WO2022201881A1 - スライド数推定装置、制御方法、及び非一時的なコンピュータ可読媒体 - Google Patents
スライド数推定装置、制御方法、及び非一時的なコンピュータ可読媒体 Download PDFInfo
- Publication number
- WO2022201881A1 WO2022201881A1 PCT/JP2022/003854 JP2022003854W WO2022201881A1 WO 2022201881 A1 WO2022201881 A1 WO 2022201881A1 JP 2022003854 W JP2022003854 W JP 2022003854W WO 2022201881 A1 WO2022201881 A1 WO 2022201881A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- slide
- specimen
- tumor cells
- interest
- region
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 50
- 210000004881 tumor cell Anatomy 0.000 claims abstract description 206
- 238000012360 testing method Methods 0.000 claims abstract description 29
- 239000000126 substance Substances 0.000 claims description 18
- 239000000463 material Substances 0.000 claims description 9
- 108090000623 proteins and genes Proteins 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 210000000056 organ Anatomy 0.000 claims description 7
- 210000004027 cell Anatomy 0.000 description 26
- 239000013076 target substance Substances 0.000 description 24
- 238000010586 diagram Methods 0.000 description 15
- 238000006243 chemical reaction Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 9
- 241001465754 Metazoa Species 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 206010028980 Neoplasm Diseases 0.000 description 3
- 239000012634 fragment Substances 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 210000003754 fetus Anatomy 0.000 description 2
- 230000007170 pathology Effects 0.000 description 2
- 239000013077 target material Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001605 fetal effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
Images
Classifications
-
- 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
- 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
- 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
- G06T2207/30242—Counting objects in image
Definitions
- This disclosure relates to techniques for testing using specimens collected from animals.
- Patent Literature 1 discloses a method of performing a genetic test on a fetus using blood of a pregnant woman containing cell fragments derived from the pregnant woman and cell fragments derived from the fetus.
- a method for determining the number of slides to be used for examination the distribution, expected value, variance, etc. of the number of fetal-derived cells that may be collected from the slide, and the cost of creating the slide are fixed costs or A method of determining by including variable costs is disclosed.
- Patent Document 1 discloses a test using blood. As such, US Pat. No. 6,330,000 does not mention how to determine the number of slides required for examination using tissue pieces such as tumor fragments.
- the present invention has been made in view of this problem, and its object is to provide a technique for improving the efficiency of examinations using animal tissue pieces.
- An apparatus for estimating the number of slides includes acquisition means for acquiring a slide image, which is an image of a specimen slide obtained from a tissue piece of a subject, and using the slide image, a tumor included in a region of interest of the specimen slide.
- acquisition means for acquiring a slide image which is an image of a specimen slide obtained from a tissue piece of a subject, and using the slide image, a tumor included in a region of interest of the specimen slide.
- first estimating means for estimating the number of cells second estimating means for estimating, based on the estimated number of tumor cells, the number of specimen slides to be obtained from the piece of tissue for performing a predetermined examination; have
- the control method of the present disclosure is executed by a computer.
- the control method includes an acquisition step of acquiring a slide image, which is an image of a specimen slide obtained from a tissue piece of a subject, and using the slide image to determine the number of tumor cells contained in a region of interest of the specimen slide. a first estimating step of estimating; and a second estimating step of estimating, based on the estimated number of tumor cells, the number of specimen slides to be obtained from the piece of tissue to perform a given examination.
- the computer-readable medium of the present disclosure stores a program that causes a computer to execute the control method of the present disclosure.
- FIG. 4 is a diagram illustrating an overview of the operation of the number-of-slides estimation device according to the first embodiment
- FIG. 2 is a block diagram illustrating the functional configuration of the number-of-slides estimation device of Embodiment 1
- FIG. 2 is a block diagram illustrating the hardware configuration of a computer that implements the number-of-slides estimation device
- FIG. 4 is a flowchart illustrating the flow of processing executed by the number-of-slides estimation device according to the first embodiment
- FIG. 4 is a diagram showing a first specific example of a tumor cell number estimation model
- FIG. 4 is a diagram showing a first specific example of training data used for learning a tumor cell number estimation model
- FIG. 10 is a diagram showing a second specific example of the tumor cell number estimation model
- FIG. 10 is a diagram showing a second specific example of training data used for learning the tumor cell number estimation model;
- predetermined values such as predetermined values and threshold values are stored in advance in a storage device or the like that can be accessed from a device that uses the values.
- FIG. 1 is a diagram illustrating an overview of the operation of the number-of-slides estimation device 2000 of the first embodiment.
- FIG. 1 is a diagram for facilitating an understanding of the outline of the number-of-slides estimation apparatus 2000, and the operation of the number-of-slides estimation apparatus 2000 is not limited to that shown in FIG.
- the tissue piece 10 is a part of the tissue (for example, part of a tumor in the body) collected by any method from the body of a person or other animal undergoing a predetermined examination.
- the predetermined examination will be referred to as a "target examination”
- a person who undergoes the target examination will be referred to as a "subject”.
- a tissue specimen slide (specimen slide 20) cut out from the tissue piece 10 is prepared, and the specimen slide 20 is used for examination.
- sample slides 20, namely sample slides 20-1 to 20-n are made from the piece of tissue 10.
- the piece of tissue 10 is preliminarily subjected to a treatment such as formalin fixation.
- a predetermined amount or more of a predetermined substance (hereinafter referred to as the target substance) contained in the subject's tumor cells is required. Therefore, a sufficient number of sample slides 20 are required to obtain a predetermined amount or more of the target substance.
- the target substance a predetermined substance contained in the subject's tumor cells. Therefore, a sufficient number of sample slides 20 are required to obtain a predetermined amount or more of the target substance.
- gene panel testing requires a sufficient number of specimen slides to secure the required amount of DNA.
- the number-of-slides estimation apparatus 2000 uses one or more slide images 30, which are images of specimen slides 20, to determine the number of specimen slides 20 to be obtained from the tissue piece 10 for the target examination (in other words, the required amount or more). Estimate the number of specimen slides 20 required to obtain the material of interest.
- the number of specimen slides 20 to be obtained from the tissue piece 10 for the target examination is also referred to as "required number of specimen slides 20".
- the slide image 30 is image data obtained by scanning the specimen slide 20 that has undergone predetermined staining by an arbitrary method.
- a specimen slide 20 scanned to obtain a certain slide image 30 is hereinafter referred to as a "specimen slide 20 corresponding to the slide image 30".
