Status change estimation system, status change estimation program, and status change estimation method

Abstract

To provide a state change estimation system, a state change estimation program, and a state change estimation method which allow a user to objectively grasp chronological change in a state of an object.SOLUTION: A state change estimation system comprises: tomographic image analysis means for quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging unit which captures continuous two-dimensional tomographic images; first state estimation means for estimating, as a first state, a current state of the object on the basis of the area analyzed by the tomographic image analysis means; and second state estimation means for estimating, as a second state, change in a state of the object after lapse of a certain period on the basis of the first state estimated by the first state estimation means.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a state change estimation system, a state change estimation program, and a state change estimation method. [Background technology]

[0002] For example, when observing or treating an object such as a tumor, an aneurysm, or an area affected by a chronic disease, a technology has been proposed that compares images of the object over time before and after the observation, treatment, etc. to estimate changes in the object before and after the observation, treatment, etc.

[0003] Patent Document 1 discloses a medical image diagnostic support device that aims to effectively display images suitable for observing the results of treatment of an object when comparing images of the object over time, before and after treatment. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP2006-87601A Summary of the Invention [Problem to be solved by the invention]

[0005] Incidentally, when comparing images of an object over time and measuring the size of the object, a common method is for a medical professional such as a doctor to place a scale on the object imaged by an imaging device to measure the diameter of the object.

[0006] When using this method to measure the diameter of an object and thereby measure its size, the medical professional performing the measurement will place a scale on any part of the object to measure it, and since the choice of which part to place the scale on is left to the subjective judgment of the medical professional, it is anticipated that the size of the object may not be measured appropriately.

[0007] As a result, there is a concern that it may not be possible to properly grasp changes over time due to comparison of objects.

[0008] The present invention has been made in consideration of the above-mentioned circumstances, and has an objective of providing a state change estimation system, a state change estimation program, and a state change estimation method that can objectively grasp changes in the state of an object over time. [Means for solving the problem]

[0009] In order to achieve the above-mentioned object, the state change estimation system of the present invention comprises a tomographic image analysis means for quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images, a first state estimation means for estimating a current state of the object as a first state based on the area analyzed by the tomographic image analysis means, and a second state estimation means for estimating a change in the state of the object after the passage of an arbitrary time as a second state based on the first state estimated by the first state estimation means.

[0010] With this, the area occupied by the object in the tomographic image is quantitatively analyzed to estimate the current state of the object as a first state, and based on the first state, the change in the state of the object after the passage of any given time is estimated as a second state, thereby making it possible to objectively grasp the change in the object's state over time.

[0011] This state change estimation system includes an indicator generating means for generating an indicator related to the object based on the second state estimated by the second state estimation means and external factor data in which external factors assumed to act on the object are stored.

[0012] The first state estimation means of this state change estimation system may estimate the first state by comparing the area with a predetermined first state model that defines the first state of the object, and in this case, the first state model may be generated by machine learning.

[0013] The tomographic image analysis means of this condition change estimation system calculates the number of pixels corresponding to a two-dimensional region of the object in successive tomographic images, and calculates the volume of the object as a region by adding up the number of pixels calculated for each successive tomographic image.

[0014] The second state estimation means of this state change estimation system estimates the second state by comparing the first state estimated by the first state estimation means with a new first state estimated by the first state estimation means after an arbitrary time has elapsed since the first state was estimated.

[0015] The external factor data processed by this condition change estimation system may include at least one of physical factor data related to the body of a subject who owns the object, lifestyle factor data related to the lifestyle of the subject, and medical diagnostic factor data related to a medical diagnosis administered to the subject.

[0016] In order to achieve the above-mentioned object, the state change estimation system of the present invention comprises a tomographic image analysis means for quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images, a first state estimation means for estimating a current state of the object as a first state based on the area analyzed by the tomographic image analysis means and external factor data in which external factors assumed to act on the object are stored, and a second state estimation means for estimating a change in the state of the object after the passage of an arbitrary time as a second state based on the first state estimated by the first state estimation means and the external factor data.

