JP2023012088A - Medical support system and medical support method - Google Patents

Abstract

To reduce oversight of disease in medical image diagnosis.SOLUTION: A diagnosis support system includes an evaluation unit and a determination unit. The evaluation unit evaluates provability of disease on the basis of medical images of a subject. The determination unit determines pursuit processing for re-evaluating the provability of disease in accordance with an evaluation result by the determination unit.SELECTED DRAWING: Figure 1

Description

The embodiments disclosed in this specification and drawings relate to a medical support system and a medical support method.

In emergency medicine, it is important to focus on imaging findings of fatal disease. However, the number of radiologists is small compared to the number of imaging examinations that can be performed, and the shortage of radiologists is becoming a serious problem. For this reason, as a method to support the diagnosis of doctors in emergency medical care at night, a consultation service that asks radiologists in remote areas such as overseas to interpret radiograms, and computer-aided diagnosis (CAD) are available. An image diagnosis support system that utilizes this technique is known. CAD uses the input medical image to calculate the degree of suspicion of a specific disease (hereinafter referred to as the degree of certainty). The diagnostic imaging support system can prioritize patients by comparing the calculated degrees of certainty among a plurality of patients.

However, even when it is determined that there is no evidence of a fatal disease as a result of using CAD, there are cases where the suspicion of a fatal disease cannot be completely denied. In this case, if diagnosis is made using only the diagnostic results of CAD using inspection images, there is a risk of overlooking a fatal disease.

JP 2020-86730 A

One of the problems to be solved by the embodiments disclosed in the specification and drawings is to reduce the oversight of diseases in diagnosis of medical images. However, the problems to be solved by the embodiments disclosed in this specification and drawings are not limited to the above problems. A problem corresponding to each effect of each configuration shown in the embodiments described later can be positioned as another problem.

A medical support system according to an embodiment includes an evaluation unit and a determination unit. The evaluation unit evaluates the possibility of disease based on the medical image of the subject. The determination unit determines a follow-up process for re-evaluating the possibility of the disease according to the evaluation result by the evaluation unit.

FIG. 1 is a diagram showing an example of the configuration of a diagnosis support system according to the first embodiment. FIG. 2 is a flowchart illustrating a processing procedure of diagnostic support processing by the diagnostic support system according to the first embodiment. FIG. 3 is a diagram showing an example of a diagnostic support screen displayed by the diagnostic support system according to the first embodiment. FIG. 4 is a correspondence table used for diagnostic support processing by the diagnostic support system according to the first embodiment. FIG. 5 is a diagram showing an example of a diagnostic support screen displayed by the diagnostic support system according to the first embodiment. FIG. 6 is a diagram showing an example of a diagnostic support screen displayed by the diagnostic support system according to the first embodiment. FIG. 7 is a diagram showing an example of a diagnostic support screen displayed by the diagnostic support system according to the first modification of the first embodiment. FIG. 8 is a diagram showing an example of the configuration of a diagnostic support system according to the second embodiment.

Hereinafter, embodiments of a medical support system will be described in detail with reference to the drawings. In the following description, components having substantially the same functions and configurations are denoted by the same reference numerals, and redundant description will be given only when necessary. Also, in the following description, the diagnostic support system is an example of a medical support system.

(First embodiment)
FIG. 1 is a diagram showing the configuration of a diagnosis support system 100. As shown in FIG. The diagnosis support system 100 includes a hospital information system (hereinafter referred to as HIS) 300, a medical image diagnostic apparatus 400, and a radiological department information management system (hereinafter referred to as RIS) through a network 200. 500.

The network 200 is, for example, a LAN (Local Area Network). The connection to the network 200 may be wired connection or wireless connection. Also, the line to be connected is not limited to a LAN as long as security is ensured by a VPN (Virtual Private Network) or the like. It may be connected to a public communication line such as the Internet.

The HIS 300 manages, for example, information related to medical facilities such as hospitals. In the HIS 300, electronic medical records (EMR), personal health records (PHR), etc. are recorded in a storage device. The HIS 300 records patient information, medical images, and the like. The patient information includes the patient's name, sex, age, nationality, medical history, information on examinations, examination results, and the like.

