Information processing device, operation method for information processing device, and operation program for information processing device

Abstract

Provided is an information processing device comprising a processor, the processor comparing a plurality of items of causality information that indicate causality of a plurality of events representing a change in an organism, and a generated event that represents a change generated in a subject organism to which a drug candidate was administered, extracting corresponding causality information including an event that corresponds to the generated event from among the plurality of items of causality information, and performing control for outputting the corresponding causality information.

Description

Information processing device, operating method for information processing device, and operating program for information processing device

[0001] The technology of the present disclosure relates to an information processing device, an operating method for an information processing device, and an operating program for an information processing device.

[0002] Japanese Patent No. 6407242 describes a system that quantitatively calculates the magnitude of changes that occur in a living organism due to a candidate drug substance (referred to as a "therapeutic compound" in Japanese Patent No. 6407242) based on causal relationship information (referred to as a "network model" in Japanese Patent No. 6407242) that indicates the causal relationships between multiple events that represent changes in the living organism.

[0003] Conventionally, evaluation of candidate pharmaceutical substances has been performed as follows: First, the candidate substance is administered to a subject, such as a rat. Then, a pathologist identifies changes that occur in the subject after administration of the candidate substance. Finally, based on the identified changes, the pathologist estimates the mechanism of action by which the candidate substance manifests its medicinal effect or toxicity. Changes that occur in the subject after administration of the candidate substance include, for example, morphological abnormalities such as inflammation and canceration that occur in the subject's organs. The pathologist identifies morphological abnormalities by observing specimen images of tissue specimens of the subject's organs.

[0004] With recent advances in image analysis technology, the identification of morphological abnormalities using specimen images is now being automated using computer processing. However, the current situation is that the estimation of the mechanism of action still relies entirely on pathologists.

[0005] One embodiment of the technology disclosed herein provides an information processing device, an operating method for the information processing device, and an operating program for the information processing device that can reduce the burden on pathologists and efficiently evaluate candidate pharmaceutical substances.

[0006] The information processing device of the present disclosure includes a processor, which compares a plurality of pieces of causal relationship information indicating the causal relationships between a plurality of events that represent changes in a living organism with an occurrence event that represents a change that has occurred in a subject, which is a living organism to which a candidate pharmaceutical substance has been administered, extracts corresponding causal relationship information that includes an event that corresponds to the occurrence event from the plurality of pieces of causal relationship information, and controls the output of the corresponding causal relationship information.

[0007] The causal relationship information is preferably information indicating the causal relationships between a plurality of events that represent changes in the living body due to the toxicity of past drug candidate substances.

[0008] Preferably, the developmental event represents a morphological abnormality that occurs in an organ of a subject following administration of a candidate substance.

[0009] The processor preferably identifies the type of morphological abnormality by performing image analysis on a specimen image showing a tissue specimen of an organ of the subject.

[0010] Preferably, the processor identifies multiple types of morphological abnormalities for a single specimen image.

[0011] In the image analysis, the processor preferably uses a machine learning model that outputs whether or not a morphological abnormality has occurred in response to an input of a specimen image.

[0012] When a plurality of pieces of corresponding causal relationship information are extracted, the processor preferably derives the reliability of each of the plurality of pieces of corresponding causal relationship information and performs control to output the corresponding causal relationship information based on the reliability.

[0013] It is preferable that the reliability of corresponding causal relationship information is higher when the number of events corresponding to the occurring event is larger.

[0014] The occurrence event represents a morphological abnormality that occurs in the subject's organ after administration of a candidate substance, and the processor preferably identifies the type of morphological abnormality using a machine learning model that outputs whether or not a morphological abnormality has occurred in response to an input of a specimen image of a tissue specimen of the subject's organ, and derives reliability based on the predicted probability of whether or not the morphological abnormality has occurred using the machine learning model.

[0015] It is preferable that the processor extracts multiple pieces of corresponding causal relationship information, and if a common event exists in at least two of the extracted multiple pieces of corresponding causal relationship information, control is performed to integrate the corresponding causal relationship information in which a common event exists and then output it.

[0016] It is preferable that causal relationship information is prepared for each of multiple organs, and the processor controls the corresponding causal relationship information for different organs where common events exist to be integrated and output.

[0017] Preferably, the incident event represents at least one of a change in the subject's weight, a change in the subject's food intake, and a change in the subject's clinical chemistry test results.

[0018] The causal relationship information includes events relating to changes in molecules of a living body, and when the processor controls the output of the corresponding causal relationship information, it is preferable that the processor distinguishes events relating to changes in molecules of a living body from other events.

[0019] The method of operating the information processing device disclosed herein includes comparing multiple pieces of causal relationship information indicating the causal relationships between multiple events that represent changes in a living organism with an occurring event that represents a change that has occurred in a subject, which is a living organism to which a candidate pharmaceutical substance has been administered; extracting corresponding causal relationship information that includes an event that corresponds to the occurring event from the multiple pieces of causal relationship information; and controlling the output of the corresponding causal relationship information.

[0020] The operating program of the information processing device disclosed herein causes a computer to perform processes including: comparing multiple pieces of causal relationship information indicating the causal relationships between multiple events that represent changes in a living organism with an occurring event that represents a change that has occurred in a subject, which is a living organism to which a candidate pharmaceutical substance has been administered; extracting corresponding causal relationship information that includes an event that corresponds to the occurring event from the multiple pieces of causal relationship information; and controlling the output of the corresponding causal relationship information.

[0021] According to the technology of the present disclosure, it is possible to provide an information processing device, an operating method for an information processing device, and an operating program for an information processing device that can reduce the burden on pathologists and efficiently evaluate candidate pharmaceutical substances.

[0022] 1 is a diagram illustrating steps of an evaluation test, specimen images, and an information processing device. FIG. 1 is a block diagram illustrating a computer constituting an information processing device. FIG. 2 is a block diagram illustrating a processing unit of a CPU of the information processing device. FIG. 2 is a diagram illustrating a morphological abnormality identification model. FIG. 3 is a diagram illustrating patch images obtained by subdividing a target specimen image in which a liver specimen is captured. FIG. 4 is a diagram illustrating patch images obtained by subdividing a target specimen image in which a pancreatic specimen is captured. FIG. 5 is a diagram illustrating a hyperplasia identification model. FIG. 6 is a diagram illustrating a process in which an aggregated identification result is generated by outputting identification results from each identification model in response to input of a patch image and aggregating the identification results. FIG. 7 is a diagram illustrating a process in which occurrence event information is generated by further aggregating the aggregated identification results of each patch image. FIG. 8 is a diagram illustrating causal relationship information. FIG. 9 is a diagram illustrating first liver causal relationship information. FIG. 10 is a diagram illustrating first pancreas causal relationship information. FIG. 11 is a diagram illustrating processing by a matching and extraction unit. FIG. 12 is a diagram illustrating processing by a matching and extraction unit. FIG. 13 is a diagram illustrating a target specification screen. FIG. 14 is a diagram illustrating an analysis result display screen. FIG. 15 is a flowchart illustrating processing procedures of an information processing device. FIG. 16 is a table illustrating the number and reliability of events corresponding to morphological abnormalities. FIG. 17 is a diagram illustrating an aspect in which a plurality of liver causal relationship information extracted as corresponding causal relationship information are displayed in descending order of reliability. 22。FIG. 23 is a diagram showing an aspect of displaying liver causal relationship information with a reliability equal to or higher than a set value in descending order of reliability from among a plurality of pieces of liver causal relationship information extracted as corresponding causal relationship information. FIG. 24 is a table showing the average value and reliability of the predicted probability of morphological abnormality corresponding to an event. FIG. 25 is a diagram showing first liver causal relationship information and first pancreas causal relationship information in which a common event exists. FIG. 26 is a diagram showing integrated causal relationship information in which the first liver causal relationship information and the first pancreas causal relationship information shown in FIG. 22 are integrated in a common event. FIG. 27 is a diagram showing an analysis result display screen in which integrated causal relationship information is displayed. FIG. 28 is a diagram showing event information including changes in the subject's weight, changes in the subject's food intake, and changes in the results of clinical chemical tests on the subject. FIG. 29 is a diagram showing an aspect of handling specimen images obtained by photographing a slide specimen on which tissue specimens of multiple types of organs are placed.