[0017] In order to achieve the above-mentioned object, the state change estimation program of the present invention comprises a tomographic image analysis means for quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images, a first state estimation means for estimating a current state of the object as a first state based on the area analyzed by the tomographic image analysis means, and a second state estimation means for estimating a change in the state of the object after the passage of an arbitrary time as a second state based on the first state estimated by the first state estimation means.

[0018] In order to achieve the above-mentioned object, the state change estimation method of the present invention quantitatively analyzes the area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images, estimates the current state of the object as a first state based on the analyzed area, and estimates the change in the state of the object after the passage of an arbitrary period of time as a second state based on the estimated first state. Effect of the Invention

[0019] According to the present invention, it is possible to objectively grasp the change over time in the state of an object. [Brief description of the drawings]

[0020] [Figure 1] 1 is a block diagram illustrating an outline of the configuration of a state change estimation system according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a block diagram illustrating an outline of a computed tomography apparatus. [Diagram 3] FIG. 2 is a diagram showing a part of a tomographic image captured by a computed tomography apparatus. [Figure 4] FIG. 2 is a block diagram illustrating an outline of the hardware configuration of a computer in the state change estimation system according to the present embodiment. [Diagram 5] FIG. 11 is a block diagram illustrating an outline of the configuration of a storage unit of a service provider terminal of the state change estimation system according to the present embodiment. [Figure 6] FIG. 11 is a diagram for explaining an overview of external factor data processed by the state change estimation system according to the present embodiment. [Figure 7] 13 is a diagram for explaining an outline of the processing of the tomographic image analysis means of the state change estimation program of the state change estimation system according to the present embodiment. FIG. [Figure 8] 13 is a diagram for explaining an outline of the processing of the tomographic image analysis means of the state change estimation program of the state change estimation system according to the present embodiment. FIG. [Figure 9]FIG. 13 is a diagram for explaining an outline of the processing of a first state estimation means of a state change estimation program of the state change estimation system according to the present embodiment. [Figure 10] FIG. 13 is a diagram for explaining an outline of the processing of a second state estimation means of the state change estimation program of the state change estimation system according to the present embodiment. [Figure 11] FIG. 13 is a diagram for explaining an outline of the processing of the index generating means of the condition change estimation program of the condition change estimation system according to the present embodiment. [Figure 12] FIG. 13 is a diagram for explaining a distribution state based on an index generated by an index generating means of the state change estimation program of the state change estimation system according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Next, a condition change estimating system according to an embodiment of the present invention will be described with reference to FIGS.

[0022] In this embodiment, a case will be described as an example in which the object to be processed by the state change estimation system is a lesion caused by an infectious disease on the chest of a patient who is the subject.

[0023] 1 is a block diagram illustrating an outline of the configuration of a condition change estimation system according to the present embodiment. As shown in the figure, a condition change estimation system 10 includes a computed tomography imaging device 20, a medical institution terminal 30 connected to the computed tomography imaging device 20, and a service provider terminal 40.

[0024] In this embodiment, a medical institution terminal 30 and a service provider terminal 40 are connected to each other via a network so as to be accessible to each other.

[0025] In this embodiment, the computed tomography imaging apparatus 20 and the medical institution terminal 30 are deployed in a medical institution 1 that provides medical treatment to a patient P, and the service provider server 40 is deployed in a service provider 2 that provides a service using the condition change estimation system 10.

[0026] 2 is a block diagram illustrating an outline of a computed tomography imaging apparatus 20. As shown in the figure, in this embodiment, the computed tomography imaging apparatus 20 is used for imaging an arbitrary part of the body of a patient U, and obtains continuous two-dimensional tomographic images D1 of the imaged part.

[0027] FIG. 3 is a diagram showing, as an example, a tomographic image D1a that is a part of a series of tomographic images D1 captured of the chest of a patient U. As shown in the figure, an affected area O is captured in the tomographic image D1.

[0028] In this embodiment, the medical institution terminal 30 and the service provider terminal 40 shown in FIG. 1 are implemented by computers having substantially the same hardware configuration, such as desktop or notebook computers.

[0029] FIG. 4 is a block diagram illustrating an outline of the hardware configuration of a computer in which the medical institution terminal 30 and the service provider terminal 40 are implemented.