- a slide image 30 obtained by scanning a certain specimen slide 20 is called a "slide image 30 corresponding to the specimen slide 20".
- the slide image 30 may be an image of the entire specimen slide 20 or an image of a part of the specimen slide 20 .
- at least slide image 30 includes an image region representing region of interest 22 of specimen slide 20 .
- a slide image 30 is generated by applying a mark representing a region of interest 22 to a sample slide 20 by an arbitrary method and then scanning the region including the mark.
- the attention area 22 may be set after the slide image 30 is created. That is, a mark or the like representing the region of interest 22 may be applied to the slide image 30 obtained by scanning the specimen slide 20 using image processing software or the like.
- An image area representing the attention area 22 among the image areas in the slide image 30 is hereinafter referred to as an attention area image 32 .
- the entire slide image 30 becomes the attention area image 32 .
- the slide number estimation device 2000 estimates the number of tumor cells contained in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 by analyzing the slide image 30 . Then, the slide number estimation device 2000 estimates the required number of specimen slides 20 based on the estimated number of tumor cells.
- the slide image 30 obtained by scanning the specimen slide 20 is used to estimate the number of tumor cells contained in the region of interest 22 of the specimen slide 20. be. Then, based on the estimated number of tumor cells, the number of specimen slides 20 required for the subject examination is estimated. According to this method, it is not necessary to analyze the slide images 30 of all the specimen slides 20 obtained from the tissue piece 10. If the slide images 30 of some of the specimen slides 20 are analyzed, the specimens necessary for the target examination can be obtained. The number of slides 20 can be grasped. Therefore, the efficiency of inspection using the specimen slide 20 can be improved.
- the specimen slide 20 used for examination it may be difficult to grasp the number of tumor cells using the slide image 30 corresponding to the specimen slide 20 . While it is preferable to stain the specimen slide 20 appropriately in order to estimate the number of cells contained in the specimen slide 20 by image analysis, the specimen slide 20 thus stained is used for inspection. This is because it may not be suitable as a slide to be played.
- the slide number estimation apparatus 2000 it is sufficient to stain only a part of the specimen slides 20 obtained from the tissue piece 10, so that the specimen slides 20 to be used for examination can be secured without being stained. . Therefore, according to the slide number estimating apparatus 2000, it is possible to estimate the number of specimen slides 20 to be used for examination even for examinations in which it is difficult to use stained specimen slides 20.
- FIG. 1 it is sufficient to stain only a part of the specimen slides 20 obtained from the tissue piece 10, so that the specimen slides 20 to be used for examination can be secured without being stained. . Therefore, according to the slide number estimating apparatus 2000, it is possible to estimate the number of specimen slides 20 to be used for examination even for examinations in which it is difficult to use stained specimen slides 20.
- the number-of-slides estimation device 2000 of this embodiment will be described in more detail below.
- FIG. 2 is a block diagram illustrating the functional configuration of the number-of-slides estimation device 2000 according to the first embodiment.
- the number-of-slides estimation device 2000 has an acquisition unit 2020 , a first estimation unit 2040 and a second estimation unit 2060 .
- Acquisition unit 2020 acquires slide image 30 .
- a first estimation unit 2040 estimates the number of tumor cells contained in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 .
- the second estimation unit 2060 estimates the required number of specimen slides 20 based on the estimated number of tumor cells.
- Each functional component of the slide number estimation device 2000 may be realized by hardware (eg, hardwired electronic circuit, etc.) that implements each functional component, or may be realized by a combination of hardware and software (eg, : a combination of an electronic circuit and a program that controls it, etc.).
- hardware e.g, hardwired electronic circuit, etc.
- software e.g, : a combination of an electronic circuit and a program that controls it, etc.
- FIG. 3 is a block diagram illustrating the hardware configuration of the computer 500 that implements the number-of-slides estimation device 2000.
- Computer 500 is any computer.
- the computer 500 is a stationary computer such as a PC (Personal Computer) or a server machine.
- the computer 500 is a portable computer such as a smart phone or a tablet terminal.
- Computer 500 may be a dedicated computer designed to implement slide number estimation apparatus 2000, or may be a general-purpose computer.
- the functions of the number-of-slides estimation device 2000 are implemented on the computer 500.
- the application is composed of a program for realizing each functional component of the number-of-slides estimation device 2000 .
- the acquisition method of the above program is arbitrary.
- the program can be acquired from a storage medium (DVD disc, USB memory, etc.) in which the program is stored.
- the program can be obtained by downloading the program from a server device that manages the storage device in which the program is stored.
- Computer 500 has bus 502 , processor 504 , memory 506 , storage device 508 , input/output interface 510 and network interface 512 .
- the bus 502 is a data transmission path through which the processor 504, memory 506, storage device 508, input/output interface 510, and network interface 512 exchange data with each other.
- the method of connecting the processors 504 and the like to each other is not limited to bus connection.
- the processor 504 is various processors such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), or FPGA (Field-Programmable Gate Array).
- the memory 506 is a main memory implemented using a RAM (Random Access Memory) or the like.
- the storage device 508 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like.
- the input/output interface 510 is an interface for connecting the computer 500 and input/output devices.
- the input/output interface 510 is connected to an input device such as a keyboard and an output device such as a display device.
- a network interface 512 is an interface for connecting the computer 500 to a network.
- This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).
- the storage device 508 stores a program that implements each functional component of the slide number estimation device 2000 (a program that implements the application described above).
- the processor 504 reads this program into the memory 506 and executes it, thereby realizing each functional component of the slide number estimation apparatus 2000 .
- the number-of-slides estimation device 2000 may be realized by one computer 500 or may be realized by a plurality of computers 500. In the latter case, the configuration of each computer 500 need not be the same, and can be different.
- FIG. 4 is a flowchart illustrating the flow of processing executed by the number-of-slides estimation device 2000 of the first embodiment.
- the acquisition unit 2020 acquires the slide image 30 (S102).
- the first estimation unit 2040 estimates the number of tumor cells contained in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 (S104).
- the second estimation unit 2060 estimates the required number of specimen slides 20 based on the estimated number of tumor cells (S106).
- the acquisition unit 2020 acquires the slide image 30 (S102). There are various methods for the acquisition unit 2020 to acquire the slide image 30 .
- the acquisition unit 2020 acquires the slide images 30 stored in a storage device accessible from the slide number estimation device 2000 .