[0023] 1 , an information processing device 10 according to the present disclosure is used to evaluate the efficacy and toxicity of a drug candidate substance 11. The information processing device 10 is, for example, a desktop personal computer, and includes a display 12 that displays various screens, and an input device 13 such as a keyboard, a mouse, a touch panel, and / or a microphone for voice input. The information processing device 10 is installed, for example, in a drug development facility, and is operated by a pathologist PT involved in drug development at the drug development facility.

[0024] A specimen image 15 is input to the information processing device 10. The specimen image 15 is an image used to evaluate the efficacy and toxicity of the candidate substance 11. The specimen image 15 is generated, for example, by the following procedure. First, a living subject S, such as a rat, prepared for evaluation of the candidate substance 11 is autopsied, and tissue specimens of the subject S's organs are collected. Here, a tissue specimen of a cross section of the liver LV (hereinafter referred to as the liver specimen) LVS and a tissue specimen of a cross section of the pancreas PC (hereinafter referred to as the pancreatic specimen) PCS are collected. Next, the collected liver specimen LVS and pancreatic specimen PCS are attached to a glass slide 16, and then stained, in this case with hematoxylin and eosin. Next, the stained liver specimen LVS and pancreatic specimen PCS are covered with a cover glass 17 to complete a slide specimen 18. The slide specimen 18 is then placed in an imaging device 19, such as a digital optical microscope, and the specimen image 15 is captured by the imaging device 19. The specimen image 15 thus obtained is assigned a specimen ID (Identification Data) for uniquely identifying the specimen S, a specimen image ID for uniquely identifying the specimen image 15, and the photographing date and time.

[0025] In the following description, the specimen image 15 in which the liver specimen LVS is captured will be referred to as specimen image 15L, and the specimen image 15 in which the pancreatic specimen PCS is captured will be referred to as specimen image 15P. When there is no need to particularly distinguish between these specimen images 15L and 15P, they will be collectively referred to as specimen image 15.

[0026] In FIG. 1 , one liver specimen LVS and one pancreatic specimen PCS are collected, and only one specimen image 15L and one specimen image 15P are captured. However, in reality, multiple cross-sections of the liver specimen LVS and the pancreatic specimen PCS are collected from a single subject S, and multiple specimen images 15L and 15P are captured. The tissue specimens are also called tissue sections. The staining may be performed using hematoxylin alone, nuclear fast red, or the like.

[0027] Here, the administration group and the control group will be described. The administration group is composed of multiple subjects S to which the candidate substance 11 has been administered. The control group, on the other hand, is composed of multiple subjects S to which the candidate substance 11 has not been administered. In this example, in order to estimate the mechanism of action of the toxicity of the candidate substance 11, images of the liver specimens LVS and pancreas specimens PCS of the subjects S in the administration group are used as the specimen images 15. The number of subjects S constituting the administration group and the number of subjects S constituting the control group are both, for example, approximately 5 to 10. The subjects S constituting the administration group and the subjects S constituting the control group are subjects S with the same attributes and placed in the same rearing environment. The same attributes include, for example, the same age in weeks and / or the same gender. The same attributes also include the same composition ratio of ages in weeks and / or the same composition ratio of genders (e.g., five males and five females). The same rearing environment includes, for example, the same food, the same temperature and humidity of the rearing space, and / or the same size of the rearing space. The "same" in "same rearing environment" refers not only to the exact sameness, but also to the sameness in the sense of an error that is generally acceptable in the technical field to which the technology of the present disclosure belongs, and that does not contradict the intent of the technology of the present disclosure.

[0028] The administration group includes a plurality of groups with different doses of the candidate substance 11. For example, the dose of the candidate substance 11 is differentiated into three levels: a high dose group, a medium dose group, and a low dose group. This allows the influence of the dose of the candidate substance 11 on the subject S to be ascertained.

[0029] 2, the computer constituting the information processing device 10 includes, in addition to the display 12 and input device 13, a storage 30, a memory 31, a CPU (Central Processing Unit) 32, and a communication unit 33. These are interconnected via a bus line 34.

[0030] The storage 30 is a hard disk drive built into a computer constituting the information processing device 10 or connected via a cable or network. Alternatively, the storage 30 is a disk array consisting of multiple hard disk drives. The storage 30 stores control programs such as an operating system, various application programs, and various data associated with these programs. Note that a solid state drive may be used instead of a hard disk drive.

[0031] The memory 31 is a work memory for the CPU 32 to execute processing. The CPU 32 loads programs stored in the storage 30 into the memory 31 and executes processing in accordance with the programs. In this way, the CPU 32 comprehensively controls each part of the computer. The CPU 32 is an example of a "processor" according to the technology of the present disclosure. Note that the memory 31 may be built into the CPU 32. The communication unit 33 controls the transmission of various information to and from external devices such as the imaging device 19.

[0032] As an example, as shown in FIG. 3 , an operating program 40 is stored in the storage 30 of the information processing device 10. The operating program 40 is an application program for causing a computer to function as the information processing device 10. In other words, the operating program 40 is an example of an "operating program of an information processing device" according to the technology of the present disclosure. The storage 30 also stores a morphological abnormality identification model 41, causal relationship information 42, and the like. The morphological abnormality identification model 41 is an example of a "machine learning model" according to the technology of the present disclosure. The causal relationship information 42 indicates the causal relationship between multiple events 85 (see FIG. 11 , etc.) that represent changes in a living organism. Here, the term "living organism" refers to a broad and general concept of a "living thing" that is not limited to the subject S. Therefore, the term "living organism" also includes animals of a different species from the subject S.

[0033] When the operating program 40 is started, the CPU 32 of the computer constituting the information processing device 10 works in cooperation with the memory 31 and the like to function as a read / write (hereinafter abbreviated as RW) control unit 50, a morphological abnormality identification unit 51, a matching / extraction unit 52, a display control unit 53, and an instruction receiving unit 54.

[0034] The RW control unit 50 controls the storage of various data in the storage 30 and the reading of various data from the storage 30. For example, the RW control unit 50 stores a specimen image 15 from the imaging device 19 in the storage 30. Note that, since a plurality of specimen images 15 are actually obtained from one subject S, the storage 30 stores a plurality of specimen images 15 for one subject S.

[0035] The RW control unit 50 reads out from the storage 30 a specimen image 15 in accordance with the specification of the pathologist PT via the input device 13. The RW control unit 50 outputs the read-out specimen image 15 to the morphological abnormality identification unit 51 and the display control unit 53. The specimen image 15 output from the RW control unit 50 to the morphological abnormality identification unit 51, etc., is a target for identifying the type of morphological abnormality that has occurred in the liver specimen LVS and the pancreatic specimen PCS. Hereinafter, this specimen image 15 that is a target for identifying the type of morphological abnormality that has occurred in the liver specimen LVS and the pancreatic specimen PCS will be referred to as a target specimen image 15T.

[0036] The RW control unit 50 reads the morphological abnormality identification model 41 from the storage 30 and outputs the read morphological abnormality identification model 41 to the morphological abnormality identification unit 51. The RW control unit 50 also reads the causal relationship information 42 from the storage 30 and outputs the read causal relationship information 42 to the matching and extraction unit 52.

[0037] The morphological abnormality identification unit 51 uses the morphological abnormality identification model 41 to identify the type of morphological abnormality that has occurred in the tissue specimens (liver specimen LVS and pancreatic specimen PCS) shown in the target specimen image 15T. Morphological abnormalities include lesions that are not found in normal tissue specimens, such as hyperplasia, infiltration, congestion, inflammation, tumor, canceration, proliferation, bleeding, and glycogen loss. The morphological abnormality identification unit 51 outputs occurrence event information 60 that includes the identified type of morphological abnormality as an occurrence event to the matching and extraction unit 52. The occurrence event represents a change that has occurred in the subject S to which the candidate substance 11 has been administered. In this example, the occurrence event represents a morphological abnormality.

[0038] The matching and extraction unit 52 matches the events 85 in the causal relationship information 42 from the RW control unit 50 with the morphological abnormalities in the occurred event information 60. Then, the matching and extraction unit 52 extracts the causal relationship information 42 including the events 85 corresponding to the morphological abnormalities in the occurred event information 60 as corresponding causal relationship information 61. The matching and extraction unit 52 outputs the corresponding causal relationship information 61 to the display control unit 53.