[0030] As shown in the figure, the computer comprises, as its main components, a processor 101, a memory 102, a storage 103, a transmitting / receiving unit 104, and an input / output unit 105, which are electrically connected to each other via a bus 106.

[0031] The processor 101 is an arithmetic unit that controls the operation of the computer, controls the transmission and reception of data between each element, and performs processes required for executing application programs.

[0032] In this embodiment, the processor 101 is, for example, a CPU (Central Processing Unit), and executes application programs stored in a storage 103 (to be described later) and deployed in a memory 102 to perform various processes.

[0033] The memory 102 includes a main storage device configured as a volatile storage device such as a dynamic random access memory (DRAM), and an auxiliary storage device configured as a non-volatile storage device such as a flash memory or a hard disk drive (HDD).

[0034] This memory 102 is used as a working area for the processor 101, and also stores a basic input / output system (BIOS) that is executed when the computer is started, various setting information, and the like.

[0035] The storage 103 stores application programs, data used in various processes, and the like.

[0036] The transceiver 104 connects the computer to a network. The transceiver 104 may include a short-range communication interface such as Bluetooth (registered trademark) or Bluetooth Low Energy (BLE).

[0037] If necessary, information input devices such as a keyboard and a mouse and output devices such as a display are connected to the input / output unit 105. In this embodiment, a keyboard, a mouse, and a display are each connected.

[0038] The bus 106 transmits, for example, address signals, data signals, and various control signals between the processor 101, memory 102, storage 103, transmission / reception unit 104, and input / output unit 105 that are connected thereto.

[0039] 5 is a block diagram illustrating an outline of the configuration of the storage 103 of the service provider terminal 40. As shown in the figure, the storage 103 includes a database 41 realized by the memory area of ​​the storage 103, and a state change estimation program 42.

[0040] In this embodiment, the database 41 stores successive tomographic images D1 of an arbitrary part of the body of a patient U imaged by the computed tomography imaging apparatus 20, and external factor data D2.

[0041] 6 is a diagram for explaining an outline of the external factor data D2. As shown in the figure, the external factor data D2 includes physical factor data d1, which are external factors assumed to act on the affected area O, lifestyle factor data d2, and medical diagnosis factor data d3.

[0042] The physical factor data d1 is data related to the body of the patient U, and in this embodiment, is composed of items such as "age (elderly)" and "gender (male)", for example.

[0043] The lifestyle factor data d2 is data relating to the lifestyle of the patient U, and in this embodiment, is composed of items such as "smoking history" and "obesity level", for example.

[0044] The medical diagnostic factor data d3 is data regarding the medical diagnosis performed on patient U, and in this embodiment is composed of items such as "CT findings," "degree of SOFA score," "degree of HScore," "degree of oxygen saturation," "virus load in PCR test," "blood test," "determination of cardiac troponin I," "ferritin value," "creatinine value," "presence or absence of underlying disease," and "presence or absence of gastrointestinal symptoms."

[0045] In this embodiment, the state change estimating program 42 shown in FIG. 5 includes a tomographic image analyzing unit 42a, a first state estimating unit 42b, a second state estimating unit 42c, and an index generating unit 42d.

[0046] In this embodiment, the tomographic image analysis unit 42a is a module that quantitatively analyzes the area occupied by the diseased area O in the successive tomographic images D1.

[0047] 7 and 8 are diagrams for explaining an outline of the processing of the tomographic image analysis unit 42a. As shown in Fig. 7, the tomographic image analysis unit 42a calculates the number of pixels P corresponding to a two-dimensional area occupied by the diseased area O in a part of the tomographic images (for example, the tomographic image D1a) of the continuous tomographic images D1 obtained by capturing the diseased area O.

[0048] Similarly, the tomographic image analysis unit 42a calculates the number of pixels P corresponding to the two-dimensional area occupied by the affected area O in other tomographic images (e.g., tomographic images D1b to D1n) of the consecutive tomographic images D1 capturing the affected area O, as shown in FIG.

[0049] Next, the tomographic image analysis unit 42a adds up the numbers of pixels P from the tomographic images D1a to D1n, and calculates the volume V of the diseased part O as the region of the diseased part O based on the sum of the numbers of pixels P.

