WO2013161155A1 - 画像計測装置、画像計測方法、および、画像計測用プログラム - Google Patents
画像計測装置、画像計測方法、および、画像計測用プログラム Download PDFInfo
- Publication number
- WO2013161155A1 WO2013161155A1 PCT/JP2013/001449 JP2013001449W WO2013161155A1 WO 2013161155 A1 WO2013161155 A1 WO 2013161155A1 JP 2013001449 W JP2013001449 W JP 2013001449W WO 2013161155 A1 WO2013161155 A1 WO 2013161155A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- region
- measurement
- mask
- tissue
- Prior art date
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 132
- 238000000691 measurement method Methods 0.000 title claims description 6
- 239000000284 extract Substances 0.000 claims abstract description 5
- 210000001519 tissue Anatomy 0.000 claims description 113
- 210000003855 cell nucleus Anatomy 0.000 claims description 59
- 238000010186 staining Methods 0.000 claims description 48
- 238000000034 method Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 206010028980 Neoplasm Diseases 0.000 description 22
- 201000011510 cancer Diseases 0.000 description 17
- 230000010354 integration Effects 0.000 description 16
- 238000003364 immunohistochemistry Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000009545 invasion Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 210000002536 stromal cell Anatomy 0.000 description 4
- 230000001575 pathological effect Effects 0.000 description 3
- WZUVPPKBWHMQCE-UHFFFAOYSA-N Haematoxylin Chemical compound C12=CC(O)=C(O)C=C2CC2(O)C1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-UHFFFAOYSA-N 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 206010006187 Breast cancer Diseases 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- YQGOJNYOYNNSMM-UHFFFAOYSA-N eosin Chemical compound [Na+].OC(=O)C1=CC=CC=C1C1=C2C=C(Br)C(=O)C(Br)=C2OC2=C(Br)C(O)=C(Br)C=C21 YQGOJNYOYNNSMM-UHFFFAOYSA-N 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 210000004907 gland Anatomy 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 230000001926 lymphatic effect Effects 0.000 description 1
- 210000004698 lymphocyte Anatomy 0.000 description 1
- 230000001338 necrotic effect Effects 0.000 description 1
- 210000004940 nucleus Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N15/14—Optical investigation techniques, e.g. flow cytometry
- G01N15/1429—Signal processing
- G01N15/1433—Signal processing using image recognition
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
-
- 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
- G06T2207/30096—Tumor; Lesion
-
- 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
- G06T2207/30221—Sports video; Sports image
- G06T2207/30224—Ball; Puck
-
- 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
- G06T2207/30242—Counting objects in image
Definitions
- the present invention relates to an image measurement apparatus, an image measurement method, and an image measurement program for measuring information on an object included in a tissue from a stained tissue specimen image.
- the number of cell nuclei contained in a target region is measured from an image of an immunostained pathological tissue specimen (IHC (Immuno-histochemistry) specimen).
- IHC immunostained pathological tissue specimen
- a system for measuring an image measures the number of cell nuclei in the designated region for each staining intensity.
- Non-Patent Document 1 describes a method of automatically recognizing a cell nucleus equivalent to a learned cell nucleus from the entire tissue region of a specimen.
- Non-Patent Document 2 describes a method for determining the staining intensity and calculating the number of cell nuclei for each staining intensity for cell nuclei automatically recognized by the method described in Non-Patent Document 1.
- FIG. 5 is an explanatory diagram showing the recognition result of the measurement object by the method described in Non-Patent Document 1.
- FIG. 5 shows that the result of recognizing the designated measurement target tissue is displayed individually.
- Patent Document 1 describes a breast cancer pathological image diagnosis support system that calculates a staining positive cell content rate.
- the system described in Patent Document 1 matches a tumor region acquired from an HE (Hematoxylin and Eosin stain) stained image with a tumor region in an IHC image, and based on information on the tumor region in the specified IHC image, The staining positive cell content in the tumor area is calculated.
- HE Hematoxylin and Eosin stain
- the numerical values such as staining intensity or positive / negative of individual cell nuclei obtained as a calculation result are summed over the entire tissue region. It will be used as a single value. In this case, for example, the staining heterogeneity of each region showing cancer cannot be observed as a numerical value.
