JP6530841B2 - DIAGNOSTIC SUPPORT SYSTEM, OPERATION METHOD THEREOF, DIAGNOSTIC SUPPORT DEVICE, AND PROGRAM - Google Patents

Description

  The present invention relates to a diagnostic support system, and more particularly to a diagnostic support system that provides information for supporting medical diagnosis.

  In the medical field, image diagnosis is performed in which a doctor interprets a medical image obtained by an imaging device such as an X-ray CT apparatus or an MRI to make a diagnosis. For example, in image diagnosis, a doctor who receives a request for interpretation by the attending doctor comprehensively determines findings (hereinafter referred to as “interpretation findings”) obtained from the image and various measurement values, and symptoms of a lesion shown in the image Identify. Then, the doctor uses the interpretation findings and measurement values to compile the process of the image diagnosis as an interpretation report to the requesting physician.

  A medical diagnosis support device that supports diagnosis by detecting abnormal shadows and the like on medical images and deducing the state of shadows by computer processing for the purpose of reducing the burden on the interpretation of such doctors. Support devices are being developed). Usually, when using such a diagnosis support device, the doctor first interprets the image, and then the doctor refers to the support information presented by the diagnosis support device, and compares the result with the result of the image interpretation. Make a judgment. Here, in order to trust the support information presented by the diagnosis support apparatus, it is desirable for the doctor to know what the support information was derived from. That is, it is preferable that the diagnosis support device presents an inference basis for the support information to be presented.

  Therefore, a diagnosis support device for presenting such a reasoning base has been developed. For example, in Patent Document 1 proposed by the applicants of the present invention, a technique for presenting negative information and positive information as support information with respect to an inference result of a device based on input information such as interpretation findings is disclosed. Have been described. Further, Patent Document 1 describes a technique for presenting negative information and positive information for each of the possible diagnosis names as support information. As a result, the diagnosis support apparatus can present the inference result and can also present, as the support information, information that has influenced the derivation of the inference result of the apparatus based on the information such as the interpretation findings.

Unexamined-Japanese-Patent No. 2010-200840

  Information such as affirming the assumed diagnostic name if the doctor has assumed the diagnosis as a tendency of interpretation by the doctor, and information such as negating other diagnosis if not confident. Often used as a clue. However, in the technique described in the above-mentioned patent documents, there is a problem that such information can not be presented as support information.

  In view of the above problems, the present invention aims to enable efficient presentation of information necessary for improving the certainty of a doctor's diagnosis.

  As one means for achieving the above object, the diagnosis support system of the present invention has the following configuration. That is, inference means for acquiring inference probabilities of a plurality of diagnostic names corresponding to the case based on a plurality of medical information corresponding to the cases, and the inference probability of a target diagnosis among the plurality of diagnosis names Selection means for selecting the medical information negatively affected on the inference probability of a diagnosis other than the target diagnosis when the is lower than a predetermined reference, and based on the selected medical information And display control means for displaying the support information on the display unit.

  According to the present invention, it is possible to efficiently present the information necessary to improve the doctor's diagnostic confidence.

FIG. 1 is a view showing a device configuration of a diagnosis support apparatus according to a first embodiment. The figure which shows the basic composition of the computer which implement | achieves each part of a diagnosis assistance apparatus by software. 3 is a flowchart showing a processing procedure in the first embodiment. The figure which showed the example of the interpretation finding and clinical information in 1st Embodiment. The figure which showed the example of the influence degree in 1st Embodiment. The figure which showed the example of the assistance information in 1st Embodiment.

  Hereinafter, embodiments (embodiments) for carrying out the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the illustrated example.