- a device that scans the specimen slide 20 to generate the slide image 30 (hereinafter referred to as a scanning device) stores the generated slide image 30 in a storage device.
- the acquiring unit 2020 acquires the slide images 30 desired by the user of the slide number estimation apparatus 2000 from among the slide images 30 stored in the storage device.
- the acquisition unit 2020 receives user input for selecting a desired slide image 30 from among the slide images 30 stored in the storage device, and acquires the slide image 30 selected by the user input.
- the acquiring unit 2020 may acquire the slide image 30 by receiving the slide image 30 transmitted from another device (for example, the scanning device described above).
- the first estimation unit 2040 analyzes the slide image 30 and estimates the number of tumor cells contained in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 (S104). For example, the first estimation unit 2040 detects cells from the region-of-interest image 32 in the slide image 30, and classifies the detected cells into tumor cells and normal cells. Then, the first estimation unit 2040 estimates the number of tumor cells by counting the number of cells classified as tumor cells.
- the first estimation unit 2040 is a model trained to detect cells from the attention area image 32 (hereinafter referred to as a cell detection model), and a model trained to classify the cell image into either tumor cells or normal cells. It has a model (hereinafter referred to as a cell type discrimination model).
- These models can be any kind of model, such as neural networks or SVMs (support vector machines).
- an existing technique can be used as a technique for learning a model so as to detect a predetermined type of object from an image.
- Existing techniques can also be used for the technique of learning a model so as to classify images of objects by object type.
- the first estimation unit 2040 inputs the slide image 30 to the cell detection model, an image of each cell included in the attention area image 32 is obtained from the cell detection model. In addition, by inputting each cell image obtained from the cell detection model to the cell type discrimination model, it is discriminated whether each cell is a tumor cell or a normal cell. The first estimation unit 2040 calculates the number of tumor cells by counting the number of cells determined to be tumor cells.
- the cell detection model and the cell type discrimination model instead of using two types of models, the cell detection model and the cell type discrimination model, one model that has been learned to detect tumor cells from the attention area image 32 may be used. Also, the estimation of the number of tumor cells may be performed without using a trained model.
- the second estimation unit 2060 estimates the required number of specimen slides 20 based on the number of tumor cells estimated by the first estimation unit 2040 (S106).
- the second estimation unit 2060 calculates the amount of the target substance contained in the tumor cells included in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 based on the number of tumor cells estimated by the first estimation unit 2040. to estimate In other words, the second estimation unit 2060 estimates the amount of the target substance contained in the tumor cells detected from the region-of-interest image 32 of the slide image 30 . Then, the second estimation unit 2060 estimates the required number of specimen slides 20 based on the estimated amount of the target substance and the amount of the target substance required for the target examination.
- the target substance is DNA.
- the second estimation unit 2060 estimates the amount of DNA obtained from the tumor cells from the number of tumor cells detected from the region-of-interest image 32 of the slide image 30 . Then, the second estimation unit 2060 estimates the required number of specimen slides 20 based on the estimated amount of DNA and the amount of DNA required for the target test.
- Non-Patent Document 1 describes the relationship between the number of tumor cells and the amount of DNA: "The yield of DNA obtained from one nucleated cell is estimated to be about 6 pg.” Therefore, based on this relationship, the number of tumor cells can be converted to DNA content.
- the method of converting the number of tumor cells into the amount of the target substance is not limited to the method using the relationship between the number of tumor cells and the amount of the target substance disclosed in the literature.
- an experiment may be conducted before operation of the slide number estimation apparatus 2000 to create a conversion formula for converting the number of tumor cells to the amount of the target substance.
- a model hereinafter referred to as , conversion model
- Any regression model can be used for this conversion model.
- the learning of the conversion model is performed using multiple sets of training data consisting of pairs of input data and correct data (output data to be output from the model in response to input of corresponding input data).
- Input data indicates the number of tumor cells contained in the region of interest 22 .
- Correct data indicates the amount of the target substance contained in the attention area 22 .
- the second estimating unit 2060 calculates the number of target substances contained in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 from the number of tumor cells estimated by the first estimating unit 2040 using the conversion formula and conversion model described above. Calculate the amount of Further, the second estimation unit 2060 calculates the required number of specimen slides 20 based on the relationship between the calculated amount of the target substance and the amount of the target substance required for the target examination. Here, information indicating the amount of the target substance required for the target examination is stored in advance in a storage unit accessible from the slide number estimation device 2000 .
- the second estimation unit 2060 calculates the required number of specimen slides 20 on the assumption that the same amount of target substance is obtained from the region of interest 22 in all the specimen slides 20 obtained from the tissue piece 10 .
- the required number of specimen slides 20 can be calculated, for example, by the following formula (1).
- M represents the required number of specimen slides 20 .
- y represents the amount of target substance required for the target inspection.
- Function f represents a conversion formula for converting the number of tumor cells into the amount of the target substance.
- x represents the number of tumor cells estimated by the first estimation unit 2040 .
- [] are Gaussian symbols. That is, [a] represents the smallest integer greater than or equal to a.
- the second estimation unit 2060 estimates the number of tumor cells contained in the region of interest 22 of another specimen slide 20 from the number of tumor cells estimated for the specimen slide 20 corresponding to the slide image 30. good too.
- the required number M of specimen slides 20 is, for example, the smallest integer k that satisfies the following equation (2).
- i represents an identification number assigned sequentially to each specimen slide obtained from tissue piece 10 .
- x_i represents the estimated number of tumor cells contained in the region of interest 22 of the specimen slide 20 with the identifier i (hereafter specimen slide 20-i). Note that the underscore in x_i represents a subscript.
- i 2 or more. This is because it is assumed that specimen slide 20-1 is stained to obtain slide image 30 and is not used for subject examination.
- the required number of specimen slides 20 may be estimated based on the number of tumor cells estimated for the specimen slide 20 corresponding to the slide image 30 and the number of tumor cells required for the target examination. For example, by converting the amount of the target substance required for the target test into the number of tumor cells, the number of tumor cells required for the target test is calculated in advance, and the value is stored in a memory accessible from the slide number estimation device 2000. Store it in the device. This conversion can be performed using, for example, the inverse function of the above conversion formula f(). In addition, in the learning of the conversion model described above, by reversing the relationship between the input data and the correct data, it is possible to generate a conversion model that converts the amount of the predetermined substance into the number of tumor cells.