- Non-Patent Document 1 by referring to the recognition result by the method described in Non-Patent Document 1, it is possible to grasp the distribution of individual cell nuclei to be measured from the image of the IHC sample. However, it is difficult for the user to understand what the recognized area to be measured has, such as the dyeability of the area, only by the information shown in FIG.
- an object of the present invention is to provide an image measurement device, an image measurement method, and an image measurement program that can measure the content indicated by the region of the object in an aspect that is easy for the user to understand from the image representing the tissue specimen.
- An image measuring apparatus includes a tissue region recognizing unit for recognizing a tissue region from an image obtained by staining a tissue including a measurement object and a non-measurement object, and a constant magnification having a predetermined size from the tissue region.
- a partial image extracting means for extracting the image of the image
- a mask generating means for generating a mask for removing the non-measurement target area, which is an area where the non-measurement target exists, from the tissue area for each extracted image, and for each image
- a global mask generation that generates a temporary global mask that integrates the generated masks and generates a global mask that includes one or more target areas by combining adjacent parts of the temporary global mask that are not masked.
- An image measurement method recognizes a tissue region from an image obtained by staining a tissue including a measurement object and a non-measurement object, and extracts an image with a predetermined size and a predetermined magnification from the tissue region. For each extracted image, generate a mask to remove the non-measurement target area, which is the area where the non-measurement target exists, from the tissue area, and generate a temporary whole mask that integrates the mask generated for each image. A whole mask is generated by combining the adjacent unmasked parts of the temporary whole mask into one or more target areas, and the measurement target included in the image is extracted for each image extracted from the tissue area. Information on the object is measured, and information on the measurement object is calculated for each target region from the measured information and the entire mask.
- the program for image measurement is a computer program for tissue region recognition processing for recognizing a tissue region from an image obtained by staining a tissue including a measurement object and a non-measurement object, and a predetermined size from the tissue region.
- Partial image extraction process for extracting an image at a constant magnification
- mask generation process for generating a mask for removing a non-measurement target area, which is an area where a non-measurement target exists, from a tissue area for each extracted image
- image An overall mask that generates a temporary overall mask that integrates the masks generated for each of the masks, and generates an overall mask that includes one or more target regions by combining adjacent portions of the temporary overall mask that are not masked.
- a measurement process for measuring information on the measurement object included in the image, and the measurement And a broadcast and entire mask characterized in that to execute the region information calculating process for calculating information related to the measurement object for each target area.
- the present invention it is possible to measure the content indicated by the region of the object from the image representing the tissue specimen in a manner that is easy for the user to understand.
- FIG. 1 is a block diagram showing an embodiment of an image measuring apparatus according to the present invention.
- the image measurement apparatus according to the present embodiment includes an image storage unit 1, a tissue region recognition unit 2, a tissue region segmentation unit 3, a mask generation unit 4, a mask integration unit 5, a cell nucleus count measurement unit 6, and a result display. Part 7.
- the image storage unit 1 stores an image S001 obtained by scanning a tissue specimen.
- the image obtained by scanning the tissue specimen is, for example, an image of an immunostained pathological tissue specimen.
- the tissue specimen image includes various structures. Examples of structures include cancer areas (cancer areas that do not distinguish between the presence or absence of invasion), cancer areas with invasion, cancer areas without invasion, benign disease areas, normal areas that are not lesions, gland duct areas, blood vessel areas, Examples include a lymphatic region, an epithelial region, a stromal region, a lymphocyte, an artifact region, a necrotic region, and a fat region. However, the structure is not limited to these contents.
- a measurement target structure hereinafter referred to as a measurement target
- a non-measurement target structure hereinafter referred to as a non-measurement target
- a “cancer area without invasion” can be a measurement object or a non-measurement object depending on the purpose of the system.
- the image storage unit 1 is realized by, for example, a magnetic disk.
- the image measurement device includes the image storage unit 1
- the image measurement device may receive an image obtained by imaging a tissue specimen from another device. In this case, the image measurement device may not include the image storage unit 1.