First Embodiment
The diagnosis support system according to the first embodiment acquires medical information on a case that is a medical diagnosis target, and performs diagnosis support on the case. In the present embodiment, the diagnosis support system acquires, as medical information, a plurality of interpretation findings and past medical history and tumor marker values (hereinafter referred to as clinical information) related to the abnormal shadow of the lung. Then, based on the acquired information, inference regarding the type (diagnosis name) of the abnormality of the lung abnormal shadow is performed, and the case where the diagnosis support information is presented based on the result is described as an example. The inference target is not limited to this, and the diagnostic name, the input readable interpretation findings, the clinical information, etc. shown below are all merely examples for explaining the process of the diagnosis support system.

  FIG. 1 shows the configuration of a diagnosis support apparatus of the system according to the first embodiment. The diagnosis support apparatus 100 according to the present embodiment includes an input information acquisition unit 102, an inference unit 104, an influence degree acquisition unit 106, a selection unit 108, and a presentation unit 110. Further, the diagnosis support device 100 is connected to the information input terminal 200.

  The information input terminal 200 is a server (not shown) corresponding to a case to be diagnosed by the operation of the user (doctor), etc., and case information (information of electronic medical record including medical image and clinical information) regarding abnormal shadow of lung Get from Note that the information input terminal 200 may be connected to an external storage device such as an FDD, an HDD, a CD drive, a DVD drive, an MO drive, a ZIP drive, etc., and the case information may be acquired from those drives. The information input terminal 200 displays the case information in a readable form.

  The user inputs an interpretation finding for case information displayed on a monitor as a display unit using a mouse or a keyboard. This process is implemented by providing the information input terminal 200 with a function that can be selected by the GUI using, for example, a template-type input support method. In the present embodiment, the interpretation findings and the clinical information include the name and the state, respectively, as described later. Further, in the information input terminal, the user may input the monitor display with reference to the interpretation findings, and the clinical information may be automatically input to the template, or may be input by the user. The information input terminal 200 transmits the interpretation findings and the clinical information and data (such as a representative image) accompanying this information to the diagnosis support apparatus 100 via the LAN or the like according to the operation of the user.

  The input information acquisition unit 102 includes information (hereinafter referred to as input information) regarding an abnormal shadow of the lung input from the information input terminal 200 to the diagnosis support apparatus 100 and data accompanying it (hereinafter referred to as input information together with medical information). ), And outputs these to the inference unit 104, the influence degree acquisition unit 106, and the presentation unit 110. Based on the input information acquired by the input information acquisition unit 102, the inference unit 104 executes an inference process on the abnormal shadow of the lung to be diagnosed, and calculates the probability (inference result) that the abnormal shadow is the diagnosis name of each Do. The calculated inference result is output to the influence degree acquisition unit 106, the selection unit 108, and the presentation unit 110. The inference process will be described later.

  The influence degree acquisition unit 106 acquires the influence degree using the input information acquired by the input information acquisition unit 102 and the inference result acquired by the inference unit 104, and outputs the acquired influence degree to the selection unit 108. The method of acquiring the degree of influence will be described later. The selection unit 108 selects information based on the inference result acquired by the inference unit 104 and the degree of influence acquired by the influence degree acquisition unit 106. The information selected by the selection unit 108 is output to the presentation unit 110. The presentation unit 110 generates and displays information to be presented. Specifically, the presentation unit 110 presents information to be presented based on the input information and accompanying data acquired by the input information acquisition unit 102, the inference result acquired by the inference unit 104, and the information selected by the selection unit 108. Control the display of the generated information.

  Note that at least a part of each unit of the diagnosis support device 100 illustrated in FIG. 1 may be realized as an independent device. Moreover, each may be implemented as software that implements a function. In the present embodiment, each unit is realized by software.

  FIG. 2 is a diagram showing a basic configuration of a computer for realizing the functions of the respective units shown in FIG. 1 by executing software. The CPU 1001 mainly controls the operation of each component. The main memory 1002 stores a control program executed by the CPU 1001, and provides a work area when the CPU 1001 executes a program. The magnetic disk 1003 stores an operating system (OS), device drives of peripheral devices, various application software including a program for performing processing described later, and the like. The display memory 1004 temporarily stores display data. The monitor 1005 is, for example, a CRT monitor or a liquid crystal monitor, and displays an image or text based on data from the display memory 1004. The mouse 1006 and the keyboard 1007 perform pointing input and input of characters and the like by the user. The above components are communicably connected to each other by a common bus 1008.

  FIG. 3 shows a flowchart showing the processing procedure in the present embodiment. In the present embodiment, the CPU 1001 is realized by executing a program for realizing the functions of the respective units stored in the main memory 1002. In the following description, interpretation findings or clinical information names are represented by Ij (j = 1 to m), and m types of interpretation findings or clinical information names I1 to Im are handled. Also, k states that I j can take are denoted as S jk. The range of k has various values depending on Ij. In this embodiment, as an example, interpretation findings or clinical information as shown in FIG. 4 can be input or acquired, and further, each interpretation finding or clinical information takes a state as shown in FIG. Shall be possible. For example, the “shape” of I1 represents the shape of an abnormal shadow, and takes three states of state S11 “spherical”, state S12 “leaf-like”, and state S13 “irregular”. The "cut" of I2 represents the degree of cut in the abnormal shadow. In addition, Il "roll (bronchus)" represents the presence or absence of bronchial involvement in abnormal shadow. In addition, “previous” of Im indicates whether or not there is a history of a disease in the past.

  Also, in the following description, a set of states S jk is referred to as a set E. However, it is assumed that a plurality of states Sjk of one Ij do not exist simultaneously in one set E. For example, when I1 takes state S11, state S12, and state S13, and I2 takes state S21, state S22, state S23, and state S24, set E = {S11, S21} can be taken, but set E = {S11, S12} can not be taken. This is because one interpretation finding or clinical information takes only one state. Also, in the following description, a diagnostic name is written using a symbol D. In this embodiment, three diagnostic values are taken: primary lung cancer (denoted as D1), lung metastasis of cancer (denoted as D2), and others (denoted as D3). Further, the inference probability of the diagnostic name Dr (r = 1, 2, 3) when the set E is given as input information is denoted as P (Dr | E). Similarly, a subset of the set E is denoted by Ex, and the inference probability of the diagnostic name Dr when the subset Ex is given is denoted by P (Dr | Ex). Further, the influence of Ex on the diagnosis name Dr is denoted as I (Dr | Ex).

  In step S3000, the input information acquisition unit 102 acquires the input information on the abnormal shadow of the lungs input to the diagnosis support apparatus 100 and the data associated therewith. For example, in the acquired input information, I1 "shape": state S12 "leaf-like", I2 "cut": state S21 "strong", ..., I1 "roll (bronchus)": state S11 "presence", ..., Im "Previous": It is assumed that the state Sm2 is "none". In this case, the set E of the state S jk (that is, the input information) is E = {S 12, S 21,..., S 11,.

  In step S3010, the inference unit 104 infers the probability (inference result) that the abnormal shadow is a diagnostic name, based on the input information (that is, E) acquired in step S3000. As the inference means at this time, various existing inference methods such as Bayesian networks, neural networks, support vector machines, etc. can be used. In this embodiment, a Bayesian network is used as an inference means. The Bayesian network is an inference model that uses conditional probability, and it is possible to obtain the inference probability of each diagnosis when the input information is input (probability that the case is each diagnosis. Also called a posterior probability). is there. In the present embodiment, the inference probability for each of the diagnostic names D1, D2, and D3 of the abnormal shadow is acquired.

  In step S3020, the influence degree acquisition unit 106 acquires the influence degree using the input information acquired in step S3000 and the inference result acquired in step S3010. Specifically, a subset Ex of at least one set E (that is, input information) is obtained (that is, a subset of input information), and an influence degree indicating the degree of influence on each diagnostic name is obtained for each subset Ex . For example, in the case of E = {S12, S21, ..., Sl1, ..., Sm2} in the above-mentioned example, when acquiring the subset Ex in which the number of elements is 2, {S12, S21}, {S12, Sl1}, Ex such as {S21, Sm2} is acquired. In the present embodiment, it is assumed that all subsets Ex in which the number of elements is one are acquired. Therefore, in the above example, since m elements of E are included, m subsets Ex are obtained.

Then, the influence degree is acquired in each subset Ex. In this embodiment, the influence degree is calculated using the prior probability of each diagnosis and the inference probability when only Ex is input. In the present embodiment, the prior probability of each diagnosis corresponds to the probability of each diagnosis when there is no input. Then, for example, the influence I (Dr | Ex) of Ex on the diagnosis name Dr is calculated by the following equation.

  In the equation (1), when I (Dr | Ex) is positive, that is, when the posterior probability when only Ex is input is larger than the prior probability, it is determined that Ex has a positive influence on Dr. On the other hand, if it is negative, that is, if the posterior probability when only Ex is input is smaller than the prior probability, it is determined that Ex has a negative influence on Dr. In addition, the calculation method of the above influence degree is an example of the process in this embodiment, and is not limited to this.

  In step S3030, the selection unit 108 selects a subset based on the inference result acquired in step S3010 and the degree of influence acquired in step S3020. In the present embodiment, the selection unit 108 selects a subset according to the inference probability of the diagnostic having the highest inference probability and the threshold among the inference results. Specifically, when the highest inference probability is equal to or higher than a predetermined threshold, the selection unit 108 selects a subset that affirms the diagnosis having the highest inference probability. On the other hand, when the highest inference probability does not exceed the predetermined threshold, the selection unit 108 determines that the inference probability is low, and selects a subset that denies a diagnosis other than the diagnosis having the highest inference probability. Note that the above selection method is an example of processing in this embodiment, and is not limited to this.

  The process according to the present embodiment when the threshold value is 70.0% will be described in detail with reference to FIG. FIGS. 5A and 5B show the inference probability P (Dr | Ex) obtained by the process of step S3010 and the process of step S3020 when different input information (set E) is obtained. The degree of influence I (Dr | Ex) on each obtained diagnostic name is shown. In FIG. 5 (a), the diagnosis having the highest inference probability is D1 (ie, primary lung cancer), and its inference probability P (D1 | E) is 47.6%. In this case, since the inference probability P (D1 | E) does not exceed 70.0% of the threshold value, the selection unit 108 outputs information that denies D2 and D3 other than D1, that is, I (D2 | Ex), I (D3). Select the subset for which | Ex) is negative. In the present embodiment, the selection unit 108 selects Ex that takes the smallest value among the subsets Ex in which I (D2 | Ex) and I (D3 | Ex) are negative. Specifically, in the present embodiment, the selection unit 108 selects {Sm2} (= −13.8%) and {S43} (= −8.80) respectively.

  On the other hand, in FIG. 5 (b), the diagnosis having the highest inference probability is D2 (ie, lung metastasis of cancer), and the inference probability P (D2 | E) is 82.1%. In this case, since the inference probability P (D2 | E) exceeds 70.0% of the threshold value, the selection unit 108 selects information that makes D2 positive, that is, a subset in which I (D2 | Ex) is positive. In the present embodiment, the selection unit 108 selects Ex that takes the largest value among the subsets Ex in which I (D2 | Ex) is positive. Specifically, in the present embodiment, the selection unit 108 selects {S11} (= 10.4).

  In step S3040, the presentation unit 110 generates and displays information to be presented. Specifically, information to be presented is generated based on the input information and accompanying data acquired in step S3000, the inference result acquired in step S3010, and the information on the subset selected in step S3030. FIG. 6 shows an example of presentation information displayed on the monitor 1005 in the present embodiment when the inference result and the degree of influence shown in FIG. 5A are obtained. The presentation information 600 includes the representative image 6000 of the abnormal lung shadow acquired in step S3000 and the input information 6010 of the abnormal lung shadow. Also, the presentation information 600 includes the inference result 6020 inferred in step S3010. In the example shown in the figure, as the inference result 6020, an inference probability 6021 of the primary lung cancer in the inference result, an inference probability 6022 of lung metastasis of cancer, and other inference probabilities 6023 are displayed by a circle graph. In addition, the presented information 600 includes the diagnosis name (primary lung cancer in the example of the figure) and the probability 6030 (in the example of the figure) of the primary lung cancer of the cancer in the inference result. Inference probability). Further, the presentation information 600 includes support information 6040 selected by the process of step S6030.

  According to this embodiment, the method of selecting the support information is changed by considering the inference probability of the inference result. Specifically, when the inference probability of the target diagnostic name is high, the information for affirming the diagnostic name is selected, and when the inference probability is low, the information for negating other diagnostic names is selected. As a result, it becomes possible to present information similar to that in the case of interpretation by a doctor as support information. Therefore, information required by the doctor can be efficiently presented. In other words, according to the present embodiment, it is possible to efficiently present information required by the user because information according to the degree of confidence of the target diagnostic name is selected and presented.

[Modification 1]
In the present embodiment, in step S3030, the information is selected according to the inference probability of the diagnostic name having the highest inference probability and the threshold value. However, not only the inference probability of the highest diagnostic name but also the inference probabilities of other diagnostic names may be used as criteria for selection. For example, the information may be selected depending on whether the difference / ratio with the inference probability of a diagnostic having the second highest inference probability exceeds a predetermined threshold. Alternatively, a difference / ratio with an inference probability of a diagnostic having the lowest inference probability and a threshold may be used. Furthermore, the difference / ratio with the sum of the second to the Nth inference probabilities may be used, or the difference / ratio with the median of the inference probabilities of each diagnostic name may be used. According to this, since the information selection is dynamically performed, the information required by the doctor can be flexibly presented.

[Modification 2]
In the present embodiment, in step S3030, the information is selected according to the inference probability of the diagnostic name having the highest inference probability and the threshold value. However, the inference probabilities of diagnostic names having second and subsequent inference probabilities may be used as selection criteria. For example, information may be selected using the inference probability of a diagnostic having the lowest inference probability and a threshold.

[Modification 3]
In the present embodiment, in step S3030, the information is selected using the inference probability of the diagnostic name having the highest inference probability. However, instead of the diagnosis having the highest inference probability, the inference probability of the diagnosis identified by another method may be used. For example, the information may be selected according to the inference probability of the diagnosis designated by the doctor. According to this, since the information is selected for the diagnosis desired by the doctor, the information required by the doctor can be efficiently presented.

[Modification 4]
In step S3030, when selecting information that denies other than the target diagnosis, the information is selected by simultaneously using the influence of each diagnosis other than the diagnosis. However, information may be selected using the degree of influence of the target diagnostic name. Specifically, while affirming the subject diagnostic name, information may be selected which denies other diagnostic names. Moreover, you may select the information which negates two or more other than target diagnostic name simultaneously. According to this, since the information is selected using the influence degree with respect to a plurality of diagnostic names, it is possible to efficiently present the information that the doctor needs more.

[Modification 5]
In step S3030, when the threshold of the diagnostic name having the highest inference probability is exceeded, information which affirms the diagnostic name is presented, and when it does not exceed, information which denies other diagnostic names is presented. . However, other methods may be used. Specifically, when the threshold of the diagnostic name is exceeded, information may be presented that denies other diagnostic names, and when the threshold is not exceeded, information may be presented that affirms the diagnostic name.
According to this method, since the information is presented from the viewpoint of the opposite of the method usually performed by the doctor, it can be expected that the doctor uses the information as a reminder when making a diagnosis.

  As described above, according to the present embodiment, the inference probability for each diagnosis obtained from the interpretation findings and the clinical information included in the medical information, and the influence of each of the findings and the subset of the clinical information on the inference concerning the inference probability It is possible to provide appropriate support information based on the degree.

Other Embodiments
The present invention is also realized by executing the following processing. That is, software (program) for realizing the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU or the like) of the system or apparatus reads the program. It is a process to execute.

DESCRIPTION OF SYMBOLS 100 Diagnosis support apparatus, 102 input information acquisition part, 104 inference part, 106 influence degree acquisition part, 108 selection part, 110 presentation part, 200 information input terminal

Claims (13)

Reasoning means for acquiring inference probabilities of a plurality of diagnostic names corresponding to the case based on a plurality of medical information corresponding to the case;
Among the plurality of diagnostic names, when the inference probability of a target diagnostic name is lower than a predetermined criterion, the inference probability negatively affected the inference probability of a diagnostic name other than the target diagnostic name. Selection means for selecting medical information;
Display control means for displaying support information based on the selected medical information on a display unit;
A diagnostic support system characterized by having.   The selection means selects the medical information which positively influenced the inference probability of the target diagnosis when the inference probability of the target diagnosis is higher than a predetermined standard. The diagnosis support system according to claim 1, characterized in that   The selection means positively influences the inference probability of the target diagnosis when the inference probability of the target diagnosis is lower than a predetermined standard, and the target diagnosis name The diagnosis support system according to claim 1 or 2, wherein the medical information having a negative influence on the inference probability of other diagnosis names is selected. An influence degree acquiring unit that acquires the influence degree of the medical information indicating the degree of influence on the inference probability;
The diagnosis support system according to any one of claims 1 to 3, wherein the selection unit selects the medical information based on the degree of influence.   The diagnosis support system according to any one of claims 1 to 4, wherein the target diagnosis name is a diagnosis name having the highest inference probability among the plurality of diagnosis names.   The diagnosis support system according to any one of claims 1 to 4, wherein the target diagnosis name is a diagnosis name designated by a user among the plurality of diagnosis names.   The diagnosis support system according to any one of claims 1 to 6, wherein the predetermined reference is a threshold.   The diagnosis support system according to any one of claims 1 to 7, wherein the medical information is information including at least one of an interpretation finding and clinical information.   The diagnosis support system according to any one of claims 1 to 8, wherein the display control means causes the display unit to display the inference probability for each diagnostic name together with the support information. Reasoning means for acquiring inference probabilities of a plurality of diagnostic names corresponding to the case based on a plurality of medical information corresponding to the case;
Among the plurality of diagnostic names, when the inference probability of a target diagnostic name is lower than a predetermined criterion, the inference probability negatively affected the inference probability of a diagnostic name other than the target diagnostic name. Selection means for selecting medical information;
Display control means for displaying support information based on the selected medical information on a display unit;
A diagnostic support device characterized by having. A method of operating a diagnosis support system comprising an inference unit, a selection unit, and a presentation unit,
An inferring step in which the inference unit acquires inference probabilities of a plurality of diagnostic names corresponding to the case based on a plurality of medical information corresponding to the case;
Among the plurality of diagnostic names, the selection unit is negative to the inference probability of a diagnostic name other than the target diagnostic name when the inference probability of the target diagnostic name is lower than a predetermined reference. A selection step of selecting the affected medical information;
A display control step of causing the display unit to display support information based on the selected medical information, the presentation unit;
A method of operating a diagnostic support system, comprising: An operation method of a diagnosis support apparatus having an inference unit, a selection unit, and a presentation unit,
An inferring step in which the inference unit acquires inference probabilities of a plurality of diagnostic names corresponding to the case based on a plurality of medical information corresponding to the case;
Among the plurality of diagnostic names, the selection unit is negative to the inference probability of a diagnostic name other than the target diagnostic name when the inference probability of the target diagnostic name is lower than a predetermined reference. A selection step of selecting the affected medical information;
A display control step of causing the display unit to display support information based on the selected medical information, the presentation unit;
A method of operating a diagnosis support apparatus, comprising:   A program for causing a computer to execute each step of the operation method according to claim 11 or 12.

Images