[0039] The display control unit 53 controls the display of various screens on the display 12. The various screens include a target designation screen 90 (see FIG. 15 ) for designating a target specimen image 15T, and an analysis result display screen 95 (see FIG. 16 ) for displaying the target specimen image 15T and the corresponding causal relationship information 61. The instruction receiving unit 54 receives various instructions from the pathologist PT via the input device 13 on the various screens.

[0040] As an example, as shown in FIG. 4 , the morphological abnormality identification model 41 includes a liver morphological abnormality identification model 41L and a pancreatic morphological abnormality identification model 41P. These liver morphological abnormality identification model 41L and pancreatic morphological abnormality identification model 41P further include identification models for each of a plurality of morphological abnormalities. That is, the liver morphological abnormality identification model 41L includes a hyperplasia identification model 41L1 for identifying hyperplasia, a congestion identification model 41L2 for identifying congestion, an inflammation identification model 41L3 for identifying inflammation, a canceration identification model 41L4 for identifying canceration, and a proliferation identification model 41L5 for identifying proliferation. Similarly, the pancreatic morphological abnormality identification model 41P includes a hyperplasia identification model 41P1 for identifying hyperplasia, a congestion identification model 41P2 for identifying congestion, an inflammation identification model 41P3 for identifying inflammation, a canceration identification model 41P4 for identifying canceration, and a proliferation identification model 41P5 for identifying proliferation. In addition to these, the morphological abnormality identification model 41 also includes an infiltration identification model for identifying infiltration, a bleeding identification model for identifying bleeding, and the like.

[0041] As an example, as shown in FIG. 5 , the morphological abnormality identification unit 51 uses well-known image recognition technology to recognize the liver specimen LVS in a target specimen image 15T (hereinafter referred to as the target specimen image 15LT) in which the liver specimen LVS is captured, and subdivides the recognized liver specimen LVS into multiple patch images 65LT. Similarly, as shown in FIG. 6 , the morphological abnormality identification unit 51 uses well-known image recognition technology to recognize the pancreatic specimen PCS in a target specimen image 15T (hereinafter referred to as the target specimen image 15PT) in which a pancreatic specimen PCS is captured, and subdivides the recognized pancreatic specimen PCS into multiple patch images 65PT. The patch images 65LT and 65PT have preset sizes that can be handled by the liver morphological abnormality identification model 41L and the pancreatic morphological abnormality identification model 41P. The morphological abnormality identification unit 51 assigns patch image IDs to the patch images 65LT and 65PT. Furthermore, the morphological abnormality identifying unit 51 associates information indicating which portion of the target specimen images 15LT and 15PT the patch images 65LT and 65PT are cut out from, i.e., position information of the patch images 65LT and 65PT, with the patch image ID. Note that although the patch images 65LT and 65PT do not have areas that overlap with other patch images 65LT and 65PT in Figures 5 and 6, the patch images 65LT and 65PT may partially overlap with other patch images 65LT and 65PT.

[0042] As an example, as shown in FIG. 7 , the hyperplasia identification model 41L1 includes an encoder unit 70, a decoder unit 71, a calculation unit 72, and an output unit 73. A patch image 65LT is input to the encoder unit 70. The encoder unit 70 converts the patch image 65LT into a feature 74. The encoder unit 70 passes the feature 74 to the decoder unit 71. The decoder unit 71 decodes the feature 74.

[0043] As is well known, the encoder unit 70 includes a convolution layer that performs convolution processing using a filter and a pooling layer that performs pooling processing such as maximum value pooling. The decoder unit 71 also includes a convolution layer (CNN). The hyperplasia identification model 41L1 is a convolutional neural network (CNN). The encoder unit 70 extracts features 74 by repeatedly performing convolution processing in the convolution layer and pooling processing in the pooling layer on the input patch image 65LT. The features 74 represent the shape and texture characteristics of the liver specimen LVS depicted in the patch image 65LT. The features 74 are a collection of multiple numerical values. In other words, the features 74 are multidimensional data. The number of dimensions of the features 74 is, for example, 512, 1024, or 2048.

[0044] The calculation unit 72 calculates a predicted probability 75 of whether or not hyperplasia has occurred in the liver specimen LVS depicted in the patch image 65LT, based on the data generated by the decoder unit 71 decoding the feature amount 74. The predicted probability 75 is, for example, a numerical value between 0 and 1.0 (0% to 100%), and the closer the value is to 1.0, the higher the probability that hyperplasia has occurred in the liver specimen LVS depicted in the patch image 65LT. The calculation unit 72 outputs the predicted probability 75 to the output unit 73.

[0045] The output unit 73 outputs a determination result 76L1 corresponding to the predicted probability 75. More specifically, the output unit 73 compares the predicted probability 75 with a preset threshold. If the predicted probability 75 is less than the threshold, the output unit 73 outputs a determination result 76L1 indicating that hyperplasia has not occurred in the liver specimen LVS depicted in the patch image 65LT (represented as "no hyperplasia" in FIG. 7). On the other hand, if the predicted probability 75 is equal to or greater than the threshold, the output unit 73 outputs a determination result 76L1 indicating that hyperplasia has occurred in the liver specimen LVS depicted in the patch image 65LT (represented as "hyperplasia present" in FIG. 7). The threshold is, for example, 0.5. Note that other morphological abnormality determination models 41, such as the congestion determination model 41L2, the cancer determination model 41L4, the hyperplasia determination model 41P1, and the inflammation determination model 41P3, have the same configuration as the hyperplasia determination model 41L1, but differ in the content of the determination result 76L they output. For this reason, the hyperplasia specifying model 41L1 will be described as a representative, and descriptions of the other morphological abnormality specifying models 41 will be omitted.

[0046] As an example, as shown in FIG. 8 , the morphological abnormality identification unit 51 inputs one patch image 65LT to all models constituting the liver morphological abnormality identification model 41L (e.g., hyperplasia identification model 41L1, congestion identification model 41L2, inflammation identification model 41L3, canceration identification model 41L4, and proliferation identification model 41L5). Then, each model outputs an identification result 76L. Specifically, the hyperplasia identification model 41L1 outputs an identification result 76L1, the congestion identification model 41L2 outputs an identification result 76L2, and the inflammation identification model 41L3 outputs an identification result 76L3. The canceration identification model 41L4 outputs an identification result 76L4, and the proliferation identification model 41L5 outputs an identification result 76L5. The morphological abnormality identification unit 51 aggregates the identification results 76L output from each model to generate an aggregated identification result 80L. The aggregated identification result 80L is a result of picking out the identification result 76 from among the multiple identification results 76L output from each model, which indicates that a morphological abnormality has occurred in the liver specimen LVS shown in the patch image 65LT.

[0047] 8 illustrates an example in which the identification result 76L2 output from the congestion identification model 41L2 indicates "congestion is present," the identification result 76L3 output from the inflammation identification model 41L3 indicates "inflammation is present," and the identification results 76L output from all other models indicate "no morphological abnormality." In this case, the aggregate identification result 80L indicates "inflammation is present" and "congestion is present," as shown in the figure. In this way, multiple types of morphological abnormality may be identified for a single patch image 65LT.

[0048] As an example, as shown in FIG. 9 , the morphological abnormality identification unit 51 generates occurrence event information 60L by further aggregating the aggregated identification results 80L of each patch image 65LT. The occurrence event information 60L summarizes the morphological abnormalities that are determined to have occurred in the aggregated identification results 80L. FIG. 9 illustrates an example of occurrence event information 60L that includes two morphological abnormalities, "inflammation" and "congestion," as occurrence events. In this way, multiple types of morphological abnormalities may be identified for a single target specimen image 15LT. Although not shown, the morphological abnormality identification unit 51 also performs the same processing on the patch image 65PT as on the patch image 65LT to generate occurrence event information 60P (see FIG. 14 ).

[0049] 10 , the causal relationship information 42 includes liver causal relationship information 42L and pancreas causal relationship information 42P. The liver causal relationship information 42L includes first liver causal relationship information 42L1, second liver causal relationship information 42L2, third liver causal relationship information 42L3, fourth liver causal relationship information 42L4, and fifth liver causal relationship information 42L5. Similarly, the pancreas causal relationship information 42P includes first pancreas causal relationship information 42P1, second pancreas causal relationship information 42P2, third pancreas causal relationship information 42P3, fourth pancreas causal relationship information 42P4, and fifth pancreas causal relationship information 42P5. In this way, causal relationship information 42 is prepared for each of multiple organs.