- equations (1) and (2) can be replaced with equations (3) and (4), respectively.
- the second estimator 2060 calculates the number of tissue pieces 10 based on the number of tumor cells estimated for the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 . Estimate the number of tumor cells contained in the region of interest 22 of each other specimen slide 20 obtained from . For this estimation, for example, a trained tumor cell number estimation model is used. Arbitrary models such as neural networks and SVMs can be used as tumor cell number estimation models.
- the tumor cell number estimation model outputs output data according to input data.
- the input data includes one or more pairs of "slide image 30, estimated number of tumor cells for that slide image 30".
- the output data is the number of tumor cells estimated to be included in the region of interest 22 of each of the plurality of specimen slides 20 obtained from the tissue piece 10 from which the slide image 30 included in the input data was obtained. show.
- the input data includes a plurality of slide images 30, all of them are obtained from the same piece of tissue 10.
- n sample slides 20 are cut from the piece of tissue 10 .
- FIG. 5 is a diagram showing a first specific example of a model for estimating the number of tumor cells.
- the input data 42 input to the tumor cell number estimation model 40 of FIG. 5 includes a pair of "the number of tumor cells contained in the slide image 30 of the specimen slide 20-1 and the region of interest 22 of the specimen slide 20-1".
- the output data 44 output from the tumor cell number estimation model 40 of FIG. The estimated number of tumor cells contained in 22 is shown.
- the tumor cell number estimation model 40 in FIG. 5 is learned using a plurality of training data composed of pairs of input data and correct data.
- One piece of training data 50 is generated using one piece of tissue 10 .
- FIG. 6 is a diagram showing a first specific example of training data used for learning the tumor cell number estimation model 40.
- the input data 52 consists of a slide image of the sample slide 20-1 cut out from the tissue piece 10 and the number of tumor cells contained in the region of interest 22 of the sample slide 20-1.
- the correct data 54 indicates the number of tumor cells contained in the region of interest 22 of each of the specimen slides 20-2 to 20-n.
- FIG. 7 is a diagram showing a second specific example of the tumor cell number estimation model 40.
- the input data 42 input to the tumor cell number estimation model 40 of FIG. 7 includes two pairs of "slide image 30, tumor cell number".
- the output data 44 output from the tumor cell number estimation model 40 in FIG. The estimated number of tumor cells contained in 22 is shown.
- n-2 sample slides 20 are all the sample slide 20 corresponding to the first pair of slide images 30 of the input data 42 and the second pair of slide images 30 of the input data in the tissue piece 10.
- Specimen slide 20 obtained from the portion between the corresponding specimen slides 20.
- FIG. 8 is a diagram showing a second specific example of training data 50 used for learning the tumor cell number estimation model 40.
- the input data 52 is generated using the first and last specimen slides 20 out of n specimen slides 20 continuously cut from the piece of tissue 10 . That is, the first pair included in the input data 52 is composed of "the slide image of the sample slide 20-1 and the number of tumor cells included in the region of interest 22 of the sample slide 20-1".
- the second pair included in the input data 52 is composed of "the slide image of the sample slide 20-n and the number of tumor cells included in the region of interest 22 of the sample slide 20-n".
- the correct data 54 indicates the number of tumor cells contained in the region of interest 22 of each of the specimen slides 20-2 to 20-(n-1).
- n which is the number of specimen slides 20 cut out from the tissue piece 10
- input data 42 and input data 52 also include the number of specimen slides 20 to be cut from tissue piece 10 .
- the input data 42 and the input data 52 may further include additional information that is data other than the slide image 30 and the number of tumor cells.
- the additional information includes the shape of the region of interest 22 of the specimen slide 20 corresponding to the slide image 30, the size of the region of interest 22, the density of tumor cells in the region of interest 22, the distribution of tumor cells in the region of interest 22, and the tissue piece 10 collected. Any one or more of the method, the type of organ containing the piece of tissue 10, and the tissue type of tumor cells are shown.
- different tumor cell number estimation models 40 may be prepared for each value of the additional information. For example, assume that a different tumor cell number estimation model 40 is prepared for each method of collecting the tissue piece 10 . In this case, the second estimating unit 2060 identifies the tumor cell number estimating model 40 corresponding to the sampling method of the tissue piece 10 indicated by the additional information from among the plurality of tumor cell number estimating models 40, and estimates the tumor cell number. The remaining data included in the input data 42 are input to the model 40 .
- an estimation model for estimating the amount of target substance contained in the region of interest 22 of each specimen slide 20 may be used.
- the correct data 54 of the training data 50 indicate the amount of target material contained in the region of interest of each specimen slide 20 instead of the number of tumor cells contained in the region of interest of each specimen slide 20 .
- Input data 42 and input data 52 may indicate either the number of tumor cells or the amount of target material contained in the region of interest of specimen slide 20 .
- the method for estimating the number of tumor cells contained in each specimen slide 20 obtained from the tissue piece 10 is not limited to the method using the tumor cell number estimation model 40.
- a function representing the number of tumor cells contained in these regions of interest 22 may be determined in advance.
- the second estimating unit 2060 uses the function to calculate the number of tumor cells included in the region of interest 22 of the specimen slide 20 corresponding to the slide image 30 from the number of tumor cells in the region of interest 22 of each of the other specimen slides 20. Estimate the number of tumor cells involved.
- the second estimating unit 2060 uses the number of tumor cells estimated for one slide image 30 to estimate the number of tumor cells contained in the regions of interest 22 of the other n ⁇ 1 sample slides 20.
- the number of tumor cells contained in the region of interest 22 of the specimen slide 20-i can be calculated by the following formula (5). Equation (3) uses the number b of tumor cells estimated for the slide image 30 of the specimen slide 20-1 cut from one end of the tissue piece 10 to calculate the attention of each of the other n-1 specimen slides 20.
- num(i) represents the number of tumor cells contained in region of interest 22 of specimen slide 20-i.
- a is a non-zero real number representing the amount of increase in the number of tumor cells between adjacent specimen slides 20;
- b represents the number of tumor cells included in the region of interest 22 of the specimen slide 20-1 estimated by the first estimation unit 2040;
- the second estimation unit 2060 estimates the number of tumor cells contained in the regions of interest 22 of the other n-2 specimen slides 20 using the tumor cells estimated for each of the two slide images 30.