The medical image diagnostic apparatus 400 is, for example, an X-ray computed tomography (CT) apparatus, a magnetic resonance imaging (MRI) apparatus, an ultrasonic diagnostic apparatus, an X-ray diagnostic apparatus, or the like.
The RIS 500 is a system that manages examination reservation information related to radiation examination work. For example, the RIS 500 adds various setting information to examination order information input by a user in an order system included in the HIS 300, accumulates the information, and manages the accumulated information as examination reservation information. The RIS 500 transmits the examination order to the medical image diagnostic apparatus 400 according to the examination appointment information. The RIS 500 also transmits, as part of the electronic medical record (EMR) contained in the HIS 300, test execution information generated by the medical imaging apparatus 400 as a result of the test being performed.

The diagnosis support system 100 can transmit and receive various information to and from the HIS 300 , the medical image diagnostic apparatus 400 and the RIS 500 via the network 200 . The diagnosis support system 100 calculates the degree of certainty of a fatal disease by executing computer-aided diagnosis (hereinafter referred to as CAD) on medical images of a subject, and calculates determines the post-stage work to be executed next, and presents or executes the decided post-stage work.

Confidence is a value indicating the degree of suspicion of a specific disease, and is represented by a numerical value within the range of 0 to 1, for example.

Subsequent tasks are processes or tasks that re-evaluate the likelihood of a fatal disease. Post-processing is an example of pursuit processing. In other words, a pursuit process is a process that seeks out the possibility of a disease. The post-stage work includes, for example, image generation processing applied to CAD, proposal of an additional examination order, and transmission of an image interpretation request by a remote image interpretation doctor. The post-stage work is preset based on typical findings and pitfalls associated with the disease.

A diagnosis support system 100 includes a diagnosis support device 10 . The diagnosis support device 10 has a memory 11 , a communication interface 12 , a display 13 , an input interface 14 and a processing circuit 15 . Although the diagnostic support apparatus 10 is described below as a single apparatus that performs a plurality of functions, the plurality of functions may be performed by separate apparatuses. For example, each function executed by the diagnosis support device 10 may be distributed and installed in different console devices or workstation devices.

The memory 11 is a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an integrated circuit that stores various information. Moreover, the memory 11 may be a portable storage medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a flash memory, or the like, in addition to an HDD, an SSD, or the like. Note that the memory 11 may be a driving device that reads and writes various information with semiconductor memory elements such as flash memory and RAM (Random Access Memory). Moreover, the storage area of the memory 11 may be in the diagnosis support apparatus 10 or in an external storage device connected via a network.

The memory 11 stores a program executed by the processing circuit 15, various data used for processing of the processing circuit 15, and the like. As the program, for example, a program that is installed in the computer in advance from a network or a non-transitory computer-readable storage medium and causes the computer to implement each function of the processing circuit 15 is used. Various data handled in this specification are typically digital data. The memory 11 is an example of a storage unit.

The communication interface 12 is a network interface that controls transmission of communication with the medical image diagnostic apparatus 400, the HIS 300, and other external devices via the network 200. FIG.

The display 13 displays various information. For example, the display 13 outputs medical information generated by the processing circuit 15, a GUI (Graphical User Interface) for accepting various operations from the operator, and the like. For example, the display 13 is a liquid crystal display or a CRT (Cathode Ray Tube) display. The display 13 is an example of a display section.

The input interface 14 receives various input operations from the operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 15 . For example, the input interface 14 receives input of medical information, input of various command signals, and the like from the operator. The input interface 14 includes a mouse, a keyboard, a trackball, switch buttons, a touch screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, and the like. and an audio input circuit or the like. The input interface 14 is connected to the processing circuit 15, converts an input operation received from an operator into an electrical signal, and outputs the electrical signal to the control circuit. In this specification, the input interface is not limited to those having physical operation components such as a mouse and keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the processing circuit 15 is also included in the input interface. The input interface 14 is an example of an input unit.