- the tissue region recognition unit 2 recognizes the entire tissue region S002 (also referred to as a tissue region) from the image S001 stored in the image storage unit 1.
- a tissue specimen image includes a region that is not a tissue specimen image (for example, a slide glass) in addition to the above-described measurement object and non-measurement object. Therefore, the tissue region recognition unit 2 may recognize the tissue region by removing a portion that is not a tissue specimen image from the image S001.
- the tissue region cutout unit 3 cuts out the image of the entire tissue region S002 recognized by the tissue region recognition unit 2 into an image S003 having a fixed size and a constant magnification. Specifically, the tissue region cutout unit 3 extracts an image S003 having a predetermined size and a predetermined magnification from the tissue region.
- the mask generation unit 4 recognizes a region where a non-measurement target exists (hereinafter, referred to as a non-measurement target region) for each image cut out by the tissue region cut-out unit 3 (that is, the image S003), and sets the mask S004. calculate. Specifically, the mask generation unit 4 generates a mask S004 for removing the non-measurement target region from the tissue region for each of the cut out images. For example, when the stromal cell is a non-measurement target, the mask generation unit 4 may recognize a region including the stromal cell for each image S003 and calculate the mask.
- the mask generation unit 4 converts the tissue specimen image into a gray scale image.
- the mask generation unit 4 performs a smoothing process such as a Gaussian filter on the converted grayscale image.
- a smoothing process such as a Gaussian filter
- the density difference decreases in the area of the measurement object, and the whole becomes one lump.
- the stained discrete stromal cell nucleus changes to a high luminance value under the influence of surrounding pixels having a high luminance value.
- the mask generation unit 4 generates a luminance value histogram of the smoothed image, and calculates a threshold value for separating the interstitial region from the measurement target region.
- the mask generation unit 4 may calculate the threshold value by, for example, dynamic programming.
- the mask generation unit 4 generates a mask by performing binarization processing based on this threshold value.
- the method of generating the mask is not limited to the above method. As long as it is a method that can identify a region where a non-measurement target included in a tissue specimen image (tissue region) exists, the mask generation unit 4 may generate a mask using another method.
- the mask integration unit 5 generates an overall mask S005 corresponding to the entire tissue region by integrating the entire mask calculated for each cut-out image.
- the mask integration unit 5 integrates the masks generated for each extracted image.
- this integrated mask is referred to as a temporary whole mask.
- the mask integration unit 5 generates an overall mask that includes one or more target regions by combining adjacent portions of the unmasked portion of the temporary overall mask.
- the part that is not masked corresponds to the part to be measured in the tissue specimen image. Therefore, grouping adjacent unmasked parts means grouping adjacent measurement target parts in the tissue specimen image. In this way, the measurement targets in the tissue specimen image are collected into several target areas. In other words, it can be said that the mask integration unit 5 collects the tissue specimen images for each meaningful region by generating such a target region.
- the mask integration unit 5 performs image processing on the temporary whole mask so as to generate the target region described above.
- the mask integration unit 5 may generate each target region by performing image processing such as expansion processing, reduction processing, closing processing, opening processing, hole filling processing, and small region deletion processing on the temporary whole mask. Good. By doing in this way, the measurement object in the tissue specimen image can be collected into a meaningful area such as a cancer area, for example.
- the cell nucleus number measurement unit 6 measures the number of cell nuclei for each staining intensity for each image cut out by the tissue region cutout unit 3 (ie, image S003).
- information indicating the number of cell nuclei for each staining intensity measured by the cell nuclei counting unit 6 is referred to as cell nuclei count information S006.
- the number of cell nuclei for each staining intensity is an example of information measured by the cell nuclei counting unit 6.
- the cell nucleus number measurement unit 6 may measure other information related to the measurement object included in the image cut out by the tissue region cutout unit 3.
- the result display unit 7 outputs a result for each measurement target area such as cancer. Specifically, the result display unit 7 calculates information on the measurement object for each target region from the information measured by the cell nucleus number measurement unit 6 and the entire mask.
- the result display unit 7 calculates, for each cancer region, the measurement result and the positive rate of the number of cell nuclei for each staining intensity based on, for example, the entire mask S005 corresponding to the entire tissue region and the cell nucleus count measurement information S006. . Then, the result display unit 7 displays a result image S007 indicating the calculation result.