- the number of tumor cells contained in the region of interest 22 of the specimen slide 20-i can be calculated by the following formula (6). Equation (6) is calculated using the numbers b and c of tumor cells estimated for the slide image 30 of the sample slide 20-1 and the slide image 30 of the sample slide 20-n cut out from the tissue piece 10, respectively. It is a formula for estimating the number of tumor cells contained in the region of interest 22 of each of the n-2 sample slides 20 located in between.
- changes in the number of tumor cells are not limited to linear changes, and may be non-linear changes.
- a nonlinear template function is prepared, and by fitting the template function to the number of tumor cells estimated for one or more slide images 30, changes in the number of tumor cells are represented. Generate functions dynamically. Then, the second estimation unit 2060 uses this function to estimate the number of tumor cells contained in the regions of interest 22 of the specimen slides 20 other than the specimen slide 20 corresponding to the slide image 30 .
- the slide number estimation device 2000 outputs information indicating the required number of specimen slides 20 .
- This information is hereinafter referred to as output information.
- the output mode of the output information is arbitrary.
- the number-of-slides estimation device 2000 stores the output information in any storage device accessible from the number-of-slides estimation device 2000 .
- the number-of-slides estimation device 2000 causes a display device accessible from the number-of-slides estimation device 2000 to display the output information.
- the number-of-slides estimation device 2000 may transmit the output information to any device accessible from the number-of-slides estimation device 2000 .
- the output information may include information other than the required number of specimen slides 20.
- this information indicates which specimen slide 20 among the n specimen slides 20 cut out from the specimen slides 20 should be used for the target examination.
- the required number of specimen slides 20 is M
- the top M specimen slides 20 in descending order of the number of tumor cells are the specimen slides 20 to be used for the target examination. Therefore, for example, the output information includes information indicating the identifier of each of the M sample slides 20 .
- the slide number estimation apparatus 2000 may output a message indicating that the required amount of target substance cannot be obtained from the tissue piece 10 . For example, it is conceivable to output a message such as "We cannot obtain the required amount of DNA with the current sample alone" or "Additional samples are required".
- Non-transitory computer readable media include various types of tangible storage media.
- Examples of non-transitory computer-readable media include magnetic recording media (e.g., floppy disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical discs), CD-ROMs, CD-Rs, CD-Rs /W, including semiconductor memory (e.g. mask ROM, PROM (programmable ROM), EPROM (erasable PROM), flash ROM, RAM).
- the program may also be provided to the computer on various types of transitory computer readable medium. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can deliver the program to the computer via wired channels, such as wires and optical fibers, or wireless channels.
- (Appendix 1) Acquisition means for acquiring a slide image, which is an image of a specimen slide obtained from a piece of tissue of a subject; a first estimating means for estimating the number of tumor cells contained in the region of interest of the specimen slide using the slide image; second estimation means for estimating the number of specimen slides to be obtained from the piece of tissue for performing a predetermined examination based on the estimated number of tumor cells.
- the second estimation means is estimating the number of tumor cells contained in the region of interest for each of the plurality of specimen slides obtained from the tissue piece, other than the specimen slide from which the slide image was obtained; 2.
- a number-of-slides estimation apparatus wherein the number of specimen slides to be obtained from the piece of tissue is estimated based on the number of tumor cells estimated for the region of interest on each respective specimen slide.
- the acquiring means acquires the slide image of the first specimen slide and the slide image of the second specimen slide
- the first estimation means estimates the number of tumor cells contained in each of the region of interest of the first specimen slide and the region of interest of the second specimen slide
- the second estimation means estimates the number of tumor cells contained in the region of interest for each of the plurality of specimen slides obtained from the portion between the first specimen slide and the second specimen slide.
- the number-of-slides estimation device according to appendix 2.
- the second estimation means is In response to input of input data indicating the image of the specimen slide and the number of tumor cells contained in the region of interest of the specimen slide, the a model trained to output output data indicating the number of tumor cells contained in a region of interest for each of the specimen slides other than the specimen slide from which the slide image was acquired; Inputting the acquired slide image and the estimated number of tumor cells into the model, and using the output data obtained from the model in response to the input, the specimen slide to be obtained from the tissue piece. 4.
- the number-of-slides estimation device according to appendix 2 or 3, which estimates a number.
- the input data includes the shape of the region of interest, the size of the region of interest, the density of tumor cells in the region of interest, the distribution of tumor cells in the region of interest, the method for collecting the tissue piece, and the size of the organ containing the tissue piece. 5.
- the second estimation means is estimating the amount of a predetermined substance contained in the region of interest from the estimated number of tumor cells; 6. Predicting the number of specimen slides to be obtained from the piece of tissue based on the estimated amount of the predetermined material and the amount of the predetermined material required for the predetermined test.
- the number-of-slides estimating device is a gene panel test, 6.
- the number-of-slides estimation device is DNA.
- a control method implemented by a computer comprising: an acquiring step of acquiring a slide image, which is an image of a specimen slide obtained from a piece of tissue from a subject; a first estimation step of estimating the number of tumor cells contained in the region of interest of the specimen slide using the slide image; a second estimation step of estimating, based on said estimated number of tumor cells, the number of said specimen slides to be obtained from said piece of tissue for performing a given examination.
- the input data includes the shape of the region of interest, the size of the region of interest, the density of tumor cells in the region of interest, the distribution of tumor cells in the region of interest, the method for collecting the tissue piece, and the size of the organ containing the tissue piece. 12.
- Appendix 13 In the second estimation step, estimating the amount of a predetermined substance contained in the region of interest from the estimated number of tumor cells; 13. Estimate the number of specimen slides to be obtained from the piece of tissue based on the estimated amount of the predetermined material and the amount of the predetermined material required for the predetermined test.
- the control method described in . (Appendix 14)
- the predetermined test is a gene panel test, 14.
- a slide image which is an image of a specimen slide obtained from a piece of tissue from a subject
- a first estimation step of estimating the number of tumor cells contained in the region of interest of the specimen slide using the slide image a second estimation step of estimating, based on the estimated number of tumor cells, the number of specimen slides to be obtained from the tissue piece for performing a predetermined examination
- computer readable medium Appendix 16
- (Appendix 17) in the obtaining step obtaining the slide image of the first specimen slide and the slide image of the second specimen slide; estimating the number of tumor cells contained in each of the region of interest of the first specimen slide and the region of interest of the second specimen slide in the first estimation step;
- the second estimation step for each of the plurality of specimen slides obtained from the portion between the first specimen slide and the second specimen slide, estimating the number of tumor cells contained in the region of interest; 17.