[0050] The first state estimation unit 42b shown in FIG. 5 is a module that estimates the current state of the affected area O as a first state based on the area occupied by the affected area O in successive tomographic images D1, and in this embodiment, the current state of the affected area O is estimated as the first state based on the volume V of the affected area O calculated by the tomographic image analysis unit 42a.

[0051] In this embodiment, the first state estimation unit 42b is implemented by an artificial intelligence module, and generates learning data based on images of various diseased areas occurring in the chest, for example.

[0052] Furthermore, the first state estimation unit 42b generates a trained model by performing machine learning on the generated training data based on any teacher data (in this embodiment, for example, an image of an affected area in the chest due to an infectious disease).

[0053] As a method for performing machine learning, various algorithms such as neural networks, random forests, and SVM (Support Vector Machine) are appropriately used.

[0054] In this embodiment, the trained model is a first state model that defines a first state, which is the current state of the affected area O, based on, for example, the width of the three-dimensional range of inflammation.

[0055] Next, as shown in FIG. 9, the first state estimation unit 42b compares the generated first state model M1 with the volume V of the affected area O, and autonomously estimates the first state, which is the current state of the affected area O grasped from the volume V.

[0056] In this embodiment, "B", which has the highest degree of agreement with the affected area O grasped from the volume V (84%), is estimated as the first state, which is the current state of the affected area O.

[0057] The second state estimation unit 42c shown in FIG. 5 is a module that estimates a change in the state of the affected area O after an arbitrary time has elapsed as a second state based on the first state estimated by the first state estimation unit 42b.

[0058] In this embodiment, the second condition estimation unit 42c estimates the second condition of the affected area O by comparing the first condition of the affected area O estimated by the first condition estimation unit 42b with a new first condition of the affected area O estimated by the first condition estimation unit 42b after an arbitrary time has elapsed since the first condition was estimated.

[0059] In this embodiment, the second state estimation unit 42c is implemented by an artificial intelligence module, and generates a learned model by performing machine learning using learning data based on the correlation between the passage of time and the change in volume V of the affected area O, for example.

[0060] In this embodiment, the learned model is a second state model M2 that defines a second state in terms of a speed concept, such as “fast” or “slow,” for the change in volume V of the affected area O before and after an arbitrary period of time.

[0061] Specifically, as shown in FIG. 10, if the first state of the affected area O on day T is “B” and the first state of the affected area O on day T+X is “C,” the second state, which is the change in the state of the affected area O grasped from the change in volume V, is autonomously estimated.

[0062] In this embodiment, for example, if the affected area O, whose first state is "B", changes to the first state "C" on day T+2, the change in the state of the affected area O is estimated to be "rapid" as the second state.

[0063] The index generating unit 42d shown in FIG. 5 is a module that generates an index related to the affected area O based on the second state estimated by the second state estimation unit 42c and the external factor data D2, and in this embodiment, generates a severity index of the affected area O as the index.

[0064] Here, in this embodiment, the external factor data D2 is used as data that is the basis for estimating the possibility that the severity of the affected area O will suddenly change due to an action on the affected area O.

[0065] In this embodiment, the index generation unit 42d is implemented by an artificial intelligence module, and generates a learned model, for example, by performing machine learning using learning data based on the correlation between the second state and external factor data D2.

[0066] 11 is a diagram for explaining an outline of the processing of the index generating unit 42d. As shown in the figure, the index generating unit 42d classifies the severity of the affected area O into i0 to i5, and classifies i0 to i1 into mild cases, i2 to i4 into moderate cases, and i5 into severe cases, to generate a severity index I.

[0067] In this embodiment, for example, if the second status is estimated to be "slow" and there is no external factor, the severity is shown to be i0, and, for example, if the second status is estimated to be "slow" and the external factor is "female", the severity is shown to be i1.

[0068] On the other hand, for example, if the second state is estimated to be "slow" and the external factor is "no smoking history", the severity is shown to be i2, if the second state is estimated to be "slow" and the external factor is "no smoking history, no underlying disease", the severity is shown to be i3, and if the second state is estimated to be "fast" and the external factor is "underlying disease, poor blood test results", the severity is shown to be i4.

[0069] Furthermore, for example, if the second state is estimated to be "fast" and the external factors include "high viral load in PCR test," the severity is indicated as i5.