[0050] 11 and 12 , the first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1 include a plurality of events 85 that represent changes in a living organism. The events 85 are connected to each other by arrows. The event 85 connected to the start point of the arrow indicates a cause, and the event 85 connected to the end point of the arrow indicates a result. Each event 85 is classified into a molecular-level change, a cellular-level change, or a tissue-level change in the living organism.

[0051] 11 , the first liver causal relationship information 42L1 indicates the causal relationships among the events 85, starting with the event 85 of "decreased bile acid excretion," which is a change at the molecular level in a living organism, and continuing with the event 85 of "release of inflammation-inducing substance," which is also a change at the molecular level, and the event 85 of "enhanced inflammation," which is a change at the cellular level, and finally leading to the event 85 of "cholestasis," which is a change at the tissue level. That is, the first liver causal relationship information 42L1 indicates the causal relationships among the multiple events 85 that represent changes in a living organism due to the toxicity of past drug candidate substances. Although not shown, the same applies to the other events, such as the second liver causal relationship information 42L2 and the third liver causal relationship information 42L3. The event 85 of "decreased bile acid excretion" and the event 85 of "release of inflammation-inducing substance" are examples of "events related to molecular changes in a living organism" according to the technology of the present disclosure.

[0052] 12 , the first pancreas causal relationship information 42P1 is information indicating the causal relationships among the events 85, starting with the event 85 of “decreased lipolysis,” which is a change at the molecular level in a living organism, and continuing to the event 85 of “cholestasis,” which is a change at the tissue level, the event 85 of “decreased digestive enzyme secretion,” and the event 85 of “pancreatic cell proliferation,” which are changes at the cellular level, and finally leading to the event 85 of “pancreatic cancer,” which is also a change at the tissue level. That is, like the first liver causal relationship information 42L1, the first pancreas causal relationship information 42P1 is information indicating the causal relationships among multiple events 85 that represent changes in a living organism due to the toxicity of past drug candidate substances. Although not shown, the same applies to the other events, such as the second pancreas causal relationship information 42P2 and the third pancreas causal relationship information 42P3. The “decreased lipolysis” event 85 is an example of an “event related to molecular changes in a living organism” according to the technology of the present disclosure.

[0053] As can be seen from the "cholestasis" event 85, the first pancreas causal relationship information 42P1 also contains some events 85 related to the liver LV. However, the final event 85 is "pancreatic cancer," which is an event 85 related to the pancreas PC, and therefore is classified as pancreas causal relationship information 42P.

[0054] Such causal relationship information 42 may be created by a pathologist PT based on the results of past evaluation tests of candidate drug substances. Furthermore, the causal relationship information 42 may be obtained from a public database, such as AOP (Adverse Outcome Pathway)-Wiki. Note that the causal relationship information 42 does not necessarily have to show the relationships between events 85 with arrows, as in the example, but may simply contain information about the events 85.

[0055] As an example, as shown in FIGS. 13 and 14 , the matching and extraction unit 52 matches the causal relationship information 42 with the incident event information 60. FIG. 13 illustrates the matching of the first liver causal relationship information 42L1 with the incident event information 60L. The matching and extraction unit 52 determines, through the matching, that the "increased inflammation" event 85 in the first liver causal relationship information 42L1 corresponds to "inflammation" in the incident event information 60L. The matching and extraction unit 52 also determines, through the matching, that the "cholestasis" event 85 in the first liver causal relationship information 42L1 corresponds to "congestion" in the incident event information 60L. In this case, since the first liver causal relationship information 42L1 includes the event 85 corresponding to the morphological abnormality in the incident event information 60L, the matching and extraction unit 52 extracts the first liver causal relationship information 42L1 as the corresponding causal relationship information 61. Although not shown, the matching and extraction unit 52 does not naturally extract as corresponding causal relationship information 61 liver causal relationship information 42L that does not include an event 85 corresponding to the morphological abnormality in the occurrence event information 60L.

[0056] 14 shows how the first pancreas causal relationship information 42P1 is matched with the occurrence event information 60P. The matching and extraction unit 52 determines, through matching, that the event 85 for "pancreatic cell proliferation" in the first pancreas causal relationship information 42P1 corresponds to "proliferation" in the occurrence event information 60P. The matching and extraction unit 52 also determines, through matching, that the event 85 for "pancreatic cancer" in the first pancreas causal relationship information 42P1 corresponds to "malignant transformation" in the occurrence event information 60P. In this case, since the first pancreas causal relationship information 42P1 includes the event 85 that corresponds to the morphological abnormality in the occurrence event information 60P, the matching and extraction unit 52 extracts the first pancreas causal relationship information 42P1 as the corresponding causal relationship information 61. Although not shown, the matching and extraction unit 52 does not naturally extract as corresponding causal relationship information 61 pancreas causal relationship information 42P that does not include an event 85 corresponding to the morphological abnormality in the occurrence event information 60P.

[0057] The display control unit 53 controls the display 12 to display a target designation screen 90, as shown in FIG. 15 , as an example. The display control unit 53 displays the target designation screen 90 when the pathologist PT issues an instruction to display a specimen image 15 via the input device 13 and the instruction is received by the instruction receiving unit 54. The target designation screen 90 displays a plurality of specimen images 15 side by side. These specimen images 15 are specimen images 15 obtained from one of the plurality of subjects S constituting the administration group. FIG. 15 shows an example in which five specimen images 15L with specimen image IDs "SIL00001" to "SIL00005" and five specimen images 15P with specimen image IDs "SIP00001" to "SIP00005," obtained from the subject S with subject ID "R001," are displayed side by side. The subject ID is displayed as a pull-down menu 91, allowing the subject S for which the specimen image 15 is displayed on the target designation screen 90 to be switched.

[0058] The target designation screen 90 is a screen for designating one target specimen image 15LT from among a plurality of specimen images 15L. The target designation screen 90 is also a screen for designating one target specimen image 15PT from among a plurality of specimen images 15P. The target designation screen 90 is provided with one selection frame 92L that can move between the specimen images 15L and one selection frame 92P that can move between the specimen images 15P. An analysis button 93 is also provided at the bottom of the target designation screen 90. The pathologist PT aligns the selection frames 92L and 92P with the desired specimen images 15L and 15P and then selects the analysis button 93. As a result, the specimen images 15L and 15P aligned with the selection frames 92L and 92P are set as the target specimen images 15LT and 15PT, and the morphological abnormality identification unit 51 identifies the type of morphological abnormality, the matching and extraction unit 52 extracts the corresponding causal relationship information 61, and so on.

[0059] When the corresponding causal relationship information 61 is input from the comparison / extraction unit 52, the display control unit 53 performs control to display, on the display 12, an analysis result display screen 95 shown in FIG. 16 as an example. The analysis result display screen 95 displays the target specimen images 15LT and 15PT, the occurrence event information 60L and 60P (denoted as "morphological abnormality that is believed to have occurred" in FIG. 16), and the corresponding causal relationship information 61. FIG. 16 illustrates an example in which the first liver causal relationship information 42L1 shown in FIGS. 11 and 13 and the first pancreas causal relationship information 42P1 shown in FIGS. 12 and 14 are displayed as the corresponding causal relationship information 61. The control to display the analysis result display screen 95 including this corresponding causal relationship information 61 on the display 12 is an example of "control to output corresponding causal relationship information" according to the technology of the present disclosure.

[0060] The display control unit 53 displays a highlight frame 96 around an event 85 related to a change in a molecule of a living body among the events 85 in the corresponding causal relationship information 61 to distinguish it from other events 85. In FIG. 16 , the events 85 related to a change in a molecule of a living body are the events 85 of "decreased bile acid excretion" and "release of inflammation-inducing substance" in the first liver causal relationship information 42L1 and the event 85 of "decreased lipid breakdown" in the first pancreas causal relationship information 42P1. Note that methods for distinguishing the events 85 related to a change in a molecule of a living body from other events 85 may include changing the color of the event 85 related to a change in a molecule of a living body from the color of the other events 85, making the size of the event 85 related to a change in a molecule of a living body larger than the other events 85, or flashing the event 85 related to a change in a molecule of a living body.