- the result display unit 7 may output information related to the measurement object for each target region, for example, by superimposing the target region on an image S001 obtained by scanning a tissue specimen.
- FIG. 2 is an explanatory diagram showing an example of an output result image S007 by the result display unit 7. As shown in FIG. In the example illustrated in FIG. 2, there are two measurement target objects (for example, cancer) target areas, and a positive rate is displayed in association with each target area and the entire area.
- two measurement target objects for example, cancer
- the measurement objects are grouped into meaningful areas. Therefore, by displaying the number of cell nuclei and the positive rate by staining intensity for each region, it becomes possible to observe the staining heterogeneity for each cancer region in the entire tissue region.
- the area distribution (histogram) of the positive rate can be obtained only for the measurement target region in the entire tissue region.
- the tissue region recognition unit 2, the tissue region cutout unit 3, the mask generation unit 4, the mask integration unit 5, the cell nucleus number measurement unit 6, and the result display unit 7 operate according to a program (an image measurement program).
- a program an image measurement program
- the program is stored in a storage unit (not shown) of the image measurement device, and the CPU reads the program, and in accordance with the program, the tissue region recognition unit 2, the tissue region segmentation unit 3, the mask generation unit 4, and the mask integration
- the unit 5, the cell nucleus number measurement unit 6, and the result display unit 7 may be operated.
- the tissue region recognition unit 2, the tissue region segmentation unit 3, the mask generation unit 4, the mask integration unit 5, the cell nucleus count measurement unit 6, and the result display unit 7 are each realized by dedicated hardware. May be.
- FIG. 3 is an explanatory diagram illustrating an example of an operation for displaying a positive rate for each region indicating a measurement target from an image obtained by scanning a tissue specimen.
- the tissue region recognition unit 2 recognizes the tissue region S002 from the image S001.
- the tissue region cutout unit 3 extracts an image S003 having a predetermined size and a predetermined magnification from the tissue region S002.
- the mask generation unit 4 generates a mask S004 for each extracted image S003.
- the mask integration unit 5 integrates the mask S004 generated for each image S003 to generate a temporary overall mask S008.
- the mask integration unit 5 generates an overall mask S005 as one or more target areas S009 by collecting adjacent portions of the temporary overall mask S008 that are not masked.
- each target region S009 is a region generated by performing image processing such as expansion processing on the portion shown in white in the temporary overall mask S008, and is included in the overall mask S005.
- the cell nucleus number measurement unit 6 measures information related to the measurement object included in each image S003. For example, the cell nucleus number measurement unit 6 measures the number of cell nuclei for each staining intensity included in each image S003 to generate cell nucleus number measurement information S006.
- the result display unit 7 calculates information on a measurement target (for example, cancer) for each target region S009 from the measured information (cell nucleus count measurement information S006) and the entire mask S005.
- the result display unit 7 calculates, for example, the measurement result of the number of cell nuclei for each staining intensity and the positive rate for each target region S009. Then, the output result unit 7 outputs the calculation result.
- the tissue region recognition unit 2 recognizes the tissue region S002 from the image S001 (for example, an IHC sample image) obtained by scanning the tissue sample, and the tissue region cutout unit 3 An image S003 having a predetermined size and a predetermined magnification is extracted from the region S002.
- the mask generation unit 4 generates a mask S004 for removing the non-measurement object region from the tissue region, and the mask integration unit 5 generates a temporary entire mask S008 that integrates the mask S004. To do.
- the mask integration unit 5 generates an overall mask S005 that combines the adjacent portions of the unmasked portions in the temporary overall mask S008 into one or more target regions S009.
- the cell nucleus number measurement unit 6 measures information S006 (for example, the number of cell nuclei for each staining intensity) related to the measurement object (for example, cancer) included in the image.
- the result display unit 7 calculates information on the measurement object (for example, the measurement result and the positive rate of the cell nuclei for each staining intensity) for each target region S009 from the measured information S006 and the entire mask S005.
- the image measuring apparatus of the present embodiment it is not necessary to select a region to be measured in advance, so that it is possible to save the user's trouble.