- the program generates a plurality of specimen slides obtained from the tissue piece in response to input of input data indicating the image of the specimen slide and the number of tumor cells contained in the region of interest of the specimen slide. Among them, for each of the specimen slides other than the specimen slide from which the slide image was acquired, a model trained to output output data indicating the number of tumor cells contained in the region of interest, In the second estimation step, the obtained slide image and the estimated number of tumor cells are input to the model, and the output data obtained from the model according to the input are used to determine the tissue 18.
- the input data includes the shape of the region of interest, the size of the region of interest, the density of tumor cells in the region of interest, the distribution of tumor cells in the region of interest, the method for collecting the tissue piece, and the size of the organ containing the tissue piece. 19.
- (Appendix 20) In the second estimation step, estimating the amount of a predetermined substance contained in the region of interest from the estimated number of tumor cells; Clause 15-19, estimating the number of specimen slides to be obtained from the piece of tissue based on the estimated amount of the predetermined material and the amount of the predetermined material required for the predetermined test.
- the predetermined test is a gene panel test, 21.
- the computer-readable medium of Clause 20, wherein said predetermined substance is DNA.
- tissue piece 20 specimen slide 22 region of interest 30 slide image 32 region of interest image 40 tumor cell number estimation model 42 input data 44 output data 50 training data 52 input data 54 correct data 500 computer 502 bus 504 processor 506 memory 508 storage device 510 input Output interface 512 Network interface 2000 Slide number estimation device 2020 Acquisition unit 2040 First estimation unit 2060 Second estimation unit
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Urology & Nephrology (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Molecular Biology (AREA)
- Hematology (AREA)
- Biomedical Technology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
Description
本実施形態のスライド数推定装置2000によれば、標本スライド20をスキャンすることで得られたスライド画像30を利用して、その標本スライド20の注目領域22に含まれる腫瘍細胞の数が推定される。そして、推定された腫瘍細胞の数に基づいて、対象検査に必要な標本スライド20の数が推定される。この方法によれば、組織片10から得られる全ての標本スライド20についてスライド画像30を解析する必要はなく、一部の標本スライド20についてスライド画像30の解析を行えば、対象検査に必要な標本スライド20の数を把握することができる。そのため、標本スライド20を利用する検査の効率を向上させることができる。
図2は、実施形態1のスライド数推定装置2000の機能構成を例示するブロック図である。スライド数推定装置2000は、取得部2020、第1推定部2040、及び第2推定部2060を有する。取得部2020は、スライド画像30を取得する。第1推定部2040は、スライド画像30に対応する標本スライド20の注目領域22に含まれる腫瘍細胞の数を推定する。第2推定部2060は、推定した腫瘍細胞の数に基づいて、標本スライド20の必要数を推定する。
スライド数推定装置2000の各機能構成部は、各機能構成部を実現するハードウエア(例:ハードワイヤードされた電子回路など)で実現されてもよいし、ハードウエアとソフトウエアとの組み合わせ(例:電子回路とそれを制御するプログラムの組み合わせなど)で実現されてもよい。以下、スライド数推定装置2000の各機能構成部がハードウエアとソフトウエアとの組み合わせで実現される場合について、さらに説明する。
図4は、実施形態1のスライド数推定装置2000によって実行される処理の流れを例示するフローチャートである。取得部2020は、スライド画像30を取得する(S102)。第1推定部2040は、スライド画像30に対応する標本スライド20の注目領域22に含まれる腫瘍細胞の数を推定する(S104)。第2推定部2060は、推定された腫瘍細胞の数に基づいて、標本スライド20の必要数を推定する(S106)。
取得部2020はスライド画像30を取得する(S102)。取得部2020がスライド画像30を取得する方法は様々である。例えば取得部2020は、スライド数推定装置2000からアクセス可能な記憶装置に格納されているスライド画像30を取得する。例えば、標本スライド20をスキャンしてスライド画像30を生成する装置(以下、スキャン装置)が、生成したスライド画像30を記憶装置に格納するようにする。取得部2020は、当該記憶装置に格納されているスライド画像30の中から、スライド数推定装置2000のユーザが所望するスライド画像30を取得する。例えば取得部2020は、記憶装置に格納されているスライド画像30の中から所望のものを選択するユーザ入力を受け付け、当該ユーザ入力によって選択されたスライド画像30を取得する。その他にも例えば、取得部2020は、他の装置(例えば前述したスキャン装置)から送信されるスライド画像30を受信することで、スライド画像30を取得してもよい。
第1推定部2040は、スライド画像30を解析して、スライド画像30に対応する標本スライド20の注目領域22に含まれる腫瘍細胞の数を推定する(S104)。例えば第1推定部2040は、スライド画像30内の注目領域画像32から細胞を検出し、検出した各細胞を腫瘍細胞と正常細胞に分類する。そして、第1推定部2040は、腫瘍細胞に分類された細胞の数をカウントすることで、腫瘍細胞の数を推定する。
第2推定部2060は、第1推定部2040によって推定された腫瘍細胞数に基づいて、標本スライド20の必要数を推定する(S106)。ここで、対象検査では、被検者の腫瘍細胞に含まれる対象物質を所定量以上得る必要がある。そこで第2推定部2060は、第1推定部2040によって推定された腫瘍細胞の数に基づいて、スライド画像30に対応する標本スライド20の注目領域22に含まれる腫瘍細胞に含まれる対象物質の量を推定する。言い換えれば、第2推定部2060は、スライド画像30の注目領域画像32から検出された腫瘍細胞に含まれる対象物質の量を推定する。そして、第2推定部2060は、推定した対象物質の量と、対象検査に必要な対象物質の量とに基づいて、標本スライド20の必要数を推定する。
スライド数推定装置2000は、標本スライド20の必要数を示す情報を出力する。以下、この情報を出力情報と呼ぶ。出力情報の出力態様は任意である。例えばスライド数推定装置2000は、スライド数推定装置2000からアクセス可能な任意の記憶装置に、出力情報を格納する。その他にも例えば、スライド数推定装置2000は、スライド数推定装置2000からアクセス可能なディスプレイ装置に、出力情報を表示させる。その他にも例えば、スライド数推定装置2000は、スライド数推定装置2000からアクセス可能な任意の装置に対して、出力情報を送信してもよい。
(付記1)
被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得手段と、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定手段と、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定手段と、を有するスライド数推定装置。
(付記2)
前記第2推定手段は、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、付記1に記載のスライド数推定装置。
(付記3)
前記取得手段は、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定手段は、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定手段は、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、付記2に記載のスライド数推定装置。
(付記4)
前記第2推定手段は、
前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを有し、
前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、付記2又は3に記載のスライド数推定装置。
(付記5)