[0061] Next, the operation of the above configuration will be described with reference to the flowchart shown in Fig. 17. First, when the operating program 40 is started in the information processing device 10, the CPU 32 of the information processing device 10 functions as the RW control unit 50, the morphological abnormality identifying unit 51, the matching and extraction unit 52, the display control unit 53, and the instruction receiving unit 54, as shown in Fig. 3.

[0062] The imaging device 19 captures a specimen image 15L of a liver specimen LVS of the subject S and a specimen image 15P of a pancreatic specimen PCS of the subject S. The specimen images 15L and 15P are output from the imaging device 19 to the information processing device 10. In the information processing device 10, the specimen images 15L and 15P from the imaging device 19 are stored in the storage 30 by the RW control unit 50.

[0063] When the pathologist PT issues an instruction to display the specimen image 15 via the input device 13, the RW control unit 50 reads the specimen image 15 specified in the display instruction from the storage 30 (step ST100). The specimen image 15 is output from the RW control unit 50 to the display control unit 53. As shown in Fig. 15, the specimen image 15 is displayed on the display 12 via the target designation screen 90 under the control of the display control unit 53 (step ST105).

[0064] When the pathologist PT aligns the selection frames 92L and 92P with the desired specimen images 15L and 15P on the target designation screen 90 and selects the analysis button 93 (YES in step ST110), the RW control unit 50 reads out the specimen images 15L and 15P on which the selection frames 92L and 92P were aligned at that time as target specimen images 15LT and 15PT from the storage 30 (step ST115). The target specimen images 15LT and 15PT are output from the RW control unit 50 to the morphological abnormality identification unit 51 and the display control unit 53.

[0065] The RW control unit 50 reads the morphological abnormality identification model 41 from the storage 30, and outputs the read morphological abnormality identification model 41 to the morphological abnormality identification unit 51. In addition, the RW control unit 50 reads the causal relationship information 42 from the storage 30, and outputs the read causal relationship information 42 to the matching and extraction unit 52.

[0066] As shown in FIGS. 5 and 6 , the morphological abnormality identification unit 51 subdivides the target specimen images 15LT and 15PT into multiple patch images 65LT and 65PT (step ST120). Next, as shown in FIG. 8 , the morphological abnormality identification unit 51 inputs the patch images 65LT to the hyperplasia identification models 41L1, etc., which then output identification results 76L1, etc. Next, the morphological abnormality identification unit 51 aggregates the multiple identification results 76L output from each model to generate an aggregated identification result 80L. This identifies the type of morphological abnormality occurring in the liver specimen LVS depicted in the patch images 65LT (step ST125). The process of step ST125 is performed on all patch images 65LT. Similar processing is performed on the patch images 65PT.

[0067] After the process of step ST125 is performed on all patch images 65LT and 65PT (YES in step ST130), the morphological abnormality identification unit 51 generates occurrence event information 60L from the aggregate identification results 80L of each patch image 65LT (step ST135), as shown in Fig. 9 . A similar process is performed on the patch image 65PT, and occurrence event information 60P is generated (step ST135). The occurrence event information 60L and 60P are output from the morphological abnormality identification unit 51 to the matching / extraction unit 52.

[0068] 13 and 14 , the collation / extraction unit 52 compares the causal relationship information 42 with the occurred event information 60, and extracts corresponding causal relationship information 61 from the plurality of pieces of causal relationship information 42 (step ST140). The corresponding causal relationship information 61 is output from the collation / extraction unit 52 to the display control unit 53.

[0069] Under the control of the display control unit 53, the analysis result display screen 95 shown in Fig. 16 is displayed on the display 12 (step ST145). The analysis result display screen 95 includes the corresponding causal relationship information 61. The pathologist PT views the analysis result display screen 95 and infers the mechanism of action of the toxicity of the candidate substance 11 by referring to the corresponding causal relationship information 61, etc.

[0070] As described above, the CPU 32 of the information processing device 10 includes a matching / extraction unit 52 and a display control unit 53. The matching / extraction unit 52 compares a plurality of pieces of causal relationship information 42 indicating the causal relationships between a plurality of events 85 representing changes in a living organism with occurrence events representing changes that occurred in the subject S, a living organism to which a drug candidate substance 11 was administered. The matching / extraction unit 52 then extracts, from the plurality of pieces of causal relationship information 42, corresponding causal relationship information 61 including events 85 corresponding to morphological abnormalities. The display control unit 53 controls the display of an analysis result display screen 95 including the corresponding causal relationship information 61 on the display 12. The corresponding causal relationship information 61 is highly useful for the pathologist PT to estimate the mechanism of action of the toxicity of the candidate substance 11. This reduces the burden on the pathologist PT and enables efficient evaluation of the candidate substance 11.

[0071] 11 and 12 , the causal relationship information 42 is information indicating the causal relationships among a plurality of events 85 that represent changes in a living organism due to the toxicity of past drug candidate substances. This facilitates the pathologist PT's estimation of the mechanism of action of the toxicity of the candidate substance 11. Note that instead of or in addition to the causal relationship information 42 indicating the causal relationships among a plurality of events 85 that represent changes in a living organism due to the toxicity of past drug candidate substances, causal relationship information 42 indicating the causal relationships among a plurality of events 85 that represent changes in a living organism due to the pharmacological effects of past drug candidate substances may be used.

[0072] The occurrence event represents a morphological abnormality that occurred in the organs of the subject S, in this case, the liver specimen LVS and the pancreas specimen PCS, after administration of the candidate substance 11. The events 85 in the causal relationship information 42 include a relatively large number of events 85 that are closely related to morphological abnormalities, such as "increased inflammation" and "cholestasis" in the first liver causal relationship information 42L1, or "pancreatic cell proliferation" and "pancreatic cancer" in the first pancreas causal relationship information 42P1. Therefore, by defining the occurrence event as a morphological abnormality, it is possible to extract more plausible corresponding causal relationship information 61, further facilitating the pathologist PT's estimation of the mechanism of action of the toxicity of the candidate substance 11.

[0073] The morphological abnormality identification unit 51 identifies the type of morphological abnormality by performing image analysis on the target specimen images 15LT and 15PT, which are tissue specimens of organs of the subject S, in this case, a liver specimen LVS and a pancreas specimen PCS. This further reduces the burden on the pathologist PT compared to when the pathologist PT identifies the type of morphological abnormality by observing the target specimen images 15LT and 15PT.

[0074] The morphological abnormality identification unit 51 identifies multiple types of morphological abnormalities for one target specimen image 15LT or 15PT. Therefore, compared to a case where only one type of morphological abnormality can always be identified for one target specimen image 15LT or 15PT, it is possible to extract corresponding causal relationship information 61 that is more useful for estimating the mechanism of action of the toxicity of the candidate substance 11.

[0075] In image analysis, the morphological abnormality identification unit 51 uses a morphological abnormality identification model 41 that outputs the presence or absence of a morphological abnormality in response to input of target specimen images 15LT and 15PT (patch images 65LT and 65PT). Machine learning models such as the morphological abnormality identification model 41 with relatively high prediction accuracy can now be easily prepared. This makes it possible to identify the type of morphological abnormality easily and accurately. Note that the type of morphological abnormality may be identified without using a machine learning model by using well-known techniques such as pattern recognition technology.

[0076] The causal relationship information 42 includes an event 85 related to a change in a molecule of a living body. As shown in FIG. 16 , when the display control unit 53 controls the display of the corresponding causal relationship information 61, it displays a highlight frame 96 around the event 85 related to a change in a molecule of a living body to distinguish it from other events 85. The event 85 related to a change in a molecule of a living body is considered to be a strong candidate for a pharmacodynamic biomarker that is important for estimating the mechanism of action of the toxicity of the candidate substance 11. Therefore, by distinguishing the event 85 related to a change in a molecule of a living body from other events 85, it is possible to make the pathologist PT aware of the event 85 related to a change in a molecule of a living body.

[0077] [Second Embodiment] In the first embodiment, the case where one piece of corresponding causal relationship information 61 is extracted for each of the liver LV and the pancreas PC is described as an example, but this is not limiting. The collation / extraction unit 52 may extract multiple pieces of corresponding causal relationship information 61.