- the staining heterogeneity for each cancer region can be clearly shown on the IHC specimen, and the area distribution (histogram) of the positive rate for only the cancer region in the entire tissue region can be calculated. Can help determine.
- the unit of the region is too fine to display the cell nucleus number and the positive rate, so it is difficult for the user to understand the contents. Therefore, as a result, even though the region (distribution) to be measured can be referred to, the number of cell nuclei and the positive rate are practically only one value for the whole specimen or the entire designated region. I can't.
- FIG. 4 is a block diagram showing an outline of an image measuring apparatus according to the present invention.
- An image measurement apparatus recognizes a tissue region from an image (for example, an image of an IHC specimen) obtained by staining a tissue including a measurement target (for example, cancer) and a non-measurement target.
- Means 81 for example, tissue region recognition unit 2), partial image extraction unit 82 (for example, tissue region segmentation unit 3) for extracting an image of a predetermined magnification having a predetermined size from the tissue region, and each extracted image
- the mask generation unit 83 for example, the mask generation unit 4 that generates a mask for removing the non-measurement target region, which is a region where the non-measurement target exists, from the tissue region and the mask generated for each image are integrated.
- information for example, the number of cell nuclei for each staining intensity
- Information calculation means 86 (result display section 7).
- the measuring means 85 may measure the number of cell nuclei for each staining intensity for each image extracted by the partial image extracting means 82. Then, the region information calculation unit 86 may calculate the measurement result of the number of cell nuclei for each staining intensity for each target region from the measured number of cell nuclei for each staining intensity and the entire mask.
- the region information calculation means 86 may calculate a positive rate for each target region from the measured number of cell nuclei for each staining intensity and the entire mask.
- the image measuring apparatus outputs information related to the measurement object for each target region calculated by the region information calculating unit 86 together with an image obtained by staining the tissue and outputting the information in association with the target region (for example, A result display unit 7) may be provided.
- the present invention is suitably applied to an image measuring apparatus that measures information on an object contained in a tissue from a stained tissue specimen image.
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Immunology (AREA)
- Dispersion Chemistry (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Description
2 組織領域認識部
3 組織領域切り出し部
4 マスク生成部
5 マスク統合部
6 細胞核数計測部
7 結果表示部
Claims (10)