The processing circuit 15 controls the operation of the diagnostic support device 10 as a whole. The processing circuit 15 is a processor that executes a reconstruction function 151 , an evaluation function 152 , a determination function 153 , a notification function 154 , a display control function 155 and an update function 156 by calling and executing programs in the memory 11 . In FIG. 1, it is assumed that the single processing circuit 15 realizes the reconstruction function 151, the evaluation function 152, the determination function 153, the notification function 154, the display control function 155, and the update function 156. A processing circuit may be configured by combining a plurality of independent processors, and each function may be realized by each processor executing a program. Further, the reconfiguration function 151, the evaluation function 152, the decision function 153, the notification function 154, the display control function 155 and the update function 156 may each be implemented as separate hardware circuits. The above description of each function executed by the processing circuit 15 is the same for each of the following embodiments and modifications.

Further, although the diagnostic support device 10 is described as performing multiple functions on a single console, separate devices may perform the multiple functions. For example, the functions of the processing circuit 15 may be distributed and installed in different devices.

The term "processor" used in the above description includes, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an ASIC, a programmable logic device (e.g., Simple Programmable Logic Device (SPLD) , Complex Programmable Logic Device (CPLD), Field Programmable Gate Array (FPGA), etc. The processor functions by reading and executing a program stored in the memory 11. In addition, instead of storing the program in the memory 11, the program may be directly embedded in the circuit of the processor.In this case, the processor can read and execute the program embedded in the circuit. Note that each processor of this embodiment is not limited to being configured as a single circuit for each processor, but is configured as a single processor by combining a plurality of independent circuits, and its function is implemented by Furthermore, a plurality of components in Fig. 1 may be integrated into a single processor to realize its functions. The same applies to modified examples.

The processing circuit 15 uses the reconstruction function 151 to perform reconstruction processing on the data acquired from the medical image diagnostic apparatus 400 to generate a medical image to be applied to CAD. For example, a CT image is generated by performing reconstruction processing on raw data acquired from a CT apparatus. In addition, the processing circuit 15 uses the reconstruction function 151 to perform noise reduction processing and enhancement processing on the raw data, and executes reconstruction processing using the data generated thereby to reproduce medical images to be applied to CAD. may be generated. The processing circuit 15 that implements the reconstruction function 151 is an example of a reconstruction unit.

The processing circuit 15 evaluates the possibility of disease based on the medical image of the subject by the evaluation function 152 . Specifically, the processing circuit 15 calculates the degree of certainty of the fatal disease to be denied by executing CAD on the medical image. The processing circuit 15 also uses the result of the pursuit process to recalculate the confidence factor. Specifically, the confidence factor is calculated again by executing CAD on the medical image generated by the pursuit process. The processing circuit 15 that implements the evaluation function 152 is an example of an evaluation section.

The processing circuit 15 uses the determination function 153 to determine the subsequent work according to the evaluation result of the evaluation function 152 . Specifically, the processing circuit 15 extracts an appropriate post-stage work from among the plurality of post-stage work candidates stored in the memory 11 according to the confidence factor value obtained by executing the CAD. At this time, the subsequent work is determined based on the confidence value of the fatal disease to be diagnosed and the typical findings and pitfalls associated with the disease to be diagnosed. Then, the processing circuit 15 causes the determined post-stage work to be executed. For example, when the determined post-stage work is noise reduction processing or enhancement processing, the processing circuit 15 causes the reconstruction function 151 and CAD to automatically execute the post-stage work. Alternatively, when the determined post-stage work is an additional inspection, the processing circuit 15 presents the user with a request to execute the post-stage work. Alternatively, if the determined subsequent work is an additional test, the processing circuitry 15 may automatically place an order for the additional test, and may prompt the user to perform the work related to the ordered additional test. . The processing circuit 15 that implements the decision function 153 is an example of a decision unit.

In general, among processes that are candidates for post-stage work, the shorter the process can be executed, the lower the accuracy of CAD diagnosis when executing CAD using the generated data. Further, the longer the processing, the higher the CAD diagnosis accuracy when executing the CAD using the generated data. Therefore, when determining the post-stage work, the processing circuit 15 determines, as the post-stage work, a process that can be executed in a short time as the calculated certainty factor increases. In addition, the processing circuit 15 determines, as a post-stage work, a process for performing evaluation with higher accuracy as the certainty factor is smaller.