[0078] When the collation / extraction unit 52 extracts multiple pieces of corresponding causal relationship information 61, the display control unit 53 derives the reliability of each piece of the multiple pieces of corresponding causal relationship information 61 based on, for example, a table 100 shown in FIG. 18 . Table 100 is data in which reliability is registered according to the number of events 85 corresponding to morphological abnormalities in the occurrence event information 60 (hereinafter referred to as the number of corresponding events). For example, when the number of corresponding events is 1, the reliability is 4 when the number of corresponding events is 4, and the reliability is 5 when the number of corresponding events is 5 or more. The higher the reliability value of the corresponding causal relationship information 61, the higher the reliability of the information. Taking the first liver causal relationship information 42L1 shown in FIG. 13 and the first pancreas causal relationship information 42P1 shown in FIG. 14 as examples, the number of corresponding events is 2, so the reliability is 2.

[0079] 19 , when the collation / extraction unit 52 extracts a plurality of pieces of corresponding causal relationship information 61, the display control unit 53 displays the corresponding causal relationship information 61 in descending order of reliability on the analysis result display screen 95. Figure 19 illustrates an example in which five pieces of liver causal relationship information 42L, namely, sixth liver causal relationship information 42L6, seventh liver causal relationship information 42L7, eighth liver causal relationship information 42L8, ninth liver causal relationship information 42L9, and tenth liver causal relationship information 42L10, are extracted as the corresponding causal relationship information 61. Figure 19 also illustrates an example in which the reliability of the sixth liver causal relationship information 42L6 is 1, the reliability of the seventh liver causal relationship information 42L7 and the tenth liver causal relationship information 42L10 is 2, the reliability of the eighth liver causal relationship information 42L8 is 5, and the reliability of the ninth liver causal relationship information 42L9 is 4.

[0080] In this case, the display control unit 53 assigns the display order of the eighth liver causal relationship information 42L8, which has the highest reliability of 5, to number 1 on the analysis result display screen 95. Subsequently, the display order of the ninth liver causal relationship information 42L9 is number 2, the seventh liver causal relationship information 42L7 is number 3, the tenth liver causal relationship information 42L10 is number 4, and finally the display order of the sixth liver causal relationship information 42L6, which has the lowest reliability of 1, is number 5.

[0081] 20 , when the collation / extraction unit 52 extracts a plurality of pieces of corresponding causal relationship information 61, the display control unit 53 displays the corresponding causal relationship information 61 having a reliability level of a set value (here, 3 or greater) on the analysis result display screen 95 in descending order of reliability. In FIG. 20 , the extracted corresponding causal relationship information 61 and their reliability levels are the same as those in the example of FIG. 19 . In this case, the display control unit 53 ranks the eighth liver causal relationship information 42L8, which has the highest reliability level of 5, as the first item on the analysis result display screen 95, and ranks the ninth liver causal relationship information 42L9, which has the next highest reliability level of 4, as the second item. The sixth liver causal relationship information 42L6, the seventh liver causal relationship information 42L7, and the tenth liver causal relationship information 42L10, which have reliability levels of 1 or 2 and less than the set value of 3, are not displayed.

[0082] As described above, in the second embodiment, when the collation / extraction unit 52 extracts a plurality of pieces of corresponding causal relationship information 61, the display control unit 53 derives the reliability of each of the plurality of pieces of corresponding causal relationship information 61. Then, control is performed to display the corresponding causal relationship information 61 based on the reliability. For this reason, it is possible to display a plurality of pieces of corresponding causal relationship information 61 in descending order of reliability as shown in FIG. 19, or to hide corresponding causal relationship information 61 whose reliability is below a set value as shown in FIG. 20. This further facilitates the pathologist PT's estimation of the mechanism of action of the toxicity of the candidate substance 11.

[0083] The reliability of the corresponding causal relationship information 61 increases with the number of corresponding events. For this reason, it is possible to display the corresponding causal relationship information 61 with a larger number of corresponding events preferentially over other corresponding causal relationship information 61. It is considered that the corresponding causal relationship information 61 with a larger number of corresponding events is more useful for estimating the mechanism of action of the toxicity of the candidate substance 11. Therefore, the pathologist PT can further advance his / her estimation of the mechanism of action of the toxicity of the candidate substance 11. Note that the reliability according to the number of corresponding events may be displayed on the analysis result display screen 95.

[0084] [Embodiment 2_2] In this embodiment, when the matching / extraction unit 52 extracts multiple pieces of corresponding causal relationship information 61, the display control unit 53 derives the reliability of each piece of the multiple pieces of corresponding causal relationship information 61 based on, for example, table 105 shown in FIG. 21 . Table 105 is data in which reliability levels are registered according to the average values ​​of the predicted probabilities 75 of morphological abnormalities corresponding to the events 85 in the corresponding causal relationship information 61. For example, when the average value of the predicted probabilities 75 is 0.5 or more and less than 0.6, the reliability level is 1; when the average value of the predicted probabilities 75 is 0.7 or more and less than 0.8, the reliability level is 3; and when the average value of the predicted probabilities 75 is 0.9 or more and less than 1.0, the reliability level is 5. In this case, as in the above-described embodiment 2_1, the higher the reliability value of the corresponding causal relationship information 61, the higher the reliability of the information.

[0085] The average value of the predicted probability 75 is calculated as follows. Let us again take the first liver causal relationship information 42L1 shown in FIG. 13 and other figures as an example. Consider a case where the predicted probability 75 of "inflammation," a morphological abnormality corresponding to the "increased inflammation" event 85, by the inflammation identification model 41L3 is, for example, 0.85, and the predicted probability 75 of "stagnation," a morphological abnormality corresponding to the "cholestasis" event 85, by the congestion identification model 41L2 is, for example, 0.65. In this case, the average value of the predicted probability 75 is (0.85 + 0.65) / 2 = 0.75. The predicted probability 75 of "inflammation" by the inflammation identification model 41L3 is a representative value of the predicted probabilities 75 obtained from all patch images 65LT for which the identification result 76L3 indicating "inflammation present" has been output. Similarly, the predicted probability 75 of "congestion" by the congestion identification model 41L2 is a representative value of the predicted probabilities 75 obtained from all patch images 65LT for which the identification result 76L2 indicating "congestion present" has been output. The representative value may be the average, maximum, median, minimum, or the like.

[0086] In this embodiment, as in the case of the 2_1 embodiment, the display control unit 53 displays a plurality of pieces of corresponding causal relationship information 61 in descending order of reliability, and hides corresponding causal relationship information 61 whose reliability is less than a set value. This has the effect of further facilitating the pathologist PT's estimation of the mechanism of action of the toxicity of the candidate substance 11, as in the case of the 2_1 embodiment.

[0087] As described above, in the second embodiment, the display control unit 53 derives the reliability based on the predicted probability 75 of the occurrence or non-occurrence of a morphological abnormality determined by the morphological abnormality identification model 41. Therefore, it is possible to display corresponding causal relationship information 61 with a high average value of the predicted probability 75 preferentially over other corresponding causal relationship information 61. Corresponding causal relationship information 61 with a high average value of the predicted probability 75 is considered to be more useful in estimating the mechanism of action of the toxicity of the candidate substance 11. This further facilitates the pathologist PT's estimation of the mechanism of action of the toxicity of the candidate substance 11. The analysis result display screen 95 may display the reliability according to the average value of the predicted probability 75, or the average value of the predicted probability 75 itself. Furthermore, instead of the average value of the predicted probability 75 of a morphological abnormality corresponding to the event 85 in the corresponding causal relationship information 61, a maximum value, a median value, a minimum value, or the like may be displayed.

[0088] The second embodiment 2_1 and the second embodiment 2_2 may be combined and implemented. In this case, the display control unit 53 derives the reliability based on data in which the reliability according to the number of corresponding events and the average value of the prediction probability 75 is registered. Alternatively, the display control unit 53 may derive the reliability by solving a calculation formula using the number of corresponding events and the average value of the prediction probability 75 as parameters.

[0089] The reliability may be derived based on the ratio between the total number of events 85 constituting the corresponding causal relationship information 61 and the number of corresponding events. In this case, for example, Fisher's exact test is performed, and the reliability is determined by subtracting the p-value calculated thereby from 1.