- 計測対象物と非計測対象物とを含む組織を染色して撮像した画像から組織領域を認識する組織領域認識手段と、
前記組織領域から予め定めた大きさの一定倍率の画像を抽出する部分画像抽出手段と、
抽出された画像ごとに、前記非計測対象物が存在する領域である非計測対象領域を前記組織領域から除くためのマスクを生成するマスク生成手段と、
前記画像ごとに生成されたマスクを統合した仮全体マスクを生成し、当該仮全体マスクにおけるマスクされていない部分のうち近接する当該部分をまとめて1つ以上の対象領域とした全体マスクを生成する全体マスク生成手段と、
前記部分画像抽出手段によって抽出された画像ごとに、当該画像に含まれる計測対象物に関する情報を計測する計測手段と、
計測された情報と前記全体マスクとから、前記対象領域ごとに計測対象物に関する情報を算出する領域情報算出手段とを備えた
ことを特徴とする画像計測装置。 - 計測手段は、部分画像抽出手段によって抽出された画像ごとに、染色強度別の細胞核数を計測し、
領域情報算出手段は、計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに染色強度別の細胞核数の計測結果を算出する
請求項1記載の画像計測装置。 - 計測手段は、部分画像抽出手段によって抽出された画像ごとに、染色強度別の細胞核数を計測し、
領域情報算出手段は、計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに陽性率を算出する
請求項1または請求項2記載の画像計測装置。 - 領域情報算出手段により算出された対象領域ごとの計測対象物に関する情報を、組織を染色して撮像した画像とともに、前記対象領域に対応づけて出力する出力手段を備えた
請求項1から請求項3のうちのいずれか1項に記載の画像計測装置。 - 計測対象物と非計測対象物とを含む組織を染色して撮像した画像から組織領域を認識し、
前記組織領域から予め定めた大きさの一定倍率の画像を抽出し、
抽出された画像ごとに、前記非計測対象物が存在する領域である非計測対象領域を前記組織領域から除くためのマスクを生成し、
前記画像ごとに生成されたマスクを統合した仮全体マスクを生成し、
前記仮全体マスクにおけるマスクされていない部分のうち近接する当該部分をまとめて1つ以上の対象領域とした全体マスクを生成し、
組織領域から抽出された前記画像ごとに、当該画像に含まれる計測対象物に関する情報を計測し、
計測された情報と前記全体マスクとから、前記対象領域ごとに計測対象物に関する情報を算出する
ことを特徴とする画像計測方法。 - 組織領域から抽出された画像ごとに、染色強度別の細胞核数を計測し、
計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに染色強度別の細胞核数の計測結果を算出する
請求項5記載の画像計測方法。 - 組織領域から抽出された画像ごとに、染色強度別の細胞核数を計測し、
計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに陽性率を算出する
請求項5または請求項6記載の画像計測装置。 - コンピュータに、
計測対象物と非計測対象物とを含む組織を染色して撮像した画像から組織領域を認識する組織領域認識処理、
前記組織領域から予め定めた大きさの一定倍率の画像を抽出する部分画像抽出処理、
抽出された画像ごとに、前記非計測対象物が存在する領域である非計測対象領域を前記組織領域から除くためのマスクを生成するマスク生成処理、
前記画像ごとに生成されたマスクを統合した仮全体マスクを生成し、当該仮全体マスクにおけるマスクされていない部分のうち近接する当該部分をまとめて1つ以上の対象領域とした全体マスクを生成する全体マスク生成処理、
前記部分画像抽出処理で抽出された画像ごとに、当該画像に含まれる計測対象物に関する情報を計測する計測処理、および、
計測された情報と前記全体マスクとから、前記対象領域ごとに計測対象物に関する情報を算出する領域情報算出処理
を実行させるための画像計測用プログラム。 - コンピュータに、
計測処理で、部分画像抽出処理で抽出された画像ごとに、染色強度別の細胞核数を計測させ、
領域情報算出処理で、計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに染色強度別の細胞核数の計測結果を算出させる
請求項8記載の画像計測用プログラム。 - コンピュータに、
計測処理で、部分画像抽出処理で抽出された画像ごとに、染色強度別の細胞核数を計測させ、
領域情報算出処理で、計測された染色強度別の細胞核数と全体マスクとから、対象領域ごとに陽性率を算出させる
請求項8または請求項9記載の画像計測用プログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014512308A JP5924406B2 (ja) | 2012-04-23 | 2013-03-07 | 画像計測装置、画像計測方法、および、画像計測用プログラム |
US14/395,583 US9390313B2 (en) | 2012-04-23 | 2013-03-07 | Image measurement apparatus and image measurment method measuring the cell neclei count |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012-097561 | 2012-04-23 | ||
JP2012097561 | 2012-04-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013161155A1 true WO2013161155A1 (ja) | 2013-10-31 |
Family
ID=49482513
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/001449 WO2013161155A1 (ja) | 2012-04-23 | 2013-03-07 | 画像計測装置、画像計測方法、および、画像計測用プログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US9390313B2 (ja) |
JP (1) | JP5924406B2 (ja) |
WO (1) | WO2013161155A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105654173A (zh) * | 2016-01-06 | 2016-06-08 | 大连海洋大学 | 工业螺母区域标定与个数检测方法 |