Moreover, the processing circuit 15 determines the next post-stage work each time the determined post-stage work is executed. At this time, the processing circuit 15 determines, as the next post-stage work, a process for performing an evaluation with higher accuracy than the accuracy of the evaluation results of the post-stage work that has already been executed. Then, the processing circuit 15 sequentially presents or executes the determined post-stage work until it is determined that emergency treatment is necessary, or until the suspicion of a fatal disease can be completely denied.

The processing circuit 15 uses the notification function 154 to notify a warning based on the evaluation result by the evaluation function 152 and the result of the post-stage work. Specifically, the processing circuit 15 issues a warning to the user when the calculated certainty factor is greater than or equal to a predetermined value. As a method of notifying the user, for example, a warning display indicating that the degree of certainty of a fatal disease is high may be displayed on the display 13, the user may be notified by voice, or the may send alerts to external systems. The processing circuit 15 that implements the notification function 154 is an example of a notification unit.

In addition, the processing circuit 15 may use the notification function 154 to notify that emergency treatment of the patient is not necessary based on the result of the evaluation by the evaluation function 152 and the result of the subsequent work. Specifically, the processing circuit 15 determines whether the degree of certainty for all fatal diseases becomes 0 by the subsequent work, or when the conditions for denying the suspicion of a fatal disease are met, the patient's emergency treatment is performed. Notify the user that it is unnecessary. A condition under which the suspicion of a fatal disease can be denied is, for example, that an interpretation result without any findings of a fatal disease is obtained by a remote radiologist. As a method of notifying the user, for example, a display indicating that emergency treatment is unnecessary may be displayed on the display 13, or the user may be notified by voice.

The processing circuit 15 causes the display 13 to display various information using the display control function 155 . For example, the processing circuit 15 causes the display 13 to display a display screen (hereinafter referred to as a diagnosis support screen) for supporting diagnosis of a fatal disease. On the diagnosis support screen, the certainty calculated by the evaluation function 152, the post-stage work determined by the determination function 153, and the warning determined by the notification function 154 are displayed. The processing circuit 15 that implements the display control function 155 is an example of a display control unit.

The processing circuit 15 acquires the evaluation result by the evaluation function 152 by the update function 156 . At this time, the processing circuit 15 updates the evaluation result when a new evaluation result is acquired. Specifically, the processing circuit 15 acquires the calculation result of the certainty each time the evaluation function 152 newly calculates the certainty. Then, the processing circuit 15 updates the confidence factor for the fatal disease for which the confidence factor is newly acquired. The processing circuit 15 that implements the update function 156 is an example of an update unit.

Next, the operation of diagnostic support processing executed by the diagnostic support system 100 will be described. Diagnosis support processing is to determine the post-stage work according to the confidence value of the fatal disease calculated by CAD, present or execute the decided post-stage work, and judge that there is no finding of the fatal disease by the first CAD. Even if a fatal disease is suspected, the subsequent work is executed until the suspicion of a fatal disease can be denied. FIG. 2 is a flow chart showing an example of the procedure of diagnostic support processing. It should be noted that the processing procedure in each processing described below is merely an example, and each processing can be changed as appropriate as possible. Further, in the processing procedures described below, steps can be omitted, replaced, and added as appropriate according to the embodiment.

(diagnosis support processing)
(Step S101)
The processing circuit 15 uses the evaluation function 152 to acquire a medical image of a subject to be diagnosed in emergency medical care. For example, the processing circuitry 15 acquires a CT image of the subject from the medical image diagnostic apparatus 400 .

(Step S102)
The processing circuit 15 uses the evaluation function 152 to apply the medical image acquired using the medical image diagnostic apparatus 400 to CAD. CAD calculates a confidence score for each fatal disease based on the applied medical images.

Next, the processing circuit 15 causes the display control function 155 to display a diagnostic support screen on the display 13 . FIG. 3 is a diagram showing an example of a diagnosis support screen 600 displayed on the display 13. As shown in FIG.

The diagnosis support screen 600 includes an image display section 610 and a subsequent work display section 620 .

The image display unit 610 displays a medical image acquired using the medical image diagnostic apparatus 400 during emergency medical care. In the example of FIG. 3, the image display unit 610 displays a CT image of the subject.