[0070] Next, a method of operating the condition change estimation system 10 will be described.

[0071] For example, in an arbitrary medical institution 1 shown in FIG. 1, chests of a plurality of patients U who are suspected of having an infectious disease are imaged by a computed tomography apparatus 20 to obtain successive tomographic images D1 (tomographic image D1a to tomographic image D1n).

[0072] The number of pixels P corresponding to the area occupied by the diseased area O in successive cross-sectional images D1a to D1n is added up, and the volume V of the diseased area O is calculated as the area of ​​the diseased area O by adding up the number of pixels P. Based on the volume V of the diseased area O, the current state of the diseased area O is estimated as a first state.

[0073] After a certain time has elapsed since the first state was estimated (e.g., two days later), the current state of the affected area O is estimated as a new first state, and the first state before and after the two days have elapsed is compared to estimate the change in the state of the affected area O as a second state.

[0074] Next, a severity index I of the affected area O is generated based on the second state and the external factor data D2.

[0075] 12 is a diagram illustrating the distribution of patients U based on the severity of the affected area O as understood from the severity index I. As shown in the figure, there are three patients U with a severity level of i0, two patients U with a severity level of i1, two patients U with a severity level of i2, three patients U with a severity level of i3, two patients U with a severity level of i4, and one patient U with a severity level of i5.

[0076] Based on this severity index I, medical institution 1, for example, will take measures to have five patients U who are deemed to have mild symptoms with severity levels i0 and i1 undergo home treatment or stay in an accommodation facility, and will transport one patient U who is deemed to have severe symptoms with severity level i5 to a designated infectious disease medical institution.

[0077] On the other hand, for the seven patients U who were deemed to have moderate symptoms, with severity levels ranging from i2 to i4, measures will be taken according to the severity of the disease, such as admitting the five patients U with severity levels i2 and i3 to medical institution 1 for treatment as it is deemed that there is little possibility of their symptoms suddenly changing, and transporting the two patients U with severity level i4 to a designated infectious disease medical institution as it is deemed that there is a high possibility of their symptoms suddenly changing.

[0078] In this way, the medical institution 1 can grasp the severity of multiple patients U who are at risk of contracting an infectious disease, and can take appropriate measures according to the severity.

[0079] Therefore, it is possible to prevent a situation such as a collapse of the medical system, which is anticipated in the event of an epidemic infectious disease that spreads widely in an extremely short period of time, in which the number of infected people exceeds the capacity of medical institutions.

[0080] When generating such a severity index I, the condition change estimation system 10 of this embodiment quantitatively analyzes the area occupied by the affected area O in the tomographic image D1 to estimate the current condition of the affected area O as a first state, and based on the first state, estimates the change in the condition of the affected area O after the passage of an arbitrary time as a second state, thereby making it possible to objectively grasp the change in the condition of the affected area O over time.

[0081] In particular, in this embodiment, the volume V of the affected area O is calculated based on the number of pixels P corresponding to the two-dimensional area occupied by the affected area O in the tomographic image D1, thereby improving objectivity in understanding changes in the condition of the affected area O over time.

[0082] The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the spirit of the invention.

[0083] In the above embodiment, the external factor data D2 is used as basic data for estimating the possibility that the severity of the affected area O will suddenly change due to an action on the affected area O, and a case has been described in which the external factor data D2 is used when generating an index related to the affected area O by the second condition estimation unit 42c, but is not limited to this case and may be used in various cases.

[0084] For example, the first state estimation unit 42b may apply the external factor data D2 to the comparison result between the first state model M1 and the volume V of the affected area O to estimate the first state.

[0085] Furthermore, the second condition estimation unit 42c may apply the external factor data D2 to the result of comparing the first condition of the affected area O with the new first condition of the affected area O to estimate the second condition.

[0086] In the above embodiment, a case has been described in which the volume V of the diseased area O is calculated as the area to quantitatively analyze the area occupied by the diseased area O in the tomographic image D1. However, the area to be calculated may be the area occupied by the diseased area O in any part of the tomographic image D1 (e.g., the tomographic image D1a).