JP2018512072A (ja) * | 2015-01-31 | 2018-05-10 | ベンタナ メディカル システムズ, インコーポレイテッド | 自動化スライド全域解析の品質管理 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09138854A (ja) * | 1995-11-15 | 1997-05-27 | Nec Corp | 画像の領域抽出方法及び装置 |
JP2004532410A (ja) * | 2001-04-20 | 2004-10-21 | イェール ユニバーシティ | 細胞および組織の自動分析のためのシステムおよび方法 |
JP2005530138A (ja) * | 2002-06-18 | 2005-10-06 | ライフスパン バイオサイエンス,インク. | 組織標本の中の重要な構造のコンピュータを利用した画像捕捉 |
JP2009508200A (ja) * | 2005-09-09 | 2009-02-26 | キネティック リミテッド | 画像領域の自動選定 |
JP2010281636A (ja) * | 2009-06-03 | 2010-12-16 | Nec Corp | 病理組織画像解析装置、病理組織画像解析方法、病理組織画像解析プログラム |
JP2011210156A (ja) * | 2010-03-30 | 2011-10-20 | Nec Corp | 画像処理装置、画像読取装置、画像処理方法及び画像処理プログラム |
WO2012011579A1 (ja) * | 2010-07-23 | 2012-01-26 | 独立行政法人産業技術総合研究所 | 病理組織画像の領域分割画像データ作成システム及び病理組織画像の特徴抽出システム |
WO2012043498A1 (ja) * | 2010-09-30 | 2012-04-05 | 日本電気株式会社 | 情報処理装置、情報処理システム、情報処理方法、プログラム及び記録媒体 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07262355A (ja) * | 1994-03-18 | 1995-10-13 | Fuji Electric Co Ltd | 画像監視装置 |
US6259807B1 (en) * | 1997-05-14 | 2001-07-10 | Applied Imaging Corp. | Identification of objects of interest using multiple illumination schemes and finding overlap of features in corresponding multiple images |
JP2006095223A (ja) * | 2004-09-30 | 2006-04-13 | Pola Chem Ind Inc | 角層細胞の鑑別法 |
EP1978485A1 (en) * | 2005-05-13 | 2008-10-08 | Tripath Imaging, Inc. | Methods of chromogen separation-based image analysis |
JP5663873B2 (ja) * | 2007-03-01 | 2015-02-04 | 日本電気株式会社 | 乳癌病理画像診断支援システム、乳癌病理画像診断支援方法、乳癌病理画像診断支援プログラム、及び、乳癌病理画像診断支援プログラムを記録した記録媒体 |
JP5245424B2 (ja) * | 2008-01-25 | 2013-07-24 | 日本電気株式会社 | 病理組織画像撮影システム、病理組織画像撮影方法、および病理組織画像撮影プログラム |
EP2438186A4 (en) * | 2009-06-01 | 2012-11-28 | Targeted Molecular Diagnostics Llc | PROCESS FOR PTEN DETECTION AND QUANTIFICATION |
PT2779089T (pt) * | 2010-07-30 | 2019-02-19 | Fund D Anna Sommer Champalimaud E Dr Carlos Montez Champalimaud | Sistemas e métodos para segmentação e processamento de imagens de tecidos e extração de características dos mesmos para tratar, diagnosticar ou prever condições médicas |
WO2012096988A2 (en) * | 2011-01-10 | 2012-07-19 | Rutgers, The State University Of New Jersey | Method and apparatus for shape based deformable segmentation of multiple overlapping objects |
US20130338016A1 (en) * | 2012-04-17 | 2013-12-19 | Vala Sciences, Inc. | Method For Integrated Pathology Diagnosis And Digital Biomarker Pattern Analysis |
-
2013
- 2013-03-07 US US14/395,583 patent/US9390313B2/en active Active
- 2013-03-07 WO PCT/JP2013/001449 patent/WO2013161155A1/ja active Application Filing
- 2013-03-07 JP JP2014512308A patent/JP5924406B2/ja active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09138854A (ja) * | 1995-11-15 | 1997-05-27 | Nec Corp | 画像の領域抽出方法及び装置 |
JP2004532410A (ja) * | 2001-04-20 | 2004-10-21 | イェール ユニバーシティ | 細胞および組織の自動分析のためのシステムおよび方法 |
JP2005530138A (ja) * | 2002-06-18 | 2005-10-06 | ライフスパン バイオサイエンス,インク. | 組織標本の中の重要な構造のコンピュータを利用した画像捕捉 |
JP2009508200A (ja) * | 2005-09-09 | 2009-02-26 | キネティック リミテッド | 画像領域の自動選定 |
JP2010281636A (ja) * | 2009-06-03 | 2010-12-16 | Nec Corp | 病理組織画像解析装置、病理組織画像解析方法、病理組織画像解析プログラム |