[0090] [Third Embodiment] In this embodiment, when the matching and extraction unit 52 extracts a plurality of pieces of corresponding causal relationship information 61 and a common event 85 exists in at least two of the extracted plurality of pieces of corresponding causal relationship information 61, the display control unit 53 integrates the corresponding causal relationship information 61 having the common event 85 under the common event 85.

[0091] 22 illustrates a case in which the matching / extraction unit 52 extracts the first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1 as the corresponding causal relationship information 61, as in the first embodiment. The first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1 share a common event 85, "cholestasis." In other words, the first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1 are examples of "corresponding causal relationship information with a common event" and "corresponding causal relationship information of different organs" according to the technology of the present disclosure. Furthermore, the "cholestasis" event 85 is an example of a "common event" according to the technology of the present disclosure.

[0092] 23 as an example, the display control unit 53 integrates the first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1 for the event 85 of "cholestasis" to generate integrated causal relationship information 110. Then, as shown in FIG. 24 as an example, the display control unit 53 performs control to display the integrated causal relationship information 110 on the analysis result display screen 95.

[0093] As described above, in the third embodiment, when the collation and extraction unit 52 extracts a plurality of pieces of corresponding causal relationship information 61 and a common event 85 exists in at least two of the extracted plurality of pieces of corresponding causal relationship information 61, the display control unit 53 performs control to display the corresponding causal relationship information 61 in which the common event 85 exists after integrating the corresponding causal relationship information 61 in terms of the common event 85. Therefore, the corresponding causal relationship information 61 in which the common event 85 exists can be compactly organized, and the corresponding causal relationship information 61 in which the common event 85 exists can be displayed in an easy-to-read manner.

[0094] 23 , the display control unit 53 integrates the corresponding causal relationship information 61 of different organs, namely the first liver causal relationship information 42L1 and the first pancreas causal relationship information 42P1. This allows the corresponding causal relationship information 61 of different organs to be compactly organized, and the corresponding causal relationship information 61 of different organs to be displayed in an easily viewable manner.

[0095] It is also possible to integrate three or more pieces of corresponding causal relationship information 61. Furthermore, the above-described second embodiment 2_1 or second embodiment 2_2 may be applied to the third embodiment. In this case, the display control unit 53 derives the reliability of the integrated causal relationship information 110.

[0096] [Fourth Embodiment] In the first embodiment and the like, occurrence events representing morphological abnormalities are exemplified, but this is not limiting. As an example, occurrence events may represent a change in the body weight of the subject S after administration of the candidate substance 11, a change in the amount of food intake (food intake) of the subject S, and a change in the results of a clinical chemistry test of the subject S, as shown in the occurrence event information 115 in FIG. 25 . The change in the body weight of the subject S is shown as "weight loss" and "weight gain" in the figure. The change in the amount of food intake of the subject S is shown as "food intake decrease" and "food intake increase" in the figure. The change in the results of the clinical chemistry test of the subject S is shown as "blood glucose level increase" and "blood glucose level decrease" in the figure. Note that the change in the results of the clinical chemistry test of the subject S may also be "cholesterol level increase" and "cholesterol level decrease," "uric acid level increase" and "uric acid level decrease," or "γ-GTP (Glutamyl Transpeptidase) increase" and "γ-GTP decrease," etc.

[0097] As described above, in the fourth embodiment, the occurring events represent changes in the weight of the subject S, changes in the amount of food intake of the subject S, and changes in the results of the clinical chemical test of the subject S. Therefore, the causal relationship information 42 having events 85 relating to changes in the weight of the subject S, changes in the amount of food intake of the subject S, and changes in the results of the clinical chemical test of the subject S can be extracted as the corresponding causal relationship information 61. As in the occurring event information 115 shown in Fig. 25 , by adding occurring events representing changes in the weight of the subject S, changes in the amount of food intake of the subject S, and changes in the results of the clinical chemical test of the subject S to the occurring event representing the morphological abnormality, the variety of the corresponding causal relationship information 61 can be increased.

[0098] Incidentally, instead of occurrence events indicating morphological abnormalities, occurrence events indicating changes in the weight of the subject S, changes in the amount of food intake of the subject S, and changes in the results of clinical chemistry tests of the subject S may be used. Furthermore, instead of all of the changes in the weight of the subject S, changes in the amount of food intake of the subject S, and changes in the results of clinical chemistry tests of the subject S, one or two of these may be used.

[0099] 26, the fifth embodiment deals with a slide specimen 120 in which tissue specimens of multiple organs are mounted on a single glass slide 16. Fig. 26 illustrates a case in which a heart specimen HS, a brain specimen BS, and a bone marrow specimen BMS are mounted in addition to a liver specimen LVS. In this case, the specimen image 15 shows the heart specimen HS, the brain specimen BS, and the bone marrow specimen BMS in addition to the liver specimen LVS.

[0100] The CPU 32 of the information processing device 10 of the fifth embodiment functions as an identification unit 121 in addition to the processing units 50 to 54 of the first embodiment. The identification unit 121 identifies the tissue specimen of each organ from the specimen image 15, for example, using a template for identifying the tissue specimen of each organ or a machine learning model. The identification unit 121 outputs coordinate information of boxes 122 to 125 surrounding the tissue specimen of each organ as an identification result. Box 122 is a box surrounding a heart specimen HS, and box 123 is a box surrounding a liver specimen LVS. Furthermore, box 124 is a box surrounding a brain specimen BS, and box 125 is a box surrounding a bone marrow specimen BMS.

[0101] As described above, in the fifth embodiment, the specimen image 15 is an image obtained by photographing the specimen slide 120 on which tissue specimens from multiple organs are placed. The identification unit 121 identifies the tissue specimens of each organ from the specimen image 15. Therefore, it is possible to handle the specimen slide 120 on which tissue specimens from multiple organs are placed. The specimen slide 120 on which tissue specimens from multiple organs are placed, as in the present embodiment, is more common than the specimen slide 18 on which a tissue specimen from a single organ is placed, as in the first embodiment. Therefore, processing that is more suited to general operations can be performed.

[0102] The pathologist PT may manually define a frame indicating the tissue specimen of each organ in the specimen image 15 .

[0103] In the target specimen images 15LT and 15PT displayed on the analysis result display screen 95, the portions where morphological abnormalities have occurred may be clearly indicated by coloring or the like.

[0104] The output mode of the corresponding causal relationship information 61 is not limited to the mode in which the illustrated analysis result display screen 95 is displayed on the display 12. The corresponding causal relationship information 61 may be printed out on a paper medium, or may be sent as an attachment to an e-mail.

[0105] The organ is not limited to the liver LV, but may be the stomach, lung, small intestine, or large intestine. The subject S is not limited to a rat, but may be a mouse, guinea pig, gizzard shad, hamster, ferret, rabbit, dog, cat, monkey, or the like.

[0106] The information processing device 10 may be a personal computer installed in a pharmaceutical development facility as shown in FIG. 1, or may be a server computer installed in a data center independent of the pharmaceutical development facility.

[0107] When the information processing device 10 is configured as a server computer, the specimen images 15 are transmitted from personal computers installed in each pharmaceutical development facility to the server computer via a network such as the Internet. The server computer distributes various screens, such as the target selection screen 90, to the personal computer in the form of screen data for web distribution created using a markup language such as XML (Extensible Markup Language). The personal computer reproduces the screen to be displayed on the web browser based on the screen data and displays it on a display. Note that other data description languages, such as JSON (Javascript (registered trademark) Object Notation), may be used instead of XML.

[0108] The information processing device 10 according to the technique of the present disclosure can be widely used across all stages of pharmaceutical development, from the earliest stage of drug discovery target setting to the final stage of clinical trials.

[0109] The hardware configuration of the computer constituting the information processing device 10 according to the technology of the present disclosure can be modified in various ways. For example, the information processing device 10 can be configured with multiple computers separated as hardware in order to improve processing power and reliability. For example, the functions of the morphological anomaly identification unit 51 and the matching / extraction unit 52 can be distributed and performed by two computers. In this case, the information processing device 10 is configured with two computers.

[0110] In this way, the hardware configuration of the computer of the information processing device 10 can be changed as appropriate depending on the required performance such as processing power, safety, reliability, etc. Furthermore, not only the hardware, but also application programs such as the operating program 40 can be duplicated or stored in a distributed manner across multiple storage devices in order to ensure safety and reliability.