Information about the fatal disease to be denied is displayed in the post-operation display section 620 . The post-operation display section 620 includes a disease name display section 621 , an attention position display section 622 , a certainty display section 623 , an update time display section 625 and a situation display section 624 .

The name of each fatal disease is displayed in the disease name display section 621 .

In the image display section 610, a region display section 611 indicating a region of interest in diagnosis is displayed for each fatal disease. In the area display section 611, each fatal disease is displayed with a different frame color and thickness. The attention position display portion 622 displays symbols and colors corresponding to the area display portion 611 related to the corresponding fatal disease. For example, for the same fatal disease, the region display section 611 and the attention position display section 622 are displayed in the same color.

The certainty display section 623 displays the calculated certainty. The certainty displayed in the certainty display section 623 is updated at any time by a process described later. The certainty display section 623 displays, for example, any value in the range from 0 to 1 as the certainty.

A status display portion 624 displays the current status of the fatal disease diagnosis. For example, the status display section 624 displays an icon 626 indicating the execution status of the subsequent work and a display field 627 indicating the content of the subsequent work.

The update time display section 625 displays the time until the next confidence factor is updated. The update time display section 625 displays, for example, the time until the reconstruction process currently being executed ends, or the time until the result of the additional examination for which the order is currently being transmitted is obtained.

(Step S103)
Next, the processing circuit 15 uses the determination function 153 to determine the processing or work to be executed next by using the correspondence table showing the correspondence between the conditions including the degree of certainty and the subsequent work that is the processing or work. . The correspondence table is stored in the memory 11, for example. FIG. 4 is a diagram showing a correspondence table used in this embodiment. First, the processing circuitry 15 determines whether or not the confidence factor is 0.8 or more for each fatal disease.

(Step S104)
If the confidence factor is greater than or equal to 0.8 (step S103-Yes), processing circuit 15, through decision function 153, decides to send an emergency alert. In this case, the processing circuit 15 uses the notification function 154 to display a warning on the diagnostic support screen displayed on the display 13 and send a signal indicating that emergency measures are required to the external system via the network 200. . FIG. 5 is a diagram showing an example in which a warning is displayed on the diagnostic support screen 600. As shown in FIG. In the example of FIG. 5 , an icon 626 indicating that an emergency alert has been sent is displayed in the situation display section 624 when the certainty of “aortic aneurysm/imminent rupture” is “0.98”.

(Step S105)
If the confidence factor is less than 0.8 (step S103-No), the processing circuit 15 causes the decision function 153 to decide the subsequent work according to the confidence factor value. For example, based on the correspondence table shown in FIG. 4, the next processing is determined.

(Step S106)
The processing circuit 15 causes the display control function 155 to display the determined subsequent work on the diagnosis support screen 600 of the display 13 . Then, the processing circuit 15 automatically executes the determined subsequent work by the determining function 153 . Alternatively, the processing circuit 15 uses the display control function 155 to display the determined post-stage work on the diagnosis support screen 600 to present it to the user. By checking the execution status of the post-stage work displayed on the diagnosis support screen 600, the user can check the post-stage work that is currently being executed. Further, the user can input an instruction to execute the presented post-stage work by selecting the post-stage work icon 626 presented on the diagnosis support screen 600 . When an instruction to execute the post-stage work is input, the selected post-stage work is executed.

(Step S107)
The processing circuit 15 uses the evaluation function 152 to determine whether or not a new medical image for CAD diagnosis has been generated by the execution of the post-stage work.

If a new medical image has been generated (step S107-Yes), the process returns to step S102, and the new medical image generated by the immediately preceding post-stage work is used to calculate the degree of certainty of the fatal disease by CAD. be done. Then, the processing circuit 15 uses the update function 156 to update the newly calculated confidence factor of the fatal disease to the newly calculated value. Then, the processing circuit 15 uses the decision function 153 to decide the subsequent work according to the updated confidence factor and other conditions. At this time, the processing circuit 15 determines the subsequent work according to the conditions shown in FIG. The processing circuit 15 repeats the processing of steps S102 to S107 as long as a new medical image is generated by the post-stage work, and uses the newly generated medical image to repeatedly execute the calculation of the confidence factor by CAD.

