication number Publication date
JPWO2022201691A1 (en) 2022-09-29

Similar Documents

Publication Publication Date Title
US8160348B2 (en) Methods and system for validating sample images for quantitative immunoassays
JP6654634B2 (en) Methods, systems and devices for quantitatively analyzing heterogeneous biomarker distributions
US7522757B2 (en) Method and apparatus for computer controlled cell based diagnosis
US9607379B1 (en) Methods for feature analysis on consecutive tissue sections
KR20220119447A (en) Method for supporting pathology diagnosis using AI, and supporting device
US20130078636A1 (en) Method for detecting and quantitating multiple subcellular components
CN106462767B (en) Inspection device for processing and analyzing images
US20060068377A1 (en) Method and apparatus for computer controlled rare cell, including fetal cell, based diagnosis
PT1334461E (en) Method and system for analyzing cells
JP2008518587A (en) Detection and quantification of subcellular components
US20080206774A1 (en) Automated cancer diagnostic methods using fish
CN114782372B (en) DNA fluorescence in situ hybridization BCR/ABL fusion state detection method and detection system
WO2022201691A1 (en) Image diagnosis method, image diagnosis apparatus, and image diagnosis program
EP4120187A1 (en) A method for measuring a prognostic marker in prostate cancer
US11908130B2 (en) Apparatuses and methods for digital pathology
JP2022142461A (en) Diagnostic imaging method, diagnostic imaging device, and diagnostic imaging program
EP1354210B1 (en) Method for cancer diagnostics
JP6592854B2 (en) Method for determining c-MYC gene translocation
Selcuk et al. Automated HER2 Scoring in Breast Cancer Images Using Deep Learning and Pyramid Sampling
Baird et al. Multiplex: From Acquisition to Analysis
TW202230394A (en) Method for evaluating immune status of tumor samples
Conway Comparison of Digital Image Analysis with Manual Reads for Chromogenic RNA ISH Slides
Bredfeldt Collagen Alignment Imaging and Analysis for Breast Cancer Classification
Conway Aperio RNA ISH Algorithm Validation
Markiewicz et al. Automatic ROI selection in virtual slide images for assessment of pathomorphological diagnostic

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: 21933281

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023508630

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21933281

Country of ref document: EP

Kind code of ref document: A1