前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、付記4に記載のスライド数推定装置。
(付記6)
前記第2推定手段は、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、付記1から5いずれか一項に記載のスライド数推定装置。
(付記7)
前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、付記6に記載のスライド数推定装置。
(付記8)
コンピュータによって実行される制御方法であって、
被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得ステップと、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定ステップと、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定ステップと、を有する制御方法。
(付記9)
前記第2推定ステップにおいて、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、付記8に記載の制御方法。
(付記10)
前記取得ステップにおいて、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定ステップにおいて、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定ステップにおいて、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、付記9に記載の制御方法。
(付記11)
前記コンピュータは、前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを有し、
前記第2推定ステップにおいて、前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、付記9又は10に記載の制御方法。
(付記12)
前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、付記11に記載の制御方法。
(付記13)
前記第2推定ステップにおいて、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、付記8から12いずれか一項に記載の制御方法。
(付記14)
前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、付記13に記載の制御方法。
(付記15)
コンピュータに、
被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得ステップと、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定ステップと、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定ステップと、を実行させるプログラムが格納されている非一時的なコンピュータ可読媒体。
(付記16)
前記第2推定ステップにおいて、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、付記15に記載のコンピュータ可読媒体。
(付記17)
前記取得ステップにおいて、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定ステップにおいて、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定ステップにおいて、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、付記16に記載のコンピュータ可読媒体。
(付記18)
前記プログラムは、前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを含み、
前記第2推定ステップにおいて、前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、付記16又は17に記載のコンピュータ可読媒体。
(付記19)
前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、付記18に記載のコンピュータ可読媒体。
(付記20)
前記第2推定ステップにおいて、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、付記15から19いずれか一項に記載のコンピュータ可読媒体。
(付記21)
前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、付記20に記載のコンピュータ可読媒体。
20 標本スライド
22 注目領域
30 スライド画像
32 注目領域画像
40 腫瘍細胞数推定モデル
42 入力データ
44 出力データ
50 訓練データ
52 入力データ
54 正解データ
500 コンピュータ
502 バス
504 プロセッサ
506 メモリ
508 ストレージデバイス
510 入出力インタフェース
512 ネットワークインタフェース
2000 スライド数推定装置
2020 取得部
2040 第1推定部
2060 第2推定部
Claims (21)
- 被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得手段と、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定手段と、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定手段と、を有するスライド数推定装置。 - 前記第2推定手段は、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、請求項1に記載のスライド数推定装置。 - 前記取得手段は、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定手段は、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定手段は、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、請求項2に記載のスライド数推定装置。 - 前記第2推定手段は、
前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを有し、
前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、請求項2又は3に記載のスライド数推定装置。 - 前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、請求項4に記載のスライド数推定装置。
- 前記第2推定手段は、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、請求項1から5いずれか一項に記載のスライド数推定装置。 - 前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、請求項6に記載のスライド数推定装置。 - コンピュータによって実行される制御方法であって、
被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得ステップと、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定ステップと、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定ステップと、を有する制御方法。 - 前記第2推定ステップにおいて、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、請求項8に記載の制御方法。 - 前記取得ステップにおいて、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定ステップにおいて、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定ステップにおいて、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、請求項9に記載の制御方法。 - 前記コンピュータは、前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを有し、
前記第2推定ステップにおいて、前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、請求項9又は10に記載の制御方法。 - 前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、請求項11に記載の制御方法。
- 前記第2推定ステップにおいて、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、請求項8から12いずれか一項に記載の制御方法。 - 前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、請求項13に記載の制御方法。 - コンピュータに、
被検者の組織片から得た標本スライドの画像であるスライド画像を取得する取得ステップと、
前記スライド画像を用いて、前記標本スライドの注目領域に含まれる腫瘍細胞の数を推定する第1推定ステップと、
前記推定された腫瘍細胞の数に基づき、所定の検査を行うために前記組織片から得るべき前記標本スライドの数を推定する第2推定ステップと、を実行させるプログラムが格納されている非一時的なコンピュータ可読媒体。 - 前記第2推定ステップにおいて、
前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定し、
各前記標本スライドそれぞれの前記注目領域について推定された腫瘍細胞の数に基づいて、前記組織片から得るべき前記標本スライドの数を推定する、請求項15に記載のコンピュータ可読媒体。 - 前記取得ステップにおいて、第1の前記標本スライドの前記スライド画像と、第2の前記標本スライドの前記スライド画像とを取得し、
前記第1推定ステップにおいて、第1の前記標本スライドの前記注目領域と第2の前記標本スライドの前記注目領域それぞれについて、その中に含まれる腫瘍細胞の数を推定し、
前記第2推定ステップにおいて、第1の前記標本スライドと第2の前記標本スライドとの間の部分から得られる複数の前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を推定する、請求項16に記載のコンピュータ可読媒体。 - 前記プログラムは、前記標本スライドの画像と、その標本スライドの前記注目領域に含まれる腫瘍細胞の数とを示す入力データが入力されたことに応じて、前記組織片から得られる複数の前記標本スライドのうち、前記スライド画像が取得された前記標本スライド以外の各前記標本スライドそれぞれについて、その注目領域に含まれる腫瘍細胞の数を示す出力データを出力するように学習されたモデルを含み、