[0087] In the above embodiment, a case has been described in which the first state estimation unit 42b is implemented by an artificial intelligence module, and the first state is estimated by a first state model M1 generated by machine learning. However, it is also possible to prepare a table that predefines the first state of the affected area O without using machine learning as the first state model, and estimate the first state by comparing this first state model with the area of ​​the affected area O.

[0088] Similarly, for the second state estimation unit 42c, a table that predefines the second state of the affected area O without using machine learning may be prepared as a second state model.

[0089] In the above embodiment, the case has been described where the service provider terminal 40 is provided at the service provider 2, but the service provider terminal 40 may be a server implemented in a cloud environment.

[0090] Furthermore, the same functions as the service provider terminal 40 may be implemented in the medical institution terminal 30 without providing a separate service provider terminal 40.

[0091] In the above embodiment, the subject is described as an infected area O in the chest of a patient U, but the subject can also be various types of tissue, such as a tumor, an aneurysm, an area affected by a chronic disease, or tissue to be cultured.

[0092] Furthermore, the change in state of the tissue that is the object estimated by the second state estimation unit 42c may be a change in state due to tissue growth, or may be a change in state due to tissue decay. [Explanation of symbols]

[0093] 1. Medical institutions 2. Service providers 10 State change estimation system 20. Computed tomography imaging device 30 Medical institution terminals 40 Service provider terminal 41 Database 42 State change estimation program 42a Tomographic image analysis unit (tomographic image analysis means) 42b First state estimation unit (first state estimation means) 42c second state estimation unit (second state estimation means) 42d Index generation unit (index generation means) D1 Tomographic image D2 External factors data I Severity Index (Indicator) M1 First state model M2 Second state model O Affected area (object) P Pixel U Patient (subject) V Volume

Claims

1. a tomographic image analysis means for quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images; a first state estimation means for estimating a current state of the object as a first state based on the region analyzed by the tomographic image analysis means; a second state estimation means for estimating a change in a state of the object after a lapse of an arbitrary time based on the first state estimated by the first state estimation means as a second state; an index generating means for generating an index for estimating a possibility of a sudden change in severity of the object based on the second state estimated by the second state estimating means and external factor data in which external factors acting on the object and serving as a basis for estimating a possibility of a sudden change in severity of the object are stored; and A state change estimation system comprising:

2. The first state estimation means The state change estimation system according to claim 1 , wherein the first state is estimated by comparing the region with a preset first state model that defines the first state of the object.

3. The state change estimation system of claim 2 , wherein the first state model is generated by machine learning.

4. The tomographic image analysis means The state change estimation system according to any one of claims 1 to 3, wherein the number of pixels corresponding to a two-dimensional region of the object in the successive tomographic images is calculated, and the volume of the object is calculated as the region by summing up the number of the pixels calculated for each of the successive tomographic images.

5. The second state estimation means The state change estimation system according to any one of claims 1 to 4, wherein the second state is estimated by comparing the first state estimated by the first state estimation means with a new first state estimated by the first state estimation means after an arbitrary time has elapsed since the first state was estimated.

6. The external factor data is The condition change estimation system of claim 2, comprising at least one of physical factor data relating to the body of a subject who owns the object, lifestyle factor data relating to the lifestyle of the subject, and medical diagnostic factor data relating to a medical diagnosis performed on the subject.

7. On the computer, Quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images; Estimating a current state of the object as a first state based on the analyzed region; estimating a change in a state of the object after a lapse of an arbitrary time based on the estimated first state as a second state; generating an index for estimating a possibility of a sudden change in the severity of the object based on the estimated second state and external factor data in which external factors acting on the object and serving as a basis for estimating a possibility of a sudden change in the severity of the object are stored; A state change estimation program that executes the process.

8. The computer Quantitatively analyzing an area occupied by an object in a tomographic image of the object captured by an imaging device that captures successive two-dimensional tomographic images; Estimating a current state of the object as a first state based on the analyzed region; estimating a change in a state of the object after a lapse of an arbitrary time based on the estimated first state as a second state; generating an index for estimating a possibility of a sudden change in the severity of the object based on the estimated second state and external factor data in which external factors acting on the object and serving as a basis for estimating a possibility of a sudden change in the severity of the object are stored; State change estimation method.

Images