JP2011210156A (ja) * | 2010-03-30 | 2011-10-20 | Nec Corp | 画像処理装置、画像読取装置、画像処理方法及び画像処理プログラム |
WO2012011579A1 (ja) * | 2010-07-23 | 2012-01-26 | 独立行政法人産業技術総合研究所 | 病理組織画像の領域分割画像データ作成システム及び病理組織画像の特徴抽出システム |
WO2012043498A1 (ja) * | 2010-09-30 | 2012-04-05 | 日本電気株式会社 | 情報処理装置、情報処理システム、情報処理方法、プログラム及び記録媒体 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018512072A (ja) * | 2015-01-31 | 2018-05-10 | ベンタナ メディカル システムズ, インコーポレイテッド | 自動化スライド全域解析の品質管理 |
US11328420B2 (en) | 2015-01-31 | 2022-05-10 | Ventana Medical Systems, Inc. | Quality control of automated whole-slide analyses |
CN105654173A (zh) * | 2016-01-06 | 2016-06-08 | 大连海洋大学 | 工业螺母区域标定与个数检测方法 |
CN105654173B (zh) * | 2016-01-06 | 2018-04-17 | 大连海洋大学 | 工业螺母区域标定与个数检测方法 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2013161155A1 (ja) | 2015-12-21 |
JP5924406B2 (ja) | 2016-05-25 |
US9390313B2 (en) | 2016-07-12 |
US20150131854A1 (en) | 2015-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10395091B2 (en) | Image processing apparatus, image processing method, and storage medium identifying cell candidate area | |
JP6772066B2 (ja) | 画像を処理して解析するための検査装置 | |
EP3391283A1 (en) | Methods and systems for assessing cell morphology | |
JP5442542B2 (ja) | 病理診断支援装置、病理診断支援方法、病理診断支援のための制御プログラムおよび該制御プログラムを記録した記録媒体 | |
JP2009115599A (ja) | 評価システム、評価方法および評価プログラム | |
JP5995215B2 (ja) | 癌細胞領域抽出装置、方法、及びプログラム | |
WO2017221592A1 (ja) | 画像処理装置、画像処理方法及び画像処理プログラム | |
JP6168426B2 (ja) | 疾患分析装置、制御方法、及びプログラム | |
JP5771513B2 (ja) | 病理診断支援装置、病理診断支援方法、及び病理診断支援プログラム | |
US10591402B2 (en) | Image processing apparatus, image processing method, and image processing program | |
JPWO2017150194A1 (ja) | 画像処理装置、画像処理方法及びプログラム | |
JP2016514869A (ja) | スペクトル画像による生物試料の分析方法およびシステム | |
JP5789786B2 (ja) | 画像計測装置および画像計測方法 | |
JP7156361B2 (ja) | 画像処理方法、画像処理装置及びプログラム | |
JP5924406B2 (ja) | 画像計測装置、画像計測方法、および、画像計測用プログラム | |
JP2014134517A (ja) | 病理組織画像解析方法、病理組織画像解析装置及び病理組織画像解析プログラム | |
Tewary et al. | SmartIHC-Analyzer: smartphone assisted microscopic image analytics for automated Ki-67 quantification in breast cancer evaluation | |
CN111028219B (zh) | 一种结肠图像识别方法、装置以及相关设备 | |
Xu et al. | Segmentation of digitized histological sections for quantification of the muscularized vasculature in the mouse hind limb | |
US20210301246A1 (en) | Image processing device, image processing method, program, and evaluation method | |
Perdigão et al. | Okapi-EM: A napari plugin for processing and analyzing cryogenic serial focused ion beam/scanning electron microscopy images | |
JP6811874B2 (ja) | 画像作成装置、画像作成方法、画像作成プログラム | |
Perdigão et al. | Okapi-EM–a napari plugin for processing and analysing cryogenic serial FIB/SEM images | |
JPWO2013118436A1 (ja) | 生体画像解析システム、生体画像解析方法および生体画像解析プログラム | |
WO2021070371A1 (ja) | 細胞画像解析方法及び細胞解析装置 |
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: 13782209 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014512308 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14395583 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13782209 Country of ref document: EP Kind code of ref document: A1 |