前記第2推定ステップにおいて、前記取得されたスライド画像と、前記推定された腫瘍細胞の数とを前記モデルに入力し、その入力に応じて前記モデルから得られる前記出力データを用いて、前記組織片から得るべき標本スライドの数を推定する、請求項16又は17に記載のコンピュータ可読媒体。 - 前記入力データは、前記注目領域の形状、前記注目領域のサイズ、前記注目領域における腫瘍細胞の密度、前記注目領域における腫瘍細胞の分布、前記組織片を採取した方法、前記組織片を含む臓器の種類、及び前記腫瘍細胞の組織型のいずれか1つ以上を表す情報をさらに含む、請求項18に記載のコンピュータ可読媒体。
- 前記第2推定ステップにおいて、
前記推定された腫瘍細胞の数から、前記注目領域に含まれる所定の物質の量を推定し、
前記推定された所定の物質の量と、前記所定の検査に必要な前記所定の物質の量とに基づき、前記組織片から得るべき標本スライドの数を推定する、請求項15から19いずれか一項に記載のコンピュータ可読媒体。 - 前記所定の検査は遺伝子パネル検査であり、
前記所定の物質は DNA である、請求項20に記載のコンピュータ可読媒体。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/283,698 US20240161280A1 (en) | 2021-03-25 | 2022-02-01 | Slide number estimation apparatus, control method, and non-transitory computer readable medium |
JP2023508737A JPWO2022201881A5 (ja) | 2022-02-01 | スライド数推定装置、制御方法、及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021-051351 | 2021-03-25 | ||
JP2021051351 | 2021-03-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022201881A1 true WO2022201881A1 (ja) | 2022-09-29 |
Family
ID=83396817
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/003854 WO2022201881A1 (ja) | 2021-03-25 | 2022-02-01 | スライド数推定装置、制御方法、及び非一時的なコンピュータ可読媒体 |
Country Status (2)
Country | Link |
---|---|
US (1) | US20240161280A1 (ja) |
WO (1) | WO2022201881A1 (ja) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006523100A (ja) * | 2003-04-03 | 2006-10-12 | モナリザ メディカル, リミテッド | 経子宮頸細胞を使用する非侵襲的出生前遺伝子診断 |
JP2013246187A (ja) * | 2012-05-23 | 2013-12-09 | Olympus Corp | 顕微鏡システム、標本画像生成方法及びプログラム |
JP2015125098A (ja) * | 2013-12-27 | 2015-07-06 | 富士ゼロックス株式会社 | 画像処理装置及びプログラム |
JP2015123047A (ja) * | 2013-12-27 | 2015-07-06 | 富士ゼロックス株式会社 | 画像処理装置及びプログラム |
JP2016049078A (ja) * | 2014-09-02 | 2016-04-11 | 富士フイルム株式会社 | 細胞片抽出個数の決定方法及び装置、並びに生物情報解析方法 |
JP2017212938A (ja) * | 2016-05-31 | 2017-12-07 | 富士フイルム株式会社 | 生物情報解析方法および生物情報解析システム |
JP2017212937A (ja) * | 2016-05-31 | 2017-12-07 | 富士フイルム株式会社 | 生物情報解析方法および生物情報解析方法システム |
-
2022
- 2022-02-01 US US18/283,698 patent/US20240161280A1/en active Pending
- 2022-02-01 WO PCT/JP2022/003854 patent/WO2022201881A1/ja active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006523100A (ja) * | 2003-04-03 | 2006-10-12 | モナリザ メディカル, リミテッド | 経子宮頸細胞を使用する非侵襲的出生前遺伝子診断 |
JP2013246187A (ja) * | 2012-05-23 | 2013-12-09 | Olympus Corp | 顕微鏡システム、標本画像生成方法及びプログラム |
JP2015125098A (ja) * | 2013-12-27 | 2015-07-06 | 富士ゼロックス株式会社 | 画像処理装置及びプログラム |
JP2015123047A (ja) * | 2013-12-27 | 2015-07-06 | 富士ゼロックス株式会社 | 画像処理装置及びプログラム |
JP2016049078A (ja) * | 2014-09-02 | 2016-04-11 | 富士フイルム株式会社 | 細胞片抽出個数の決定方法及び装置、並びに生物情報解析方法 |
JP2017212938A (ja) * | 2016-05-31 | 2017-12-07 | 富士フイルム株式会社 | 生物情報解析方法および生物情報解析システム |
JP2017212937A (ja) * | 2016-05-31 | 2017-12-07 | 富士フイルム株式会社 | 生物情報解析方法および生物情報解析方法システム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022201881A1 (ja) | 2022-09-29 |
US20240161280A1 (en) | 2024-05-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2004174254A5 (ja) | ||
CN107567631B (zh) | 组织样品分析技术 | |
CN112634987B (zh) | 一种单样本肿瘤dna拷贝数变异检测的方法和装置 | |
JP2013201909A (ja) | 細胞画像判定装置、方法、並びにプログラム | |
JP2007122418A (ja) | 予測方法、予測装置および予測プログラム | |
Gofer et al. | Machine learning algorithms for classification of first‐trimester fetal brain ultrasound images | |
WO2022201881A1 (ja) | スライド数推定装置、制御方法、及び非一時的なコンピュータ可読媒体 | |
CN110930402A (zh) | 一种基于子宫内膜癌的dki序列mk图的影像组学特征处理方法 | |
Padmanaban et al. | Between-tumor and within-tumor heterogeneity in invasive potential | |
WO2008007630A1 (fr) | Méthode et appareil de recherche de protéine | |
CN107391962A (zh) | 基于多组学分析基因或位点对疾病调控关系的方法 | |
US20230215571A1 (en) | Automated classification of immunophenotypes represented in flow cytometry data | |
EP4207059A1 (en) | Method and apparatus for tumor purity based on pathological slide image | |
KR101771042B1 (ko) | 질병 관련 유전자 탐색 장치 및 그 방법 | |
AU2022218581B2 (en) | Sequencing data-based itd mutation ratio detecting apparatus and method | |
CN113990492B (zh) | 确定关于实体瘤微小残留病灶的检测参数的方法、设备和存储介质 | |
Yang et al. | Keeping continuous diagnostic data continuous: Application of Bayesian latent class models in veterinary research | |
Bogomolovas et al. | Automated quantification and statistical assessment of proliferating cardiomyocyte rates in embryonic hearts | |
Sai et al. | SAI: fast and automated quantification of stomatal parameters on microscope images | |
Dávalos et al. | A coalescent-based estimator of genetic drift, and acoustic divergence in the Pteronotus parnellii species complex | |
WO2016068625A1 (ko) | Nmf를 이용한 타겟 염기 서열 분석에서의 바이어스 제거 방법 | |
JPWO2002048915A1 (ja) | 遺伝子間の関連を検出する方法 | |
Zhang et al. | Exon prediction based on multiscale products of a genomic-inspired multiscale bilateral filtering | |
KR102671745B1 (ko) | 병리 슬라이드 이미지의 품질을 평가하는 방법 및 장치 | |
EP4283623A1 (en) | Method and device for evaluating quality of pathological slide image |
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: 22774683 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023508737 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18283698 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: 22774683 Country of ref document: EP Kind code of ref document: A1 |