(Step S108)
When the request for immediate remote interpretation is determined as the post-stage work, that is, when no new medical image is generated by the post-stage work (step S107-No), the processing circuit 15 causes the determination function 153 to determine whether the remote reading doctor ( (hereinafter referred to as a remote interpreting doctor) is transmitted to the remote interpreting doctor. For example, the patient information and the generated medical image are transmitted to a remote radiologist who provides an immediate remote radiological reading service, and a diagnosis of a fatal disease for the medical image is requested.

(Step S109)
Once the telereader's diagnosis of fatal disease is obtained, processing circuitry 15 determines, through decision function 153, whether there are findings of fatal disease in the diagnosis. If the diagnosis result by the remote radiologist indicates that a fatal disease is suspected (step S109-Yes), the processing circuit 15 executes the process of step S104 to transmit an emergency alert.

(Step S110)
If it is determined that there is no suspicion of a fatal disease in the diagnosis result by the remote radiologist (step S109-No), the processing circuit 15 causes the update function 156 to confirm the existence of a fatal disease that is determined to be unsuspected. Update the degrees to 0. Processing circuitry 15 then determines, via decision function 153, to send a notification that no emergency action is required. In this case, the processing circuit 15 uses the notification function 154 to display a notification indicating that emergency treatment is unnecessary on the display 13, and sends a signal indicating that emergency treatment is not necessary to the external system via the network 200. Send. FIG. 6 is a diagram showing an example in which a notification indicating that emergency treatment is unnecessary is displayed on the diagnosis support screen 600. As shown in FIG. In the example of FIG. 6, the status display portion 624 displays an icon 626 indicating that all fatal diseases have a confidence level of "0" and no emergency treatment is required.

When an emergency alert is notified by step S104, or when emergency treatment is not required by the processing of step S110, processing circuit 15 stops updating the confidence level of the fatal disease and supports diagnosis. End the process.

Here, an example of a case of diagnosing a fatal disease using the diagnosis support system 100 of the present embodiment in an emergency outpatient clinic will be described. When a patient with chief complaints of low back pain and abdominal pain visits the emergency department, the emergency physician must diagnose abdominal aortic aneurysm/imminent rupture as a fatal disease to be denied. In this case, the emergency doctor diagnoses suspected abdominal aortic aneurysm/imminent rupture using the medical images obtained by the examination and the results of CAD performed using the medical images. Conventionally, when the degree of certainty of "abdominal aortic aneurysm/imminent rupture" calculated by CAD is 0.45, it is judged that there is no finding. In such cases, fatal diseases may be overlooked.

On the other hand, according to the diagnosis support system 100 of the present embodiment, for example, when the certainty factor of "abdominal aortic aneurysm/imminent rupture" calculated by CAD is 0.45, "work 2: reconstruction "noise reduction processing" is determined for the previous image.

In "operation 2", for example, a reconstructed image is generated using noise reduction processing and edge enhancement parameters. Next, by applying the highly accurate reconstructed image generated by the "operation 2" to CAD, a more accurate confidence factor is calculated and updated. If the confidence of "abdominal aortic aneurysm imminent rupture" rises to 0.85, an emergency alert is sent. Also, assume that the confidence level for "abdominal aortic aneurysm/imminent rupture" has dropped to 0.25. In this case, since the certainty factor is less than 0.8 and the "work 2" has already been performed, the latter work can be applied to CAD to generate a medical image that enables more accurate diagnosis. “Work 3: Acquire past images” is determined as the work.

In "Work 3", past inspection images are acquired, and a diagnosis is made using CAD using the results of comparison between the past inspection images and the current inspection images, thereby calculating a more accurate degree of confidence and updating it. be done. Here, it is assumed that the confidence level for "abdominal aortic aneurysm/imminent rupture" has dropped to 0.00. In this case, since the certainty factor is less than 0.8 and "work 3" has already been performed, "work 4: order additional inspection" is determined as the subsequent work.