[0111] In each of the above embodiments, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the RW control unit 50, the morphological abnormality identification unit 51, the comparison / extraction unit 52, the display control unit 53, the instruction reception unit 54, and the identification unit 121. The various processors include the CPU 32, which is a general-purpose processor that executes software (operation program 40) to function as various processing units, as described above, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a programmable logic device (PLD) that is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0112] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs and / or a combination of a CPU and an FPGA).Furthermore, multiple processing units may be configured with a single processor.

[0113] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, as typified by computers such as client and server, and this processor functions as multiple processing units. Second, a form in which a processor is used to realize the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0114] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit (circuitry) that combines circuit elements such as semiconductor elements.

[0115] From the above description, the technology described in the following supplementary paragraphs can be understood.

[0116] [Supplementary Item 1] An information processing device comprising a processor, wherein the processor compares a plurality of pieces of causal relationship information indicating the causal relationships between a plurality of events representing changes in a living organism with an occurrence event representing a change that has occurred in a subject, the living organism, to which a drug candidate substance has been administered, extracts corresponding causal relationship information including an event corresponding to the occurrence event from the plurality of pieces of causal relationship information, and performs control to output the corresponding causal relationship information. [Supplementary Item 2] The information processing device according to Supplementary Item 1, wherein the causal relationship information is information indicating the causal relationships between a plurality of events representing changes in the living organism due to past toxicity of a drug candidate substance. [Supplementary Item 3] The information processing device according to Supplementary Item 2, wherein the occurrence event represents a morphological abnormality that has occurred in an organ of the subject after administration of the candidate substance. [Supplementary Item 4] The information processing device according to Supplementary Item 3, wherein the processor identifies a type of the morphological abnormality by image analysis of a specimen image showing a tissue specimen of the organ of the subject. [Supplementary Item 5] The information processing device according to Supplementary Item 4, wherein the processor identifies a plurality of types of morphological abnormality for one specimen image. [Supplementary Item 6] The information processing device according to Supplementary Item 4 or Supplementary Item 5, wherein the processor uses a machine learning model that outputs whether or not the morphological abnormality has occurred in response to input of the specimen image in the image analysis. [Supplementary Item 7] The information processing device according to any one of Supplementary Items 1 to 6, wherein, when a plurality of pieces of corresponding causal relationship information are extracted, the processor derives a reliability for each of the plurality of pieces of corresponding causal relationship information, and controls output of the corresponding causal relationship information based on the reliability. [Supplementary Item 8] The information processing device according to Supplementary Item 7, wherein the reliability is higher for a corresponding causal relationship information with a greater number of events corresponding to the occurred event. [Supplementary Item 9] The information processing device according to Supplementary Item 7 or Supplementary Item 8, wherein the occurred event represents a morphological abnormality that has occurred in an organ of the subject after administration of the candidate substance, and the processor identifies the type of the morphological abnormality using a machine learning model that outputs the type of morphological abnormality in response to input of a specimen image depicting a tissue specimen of the organ of the subject, and derives the reliability based on the predicted probability of the occurrence of the morphological abnormality by the machine learning model.[Supplementary Item 10] The information processing device according to any one of Supplementary Items 1 to 9, wherein the processor extracts a plurality of pieces of the corresponding causal relationship information, and if at least two of the extracted pieces of corresponding causal relationship information have a common event, controls to integrate the corresponding causal relationship information for which the common event exists, and output the integrated information. [Supplementary Item 11] The causal relationship information is prepared for each of a plurality of organs, and the processor controls to integrate the corresponding causal relationship information for different organs for which the common event exists, and output the integrated information. [Supplementary Item 12] The information processing device according to any one of Supplementary Items 1 to 11, wherein the occurred event represents at least one of a change in body weight of the subject, a change in food intake of the subject, and a change in results of a clinical chemical test of the subject. [Supplementary Item 13] The causal relationship information includes events related to molecular changes in the living body, and the processor, when controlling the output of the corresponding causal relationship information, distinguishes events related to molecular changes in the living body from other events. An information processing device according to any one of Supplementary Items 1 to 12.

[0117] The technology of the present disclosure can be appropriately combined with the various embodiments and / or various modified examples described above. Furthermore, it is not limited to the above-described embodiments, and various configurations can be adopted without departing from the spirit of the present disclosure. Furthermore, the technology of the present disclosure extends not only to programs but also to storage media that non-temporarily store programs.

[0118] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0119] In this specification, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0120] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

Claims

1. A processor is provided. The processor, A plurality of pieces of causal relationship information showing causal relationships between a plurality of events showing changes in a living body is collated with occurrence events showing changes that have occurred in a subject, which is a living body to which a drug candidate substance has been administered; extracting corresponding causal relationship information including the event corresponding to the occurrence event from the plurality of pieces of causal relationship information; and performing control to output the corresponding causal relationship information. Information processing device.

2. The information processing apparatus according to claim 1 , wherein the causal relationship information is information indicating causal relationships between a plurality of events that represent changes in a living body caused by toxicity of a past drug candidate substance.

3. The information processing apparatus according to claim 2 , wherein the occurrence event represents a morphological abnormality occurring in an organ of the subject after administration of the candidate substance.

4. The processor, The information processing apparatus according to claim 3 , wherein the type of the morphological abnormality is identified by performing image analysis on a specimen image in which a tissue specimen of the subject's organ is captured.

5. The processor, The information processing apparatus according to claim 4 , wherein a plurality of types of morphological abnormality are identified for one of the specimen images.

6. The processor, The information processing device according to claim 4 , wherein the image analysis uses a machine learning model that outputs the presence or absence of the morphological abnormality in response to an input of the specimen image.

7. The processor, When a plurality of pieces of corresponding causal relationship information are extracted, Deriving a reliability of each of the plurality of corresponding causal relationship information; The information processing apparatus according to claim 1 , further comprising a control for outputting the corresponding causal relationship information based on the reliability.

8. The information processing apparatus according to claim 7 , wherein the reliability is higher for the corresponding causal relationship information having a larger number of events corresponding to the occurrence event.

9. the developmental event represents a morphological abnormality occurring in an organ of the subject after administration of the candidate substance; The processor, Identifying the occurrence of each type of morphological abnormality using a machine learning model that outputs the occurrence of each type of morphological abnormality in response to an input of a specimen image showing a tissue specimen of the subject's organ; The information processing device according to claim 7 , wherein the reliability is derived based on a predicted probability of occurrence or non-occurrence of each type of morphological abnormality by the machine learning model.

10. The processor, When a plurality of pieces of corresponding causal relationship information are extracted and the common event exists in at least two of the extracted plurality of pieces of corresponding causal relationship information, The information processing apparatus according to claim 1 , wherein control is performed such that the corresponding causal relationship information for which a common event exists is integrated for the common event and then output.

11. the causal relationship information is prepared for each of a plurality of organs, The processor, The information processing device according to claim 10 , wherein control is performed such that, in the corresponding causal relationship information in which a common event exists, the corresponding causal relationship information of different organs is integrated in the common event and then output.

12. The information processing apparatus of claim 1 , wherein the occurrence represents at least one of a change in the subject's weight, a change in the subject's food intake, and a change in the subject's clinical chemistry test results.

13. The causal relationship information includes an event related to a change in a molecule of the living body, The processor, The information processing apparatus according to claim 1 , wherein, when controlling to output the corresponding causal relationship information, an event relating to a change in a molecule of the living body is distinguished from other events.

14. Collating a plurality of pieces of causal relationship information showing causal relationships between a plurality of events showing changes in a living body with an occurrence event showing a change that has occurred in a subject, which is a living body to which a drug candidate substance has been administered; extracting corresponding causal relationship information including the event corresponding to the occurring event from the plurality of pieces of causal relationship information; and performing control to output the corresponding causal relationship information; A method for operating an information processing device comprising the steps of:

15. Collating a plurality of pieces of causal relationship information showing causal relationships between a plurality of events showing changes in a living body with an occurrence event showing a change that has occurred in a subject, which is a living body to which a drug candidate substance has been administered; extracting corresponding causal relationship information including the event corresponding to the occurring event from the plurality of pieces of causal relationship information; and performing control to output the corresponding causal relationship information; An operating program for an information processing device that causes a computer to execute a process including the steps of: