JP2009082442A - Diagnosis support apparatus, its control method, program, and storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To efficiently refer to data relevant to an affected region. <P>SOLUTION: A diagnosis support apparatus includes: a medical inspection data input part for inputting medical inspection data based on the inspection result of a subject; an acquiring part for acquiring information about a lesion candidate based on the medical inspection data; a determining part for determining whether or not information indicating a medical importance degree to be obtained by weighting of the medical inspection data among pieces of the information about the lesion candidate becomes higher than a predetermined threshold; and a data output part for outputting data in response to the determination result, which indicates that the information indicating the medical importance degree becomes higher than the threshold. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a diagnosis support apparatus that contributes to improvement of diagnosis efficiency of a doctor by acquiring information related to a lesion site from a medical examination data and selectively presenting only information necessary for diagnosis.

  Various apparatuses including CT (Computed Tomography), MRI (Magnetic Resonance Imaging), and an ultrasonic diagnostic apparatus have been developed as apparatuses for acquiring information inside the human body. Medical image data acquired from these imaging devices is displayed on a monitor for interpretation, and a doctor reads a state of a lesioned part and a change with time from these data to make a diagnosis.

  With the advance of imaging technology, the types of medical images and the amount of data per case are steadily increasing, and a technology that contributes to reducing the burden of interpretation and improving diagnostic accuracy is desired. Computer Aided Diagnosis (CAD) automatically detects abnormal shadow candidates such as malignant tumors from the above-mentioned medical image data by computer-based image processing, reducing the burden of interpretation and improving diagnostic accuracy Contribute. The doctor makes a final diagnosis by referring to the diagnosis support information output by the CAD and comparing it with the result of his / her interpretation and examining the presence or absence of an oversight or a false detection.

It is necessary to present not only the detection results of abnormal shadow candidates but also the detection grounds at the same time in cases where the validity of the detection results by CAD is questioned, such as when differences in findings are seen between doctors and CAD. On the other hand, a technique for quantitatively presenting the degree of similarity and contribution as a basis for calculating the determination together with the result of determination by similar case search or neural network when performing a medical diagnosis by a computer is disclosed in, for example, Patent Document 1, 2 is disclosed.
JP 2004-288047 A JP 2006-043007 A

  However, in the techniques described in Patent Documents 1 and 2, when referring to information related to a lesion site output by the diagnosis support apparatus, it is complicated for the doctor to read all the information indicated by the diagnosis support apparatus. There was a problem of becoming. In particular, when the diagnosis support apparatus detects a plurality of types of lesions, this problem appears remarkably, which may cause a new burden on the interpretation doctor.

  An object of the present invention is to provide a diagnosis support technique that enables efficient reference to information related to a lesion site.

In order to solve the above problems, a diagnosis support apparatus according to the present invention includes a medical examination data input unit for inputting medical examination data based on a test result of a subject,
Acquiring means for acquiring information of lesion candidates based on the medical examination data;
Judgment means for judging whether information indicating medical importance obtained by weighting of the medical examination data among information on the lesion candidates is higher than a predetermined threshold;
According to the determination result of the determination means, data output means for outputting data in which information indicating the medical importance is higher than the threshold;
It is characterized by providing.

  According to the present invention, it is possible to efficiently refer to information related to a lesion site.

  Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings. However, the constituent elements described in this embodiment are merely examples, and the technical scope of the present invention is determined by the scope of claims, and is limited by the following individual embodiments. is not.

(First embodiment)
FIG. 1 is a diagram showing a configuration of a diagnosis support apparatus according to the first embodiment of the invention. The diagnosis support apparatus 1 includes a central processing unit (CPU) 100, a main memory 101, a magnetic disk 102, a display memory 103, a monitor 104, a mouse 105, and a keyboard 106. The diagnosis support apparatus 1 communicates with the medical examination data acquisition apparatus 2 via a network (LAN 4), and includes an X-ray CT apparatus, an MRI apparatus, an ultrasonic diagnosis apparatus, a simple X-ray imaging apparatus, an electrocardiograph, Data on the specimen can be acquired.

  The medical examination data acquisition apparatus 2 can be connected to the database 3 via a network (LAN 4) and store medical examination data.

  The central processing unit (CPU) 100 can control the overall operation of each component of the diagnosis support apparatus 1.

  The main memory 101 stores a control program for the diagnosis support apparatus 1 and functions as a work area when executing various applications including the control program. The magnetic disk 102 can store an operating system (OS), a device drive of a peripheral device, various application software including a program for performing diagnosis support processing described later, and the like. The display memory 103 can temporarily store display data. The monitor 104 is, for example, a CRT monitor, a liquid crystal monitor, or the like, and can display an image based on data from the display memory 103. The mouse 105 and the keyboard 106 can function as input means for performing pointing input and character input by the user. Each component described above is connected to each other by a common bus 107.

  The diagnosis support apparatus 1 can read medical examination data such as medical images from the database 3 via the LAN 4. It is also possible to connect a storage device such as an FDD, CD-RW drive, MO drive, ZIP drive or the like to the diagnosis support apparatus 1 and read medical examination data from these drives. It is also possible to acquire medical examination data directly from the medical examination data acquisition device 2 via the LAN 4.

  FIG. 2 is a diagram illustrating a functional configuration of the diagnosis support apparatus 1. The diagnosis support apparatus 1 includes a medical examination data input unit 201, a lesion candidate acquisition unit 202, a case database 203, a medical knowledge database 204, a determination unit 205, and a data output unit 206 as functional configurations.

(Medical examination data input part)
The medical examination data input unit 201 communicates with the medical examination data acquisition apparatus 2 or the database 3 via the network, and inputs (reads) medical examination data based on the examination result of the subject to the diagnosis support apparatus 1. Is possible. It is also possible to read medical examination data from various storage media including a storage device connected to the diagnosis support device 1, such as an FDD, CD-RW drive, MO drive, and ZIP drive. The medical examination data input unit 201 inputs medical image data based on the examination result of the subject from a medical examination apparatus such as an X-ray CT apparatus, an MR apparatus, an ultrasonic diagnosis support apparatus, and an electrocardiograph. Is also possible. In addition, the medical examination data input unit 201 is not limited to inputting medical image data, but numerical data such as electrocardiograms, electroencephalogram data and white blood cell counts, and text related to acquiring lesion candidates such as handwritten or digitized medical chart information It is also possible to input medical examination data including data.

(Lesion candidate acquisition unit)
The lesion candidate acquisition unit 202 acquires lesion candidate related data related to the subject based on the image / numerical value / text data input by the medical examination data input unit 201. For example, when performing lung cancer screening, the level candidate method is used as a method for acquiring a lesion candidate, and the lesion candidate acquiring unit 202 extracts an interpretation target organ such as a lung field. The lesion candidate acquisition unit 202 can acquire a nodule candidate by applying a minimum direction difference filter within the region or by calculating a three-dimensional curvature. The lesion candidate acquisition unit 202 refers to the case database 203 to compare the similarity with the past case data in the acquisition of the lesion candidate, or uses the diagnostic criteria and diagnostic procedure data stored in the medical knowledge database 204. Can be referred to.

(Case database)
The case database 203 stores medical image data taken by the medical examination data acquisition device 2, numerical data such as an electrocardiogram and a white blood cell count, and text data such as a medical record relating to a subject. The data stored in the case database 203 can also include the value of the data analysis result and the definitive diagnosis result by the diagnosis support apparatus 1, and the information can be used for similar case search.

  The case database 203 can be used not only by the determination unit 205 but also by the lesion candidate acquisition unit 202. The case database 203 is not limited to a configuration independent of the lesion candidate acquisition unit 202 and the determination unit 205, and is, for example, a configuration connected to the inside of the determination unit 205 or the lesion candidate acquisition unit 202 or via the LAN 4. May be.

(Medical knowledge database)
The medical knowledge database 204 stores diagnostic criteria including a lesion size and information on diseases related to a disease to be examined including metastatic lesions and complications. It is also possible to store data such as a diagnostic procedure such as a procedure for examining the presence or absence of a related disease when a primary lesion is detected.

  Similar to the case database 203, the medical knowledge database 204 can be used not only from the determination unit 205 but also from the lesion candidate acquisition unit 202. Further, the medical knowledge database 204 is not limited to a configuration independent of the lesion candidate acquisition unit 202 and the determination unit 205, and is connected, for example, inside the determination unit 205 or the lesion candidate acquisition unit 202 or via the LAN 4. It may be a configuration.

(Judgment part)
The determination unit 205 determines whether to output data (lesion candidate related data) related to the lesion candidate obtained by the lesion candidate acquisition unit 202 to the user.

  When determining whether or not to output lesion candidate related data, the determination unit 205 determines whether or not to output lesion candidate related data by comparing with various criteria including medical importance. Specific criteria for determining whether output is possible, including its medical importance, and a calculation method thereof will be described in detail later. The determination unit 205 can also use data in the case database 203 and the medical knowledge database 204 when determining whether or not to output candidate lesion related data.

(Data output part)
When the determination unit 205 determines to output lesion candidate related data, the data output unit 206 outputs lesion candidate related data based on the determination result. The data related to the lesion candidate includes data explaining the interpretation basis such as the feature amount of the medical image data used when acquiring the lesion candidate, the interpretation result of the similar case image, and data related to the medical treatment method such as diagnostic guidelines. Specific contents will be described later.

  Next, a specific processing procedure executed by the diagnosis support apparatus 1 will be described with reference to FIG. FIG. 3 is a flowchart for explaining the processing procedure of the diagnosis support apparatus 1 according to the first embodiment. This processing is executed by each functional component described in FIG. 2 under the overall control of the CPU 100. To do.

  In step S31, the medical examination data input unit 201 obtains medical examination data based on the examination result of the subject from the medical examination data acquisition apparatus 2 and the like and inputs the medical examination data to the diagnosis support apparatus 1. In addition, because the lesion detection criteria and the lesion detection procedure when acquiring lesion candidates differ depending on the purpose of the examination, it is also possible for a doctor to input information on the purpose of examination such as screening, detailed examination, and follow-up to the diagnosis support device in advance. is there. When information related to the examination purpose is included in the DICOM header of the medical examination data, the information may be read from the header, or examination order information may be acquired from a radiation information system (RIS).

  In step S32, the lesion candidate acquisition unit 202 acquires a lesion candidate based on the medical examination data input in step S31. At this time, information on the diagnostic criteria stored in the medical knowledge database 204 may be used, or similar case data that has already been diagnosed and stored in the case database 203 may be used. As a result of acquiring the lesion candidate, lesion candidate related data including the interpretation basis is obtained. The processing target of the lesion candidate acquisition unit 202 is not limited to medical image data. For example, measurement data or medical record data other than the image related to the subject is a processing target, and a lesion candidate can be acquired based on the data. It is.

  In step S33, the determination unit 205 causes the user to present only data that has been determined that the information indicating the medical importance obtained by weighting is higher than the threshold among the lesion candidate related data acquired by the lesion candidate acquisition unit 202. Here, the information I indicating the medical importance calculated by the determination unit 205 will be described. Information I indicating medical importance can be defined as follows.

I = A * B * C
However,
A: Critical illness (relative severity among different diseases)
B: Progression (stage) (severity within the same disease)
C: Related lesion degree
And

  For example, when a plurality of types of diseases are detected in the lesion candidate acquisition unit 202, the related lesion degree C for each lesion is set according to the examination purpose as follows. That is,

It becomes. If the flag indicating whether data can be output is F,

It can be expressed as.

For T _I , for example,

As described above, an appropriate value may be set according to the sensitivity of the inspection, and is not necessarily limited to the above value.

For _TAB , even if it is not the disease to be examined or its related disease, if it is a serious lesion or the progression of the lesion is higher than the threshold, data related to the lesion candidate is output. Show. In this embodiment, T _AB = 50 is set, but it is not necessarily limited to this value.

Here, examples of the important disease degree A, the progression degree B, and the related lesion degree C are shown in FIG. For example, in the case of follow-up of lung cancer, the lesion candidate acquisition unit 202 detects one malignant tumor (stage I) in the lung field and one mediastinal lymph node with a minor axis of 1.2 cm, and the thoracic aorta diameter is 4 cm. When there, the information I _c indicating the medical importance regarding malignancy,
I _c = 10 * 4 * 1 = 40> 20 (= T _I )
Thus, the data output propriety flag F _c regarding the malignant tumor is set to 1. Information I _ln indicating the medical importance of mediastinal lymphadenopathy is
I _ln = 10 * 10 * 0.5 = 50> 20 (= T _I )
Thus, the data output enable / disable flag _Fln regarding the mediastinal lymphadenopathy is set to 1. Furthermore, the information I _a4 indicating the medical importance regarding the thoracic aortic aneurysm is
I _a4 = 8 * 2 * 0 = 0 <20 (= T _I )
Thus, the data output permission flag F _a4 regarding the thoracic aortic aneurysm is set to 0.

When the thoracic aorta diameter is 8 cm, the data output availability flag F _a8 is C _a8 = 0 and A _a8 * B _a8 = 8 * 8> 50 (= T _AB ), so F _a8 = 1. . In other words, although it is not the original lesion to be examined, the data on the thoracic aortic aneurysm is output because the progress of the lesion is higher than the threshold. It should be noted that the information indicating the medical importance described here is merely an example, and it is needless to say that the information is not limited to the numerical example shown in FIG.

  When it is determined by the determination in step S33 that the information indicating the medical importance is not higher than the threshold (S33-NO), the process is terminated. On the other hand, if it is determined in S33 that the information indicating the medical importance is higher than the threshold (S33-Yes), the process proceeds to Step S34.

  In step S34, the determination unit 205 determines the type of lesion candidate related data to be output to the data output unit 206. Data related to lesion candidates include data such as image feature values indicating the basis of interpretation results, measured numerical values and patient attributes, or calculation results obtained by classifiers using these as input. The determination unit 205 determines what type of data.

  However, the type of data to be output is not necessarily limited to the interpretation basis, and may be, for example, reference case data such as similar cases, or data related to a medical method such as medical guidelines. Further, the data type to be output can be set in advance by the user.

  In step S35, the data output unit 206 outputs the lesion candidate related data determined to be output in the previous steps S33 and S34. Here, the data output destination includes paper, a storage device such as a memory and a hard disk, and a display device such as a monitor.

  FIG. 5 is a diagram illustrating an output example of lesion candidate related data. A mark 503 indicating a lesion candidate is displayed on the medical examination data (FIG. 5A), and an image feature amount and patient attribute / time-change data as a basis of the detection result are displayed next to the mark 503 (FIG. 5). 5 (b)). When the lesion candidate related data is output to a display device such as a monitor, it may be displayed in a pop-up format or in a separate window.

  As described above, according to the present embodiment, the doctor outputs the data related to the lesion candidate only when the information indicating the medical importance is higher than the threshold, so that the doctor relates to the lesion site output by the diagnosis support apparatus. Information can be referred to efficiently.

(Second Embodiment)
In the first embodiment, as a specific process of the determination unit 205, a configuration has been described in which whether or not to output lesion candidate related data is determined according to information indicating medical importance. However, the gist of the present invention is not limited to this example. For example, as a process of the determination unit 205, a configuration in which the determination unit 205 outputs lesion candidate related data when there is a difference (difference) between the lesion candidate related data and a report indicating a doctor's interpretation result will be described. . FIG. 6 is a diagram showing a functional configuration of the diagnosis support apparatus 61 according to the second embodiment. The same functional configuration as that of the diagnosis support apparatus 1 according to the first embodiment is denoted by the same reference numeral. Description is omitted.

  The report input unit 207 functions as a diagnosis result input unit, and inputs information (interpretation report) indicating a diagnosis result read by the doctor based on the medical examination data to the diagnosis support apparatus 1. For example, the report input unit 207 can input interpretation report data to the diagnosis support apparatus 61 via a network from a database storing interpretation reports created by a doctor who has performed interpretation. Further, data is read from various storage media (storage means) connected to the diagnosis support apparatus 1, for example, FDD, CD-RW drive, MO drive, and ZIP drive, and the data of the interpretation report is read by the diagnosis support apparatus 61. Can also be entered.

  The report input unit 207 can also input interpretation report data indicating the interpretation result directly to the diagnosis support apparatus 61 by a doctor who has performed interpretation using a keyboard or a mouse.

  Furthermore, the report input unit 207 can also input the interpretation result to the diagnosis support apparatus 61 via a predetermined format. The standard format has items and options for inputting the result of interpretation, and the doctor who performed the interpretation performs input according to the input to the item or selection of the option. Is input. Alternatively, the report input unit 207 is connected to a reading device including a scanner or an optical character recognition device so that a sentence written by a doctor who has performed interpretation can be input to the diagnosis support device 61 in a format that can be edited by a computer. Is also possible.

  The report analysis unit 208 analyzes the interpretation result by the doctor input by the report input unit 207, and analyzes the medical meaning. For example, the report analysis unit 208 includes a morphological analysis unit 701, a class specifying unit 702, and a meaning specifying unit 704 as shown in FIG. 7, and includes a structuring dictionary 703 and a medical thesaurus dictionary 705 for specifying a class. Prepare. The morphological analysis unit 701, the class specifying unit 702, the structuring dictionary 703, the meaning specifying unit 704, and the medical thesaurus dictionary 705 function as text analysis means.

  The morpheme analysis unit 701 divides an interpretation report described in a natural sentence into morphemes (the smallest unit having meaning in a language column). The structuring dictionary 703 is a dictionary in which medical words and classes are registered. Types of classes registered in the structuring dictionary 703 include “part”, “disease name”, and the like.

  The class specifying unit 702 uses the structuring dictionary 703 to specify the class of words obtained by the morphological analysis unit 701, and generates structured data for the interpretation report. By referring to the medical thesaurus dictionary 705, the semantic identification unit 704 has an ontology that describes the relationship between medical-related words, conceptually upper words are positioned higher in the hierarchical structure, and conceptually lower words are Organize words hierarchically so that they are located at the bottom. The meaning identification unit 704 refers to the medical thesaurus dictionary 705 to determine a thesaurus code that represents the hierarchical position of words included in the structured data of the report. Further, in the case of another configuration in which the report input unit 207 inputs the contents of the interpretation report based on the word selected from the options, the report analysis unit 208 is not limited to the configuration shown in FIG. For example, the report analysis unit 208 can be configured by providing the report input unit 207 with a thesaurus dictionary regarding words prepared as options in advance and means for collating the dictionary.

  Next, a specific processing procedure executed by the diagnosis support apparatus 61 will be described with reference to FIG. FIG. 8 is a flowchart for explaining the processing procedure of the diagnosis support apparatus 61 according to the second embodiment. This processing is performed by each functional component described in FIGS. 6 and 7 under the overall control of the CPU 100. Execute the process.

  In step S81, the medical examination data input unit 201 obtains medical examination data based on the examination result of the subject from the medical examination data acquisition apparatus 2 and the like and inputs the medical examination data to the diagnosis support apparatus 1. The details of this process are the same as in step S31 of the first embodiment, and a description thereof will be omitted.

  In step S82, the lesion candidate acquisition unit 202 acquires a lesion candidate based on the medical examination data input in step S81. The details of this process are the same as in step S32 of the first embodiment, and a description thereof will be omitted.

  In step S83, the CPU 100 checks whether or not the interpretation report data is input to the report input unit 207. If interpretation report data based on the diagnosis result is input (S83-Yes), the process proceeds to step S84, and if no report data is input (S83-No), the process proceeds to step S85. As information based on the diagnosis result, the interpretation report data includes at least one of a doctor's diagnosis result, a diagnosis result by the measuring device, or an image, text, or numerical data that has been analyzed by the diagnosis support device.

  In step S84, the report analysis unit 208 performs morphological analysis, class specification, and meaning specification, and generates finding data 901 indicating a diagnosis result as shown in FIG. The finding data 901 includes data related to the site, lesion type, size, state, and findings. Then, the report analysis unit 208 detects a difference (difference) between the observation data 901 based on the input interpretation report and the lesion candidate related data obtained by the lesion candidate acquisition unit 202.

In step S85, for the difference between the findings data 901 obtained in step S84 and the lesion candidate related data obtained by the lesion candidate acquisition unit 202, the determination unit 205 calculates information I _diff indicating medical importance. .

For example, I _diff can be determined as follows:

However, A _doc : Critical illness in the findings by doctors
B _doc : Progression level (stage) in findings data by doctor
C _doc : Degree of related lesions in findings data by doctor
A _cad : Critical disease degree calculated by the lesion candidate acquisition unit 202
B _cad : degree of progression (stage) calculated by the candidate lesion acquisition unit 202
C _cad : related lesion degree calculated by the lesion candidate acquisition unit 202 For example, if the findings by the doctor are benign tumors in the lung field and the data obtained by the lesion candidate acquisition unit 202 is stage I lung cancer, it is medically important Information I _diff indicating the degree is obtained as follows.

  The information indicating the medical importance described here is merely an example, and is not limited to the definition in the present embodiment.

In step S86, when the information indicating the medical importance obtained in step S85 is higher than a predetermined threshold value, the determination unit 205 sets the data output permission flag F _diff to 1 and proceeds to step S87. If the information indicating the medical importance is lower than the threshold value, the data output enable / disable flag _Fdiff is set to 0, and the processing of the determination unit 205 is terminated without outputting the data related to the lesion candidate to the data output unit 206. .

In this embodiment, since the calculation result of Formula 5 is I _diff > 20, the data output enable / disable flag F _diff = 1.

  In step S87, the determination unit 205 determines the type of lesion candidate related data to be output to the data output unit 206. Data related to lesion candidates include data such as image feature values indicating the basis of interpretation results, measured numerical values and patient attributes, or calculation results obtained by classifiers using these as input. The determination unit 205 determines what type of data. The outputted lesion candidate related data is not necessarily limited to the interpretation basis. For example, it may be reference case data such as a similar case, data related to a medical treatment method such as medical guidelines, or data related to report creation support such as a report correction candidate.

In step S88, when the data output enable / disable flag _Fdiff is set to 1 in step S86, the data output unit 206 outputs data relating to the lesion candidate determined in step S87 (lesion candidate related data). In the case of this embodiment, since the output propriety flag F _diff = 1 based on the calculation result of Formula 5, data related to a lesion candidate detected as lung cancer is output. For example, when the finding data 901 shown in FIG. 9 is obtained (FIG. 9A), the data output unit 206 outputs the image feature amount and the patient attribute / time-change data as an image as the basis of interpretation. Based on the output of the data output unit 206, the monitor 104 displays image feature amounts and patient attribute / time-change data 902 as images that are the basis of interpretation (FIG. 9B).

  When there is a difference between the interpretation report and the acquired lesion candidate, if the information indicating the medical importance is higher than the threshold, the lesion candidate related data is output, so that the doctor efficiently It becomes possible to refer.

(Third embodiment)
In the first embodiment, as a specific process of the determination unit 205, a configuration has been described in which whether or not to output lesion candidate related data is determined according to information indicating medical importance. In the second embodiment, the configuration in which the determination unit 205 outputs the lesion candidate related data when there is a difference (difference) between the lesion candidate related data and the report indicating the doctor's interpretation result has been described. However, the gist of the present invention is not limited to this example. For example, as a process of the determination unit 205, a configuration in which lesion candidate related data is output when a doctor directly designates the position of a specific lesion candidate and the type of data to be output will be described.

  FIG. 10 is a diagram illustrating a functional configuration of the diagnosis support apparatus 1001 according to the third embodiment, which is the same as the functional configuration of the diagnosis support apparatus 1 according to the first embodiment and the diagnosis support apparatus 61 according to the second embodiment. Functional configurations are denoted by the same reference numerals, and description thereof is omitted.

  In the present embodiment, the determination unit 205 includes a comparison unit 209 that compares the analysis result of the report analysis unit 208 and the information on the lesion candidate acquired by the lesion candidate acquisition unit 202, and the comparison unit 209 is different from the two. (Difference) is obtained. In addition, the determination unit 205 includes a designation unit 210 that accepts designation of a lesion position and data type that the doctor wants to output. The designation unit 210 includes a position designation unit 211 that designates a lesion position to which a doctor wants to output lesion candidate related data, and a data type designation unit 212 that designates the type of lesion candidate related data to be output.

  Next, a specific processing procedure executed by the diagnosis support apparatus 1001 will be described with reference to FIG. FIG. 11 is a flowchart for explaining the processing procedure of the diagnosis support apparatus 1001 according to the third embodiment. This processing is executed by each functional component described with reference to FIG. 10 under the overall control of the CPU 100. To do.

  In step S111, the medical examination data input unit 201 obtains medical examination data based on the examination result of the subject from the medical examination data acquisition apparatus 2 and the like, and inputs the medical examination data to the diagnosis support apparatus 1. The details of this process are the same as in step S31 of the first embodiment, and a detailed description thereof will be omitted.

  In step S112, the lesion candidate acquisition unit 202 acquires a lesion candidate based on the medical examination data input in step S111. The details of this process are the same as in step S32 of the first embodiment, and a detailed description thereof will be omitted.

  In step S113, the CPU 100 checks whether or not the interpretation report data is input to the report input unit 207. If interpretation report data is input (S113-Yes), the process proceeds to step S114. If report data is not input (S113-No), the process proceeds to step S115.

  In step S114, the report analysis unit 208 performs morphological analysis, class specification, and meaning specification. FIG. 12 is a diagram illustrating an output example of lesion candidate related data. A mark 1201 indicating a lesion candidate is displayed on the medical examination data, and finding data 1202 is generated by processing of the report analysis unit 208. The finding data 1202 includes data related to the site, lesion type, size, state, and findings. Then, the comparison unit 209 compares the finding data 1202 based on the input interpretation report with the lesion candidate related data obtained by the lesion candidate acquisition unit 202, and detects a difference (difference).

In step S115, for the difference between the findings data 901 obtained in step S114 and the lesion candidate related data obtained by the lesion candidate acquisition unit 202, the determination unit 205 calculates information I _diff indicating medical importance. .

  In step S116, when the doctor wants to refer to data related to a specific lesion candidate, the lesion candidate to be referred to and the type of data to be referred to for the lesion candidate are designated. The designated lesion position is input to the position specifying unit 211, and the specified data type is input to the data type specifying unit 212, and what type of data is output for which lesion is determined.

  For example, as shown in FIG. 12, when the findings by the doctor (pneumonia) and the lesion name (benign tumor) by the lesion candidate acquisition unit 202 are different, data based on the processing of the determination unit 205 and the operation input of an input device such as a mouse The output unit 206 controls data output. Based on the data output of the data output unit 206, the screen displayed on the monitor 104 is controlled. In this case, the data output unit 206 functions as a display control unit.

  By the mouse over (first operation), interpretation interpretation information 1203 indicating the diagnosis result based on the medical examination data is displayed on the monitor 104 (display means).

  By left-clicking the mouse (second operation), the case with the maximum similarity is displayed (screen 1204). When the left click is performed, cases having the second or lower similarity are displayed on the monitor 104 (display means) (screen 1205). By repeating the left click operation, cases having similarities of the second and lower ranks are sequentially displayed.

  By right-clicking the mouse (third operation), correction candidates for the diagnosis result (report correction candidates) are displayed, and a message asking whether or not to adopt the correction candidates is displayed on the screen. When the OK button is pressed, a screen 1206 in which the contents of the diagnosis result are corrected is displayed on the monitor 104 (display means). When the user (doctor) designates switching of data to be displayed by operating an input unit such as a mouse, the data output unit 206 can control data output.

  In step S117, the data output unit 206, based on the calculation result of information indicating medical importance (S115) and the designation of the lesion position and data type (S116), data related to the lesion candidate (lesion candidate related data). Is output.

  In step S118, it is further checked whether the user has designated a lesion candidate / data type. If there is further designation (S118-Yes), the process returns to step S116, and the same process is repeated. On the other hand, when the lesion candidate / data type is not designated by the user (S118-No), the process is terminated.

  By outputting the related data to the lesion site by specifying the lesion position and data type specified by the doctor, the doctor can efficiently refer to the information related to the lesion site output by the diagnosis support apparatus.

(Other embodiments)
Note that it is needless to say that the object of the present invention can also be achieved by supplying a computer-readable storage medium that records a software program for realizing the functions of the above-described embodiments to a system or apparatus. Needless to say, this can also be achieved by the computer (or CPU or MPU) of the system or apparatus reading and executing the program stored in the storage medium.

  In this case, the program itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program constitutes the present invention.

  As a storage medium for supplying the program, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a nonvolatile memory card, a ROM, or the like can be used.

  Further, the functions of the above-described embodiments are realized by executing the program read by the computer. In addition, it is also included that an OS (operating system) or the like running on a computer performs part or all of actual processing based on a program instruction, and the above-described embodiment is realized by the processing. Needless to say.

It is a figure which shows the structure of the diagnosis assistance apparatus concerning 1st Embodiment. It is a figure explaining the functional structure of the diagnosis assistance apparatus concerning 1st Embodiment. It is a flowchart explaining the process sequence of the diagnosis assistance apparatus concerning 1st Embodiment. It is a figure which illustrates the data stored in a medical knowledge database. It is a figure which shows the information relevant to the lesion candidate output from the data output part of the diagnosis assistance apparatus concerning 1st Embodiment exemplarily. It is a figure which shows the function structure of the diagnostic assistance apparatus concerning 2nd Embodiment. It is a figure which shows the function structure of the text analysis part of the diagnostic assistance apparatus concerning 2nd Embodiment. It is a flowchart explaining the process sequence of the diagnosis assistance apparatus concerning 2nd Embodiment. It is a figure which shows the information relevant to the lesion candidate output from the data output part of the diagnosis assistance apparatus concerning 2nd Example illustratively. It is a figure which shows the function structure of the diagnostic assistance apparatus concerning 3rd Embodiment. It is a flowchart explaining the process sequence of the diagnosis assistance apparatus concerning 3rd Embodiment. It is a figure which shows the information relevant to the lesion candidate output from the data output part of the diagnosis assistance apparatus which concerns on 3rd Embodiment exemplarily.

Explanation of symbols

1 Diagnosis support device
2 Medical examination data acquisition device
3 Database
4 LAN
100 CPU
101 Main memory
102 magnetic disk
103 Display memory
104 Monitor
105 mice
106 keyboard
201 Medical examination data input part
202 Lesion candidate acquisition unit
203 Case Database
204 Medical Knowledge Database
205 Judgment part
206 Data output section
207 Report input section
208 Report Analysis Department
209 Comparison part
210 Designated part
211 Position specification part
212 Data type specification part

Claims (18)

Medical test data input means for inputting medical test data based on the test result of the subject;
Acquiring means for acquiring information of lesion candidates based on the medical examination data;
Judgment means for judging whether information indicating medical importance obtained by weighting of the medical examination data among information on the lesion candidates is higher than a predetermined threshold;
According to the determination result of the determination means, data output means for outputting data in which information indicating the medical importance is higher than the threshold;
A diagnostic support apparatus comprising:   The acquiring means refers to at least one of a medical knowledge database storing diagnostic criteria information and a case database storing similar case data when acquiring information on the lesion candidate. The diagnosis support apparatus according to claim 1. The medical examination data input means is capable of inputting at least one of medical image data, numerical data, and text data inputted from a medical examination apparatus that examines the subject.
The diagnosis support apparatus according to claim 1 or 2, wherein the acquisition unit acquires information on the lesion candidate based on data input by the medical examination data input unit. Diagnostic result input means for inputting diagnostic result information based on the medical examination data;
The diagnosis support apparatus according to claim 1, further comprising: an analysis unit that analyzes information on the diagnosis result input by the diagnosis result input unit. The determination unit obtains a difference between the analysis result of the analysis unit and the information of the lesion candidate acquired by the acquisition unit,
The diagnosis support apparatus according to claim 4, wherein it is determined whether or not information indicating medical importance obtained based on weighting for the difference result is higher than a predetermined threshold value.   The diagnosis support apparatus according to claim 4, wherein the analysis unit includes a text analysis unit that analyzes text data included in the diagnosis result information. It further has a designation means for accepting designation of a lesion candidate to be referred to,
The determination means determines whether or not information indicating medical importance for the lesion candidate specified by the specification means is higher than the threshold value;
The diagnosis support apparatus according to claim 1, wherein the data output unit outputs data that is higher than the threshold value for the designated lesion candidate based on a determination result of the determination unit.   Based on an operation input, the data output means controls data output for displaying at least one of information indicating a diagnosis result, display of similar cases, and correction candidates of the diagnosis result on the display means, The diagnosis support apparatus according to claim 1. Medical examination data input means for inputting medical examination data based on the examination result of the subject;
An acquisition step of acquiring information on candidate lesions based on the medical examination data;
A determination step of determining whether information indicating medical importance obtained by weighting of the medical examination data among information on the lesion candidates is higher than a predetermined threshold;
A data output step in which data output means outputs data in which the information indicating the medical importance is higher than the threshold according to the determination result in the determination step;
A diagnostic support apparatus control method comprising:   In the acquisition step, when acquiring information on the lesion candidate, at least one of a medical knowledge database storing diagnostic criteria information and a case database storing similar case data is referred to. A method for controlling a diagnosis support apparatus according to claim 9. In the medical examination data input step, it is possible to input at least one of medical image data, numerical data, and text data inputted from a medical examination apparatus that examines the subject.
The method of controlling a diagnosis support apparatus according to claim 9 or 10, wherein in the acquisition step, information on the lesion candidate is acquired based on the data input in the medical examination data input step. A diagnostic result input step, wherein the diagnostic result input means inputs information of a diagnostic result based on the medical examination data;
The method for controlling the diagnosis support apparatus according to claim 9, further comprising: an analysis step in which the analysis unit analyzes information on the diagnosis result input in the diagnosis result input step.   In the determination step, a difference between the analysis result of the analysis step and the information on the lesion candidate acquired in the acquisition step is obtained, and information indicating medical importance obtained based on weighting on the result of the difference is stored in advance. 13. The method of controlling a diagnosis support apparatus according to claim 12, wherein it is determined whether or not the threshold value is higher than a predetermined threshold value.   The method for controlling a diagnosis support apparatus according to claim 12, wherein the analysis step includes a text analysis step of analyzing text data included in the information of the diagnosis result. The analysis step includes a designation step for accepting designation of a lesion candidate to be referred to,
In the determining step, it is determined whether or not information indicating medical importance for the lesion candidate specified in the specifying step is higher than the threshold.
13. The diagnosis support apparatus control according to claim 12, wherein, in the data output step, data that is higher than the threshold value is output for the designated lesion candidate based on a determination result of the determination step. Method.   Based on an operation input, the data output step controls data output for displaying at least one of information indicating a diagnosis result, display of similar cases, and correction candidates of the diagnosis result on a display means, A method for controlling a diagnosis support apparatus according to claim 9.   A program for causing a computer to execute the method for controlling the diagnosis support apparatus according to any one of claims 9 to 16.   A computer-readable storage medium storing the program according to claim 17.

Images