In "Work 4", for example, an order for contrast-enhanced CT image inspection is additionally issued, and by applying the CT image obtained by the contrast-enhanced CT image inspection to CAD, a more accurate confidence factor is calculated and updated. be. Assume here that the confidence level for "abdominal aortic aneurysm/imminent rupture" is maintained at 0.00. In this case, since the certainty factor is less than 0.8 and "task 4" has already been performed, "task 5: request immediate remote interpretation" is determined as the subsequent task.

In "task 5", a request for image interpretation is issued to a remote radiologist, and the remote radiologist diagnoses suspicion of "abdominal aortic aneurysm/imminent rupture". Here, it is assumed that there is no finding for "abdominal aortic aneurysm/imminent rupture". In this case, it is notified that emergency measures are not required.

Effects of the diagnosis support system 100 according to the present embodiment will be described below.

In general, diagnosis support systems used in emergency medical care are based on the premise of detailed diagnosis of medical images by radiologists. This makes it time consuming to establish a diagnosis for a fatal disease. Moreover, even when a diagnosis is made using the confidence factor calculated by CAD, findings of a fatal disease may be overlooked when the diagnosis is made by an unspecialized doctor.

The diagnosis support system 100 according to this embodiment can evaluate the possibility of disease based on the medical image of the subject, and determine follow-up processing for re-evaluating the possibility of disease according to the evaluation result. Specifically, the diagnosis support system 100 calculates a degree of certainty indicating the degree of suspicion of a disease based on the medical image, determines pursuit processing based on the degree of certainty, and uses the result of the pursuit processing to determine the degree of certainty. is calculated again. For example, the disease is a fatal disease. The pursuit process is, for example, post-stage work.

With the above configuration, according to the diagnosis support system 100 according to the present embodiment, even if there is no finding of a fatal disease in the evaluation of suspicion of a fatal disease using an examination image, Appropriate post-work is selected and performed or presented. By performing re-evaluation using the results of the post-stage work, it is possible to prevent the findings of fatal diseases from being overlooked.

In the diagnosis support system 100 according to this embodiment, the pursuit processing includes, for example, execution of CAD and proposal of additional examination orders. Further, the diagnosis support system 100 determines follow-up treatment based on typical findings and pitfalls associated with the disease.

For example, a process or work that serves as a countermeasure against a pitfall in image interpretation is determined as a post-stage work. For example, in the diagnosis of acute subdural hematoma, a crescent-shaped high density area in a plain CT image is typically used as a finding. Pitfalls include the difficulty in diagnosing thin hematomas and isosceles hematomas when performing image interpretation for this finding, and the easy overlooking of subdural hematomas along the falx and cerebellar tentorium. As a countermeasure against such pitfalls, it is effective to generate a reconstructed image of a coronal section or a sagittal section and use it for diagnosis. According to the diagnosis support system 100 according to the present embodiment, by executing the reconstruction image of the coronal section and the sagittal section as the post-stage work, it is possible to prevent oversight of typical findings and improve the diagnostic accuracy by CAD. can be enhanced.

Further, the diagnosis support system 100 according to the present embodiment can display the determined post-stage work on the display 13 . The doctor in charge of emergency medical care can confirm the post-stage work currently being performed by checking the displayed post-stage work. Further, by providing an input button for inputting an instruction to execute the post-stage work on the display screen of the display 13, the doctor in charge can judge whether or not to execute the decided post-stage work depending on the situation. can.

Further, the diagnosis support system 100 according to this embodiment can execute the determined pursuit process. With this configuration, the determined post-stage work is automatically executed. For example, when it is decided to perform an additional examination as a post-stage work, an order for the additional examination is automatically sent, thereby shortening the time required for diagnosis.

Further, the diagnosis support system 100 according to this embodiment can issue a warning based on the evaluation result and the pursuit process result. For example, an emergency alert can be sent if the confidence level of a fatal disease exceeds a threshold.

With the above configuration, according to the diagnosis support system 100 according to the present embodiment, even if there is no finding of a fatal disease in the evaluation of suspicion of a fatal disease using an examination image, re-evaluation using the results of the subsequent work An emergency alert can be sent if the confidence in . This prevents findings of lethal disease from being overlooked. In addition, by confirming the emergency alert, the attending physician can immediately determine the suspicion of a fatal disease, thereby shortening the time required for diagnosis. In addition, if it is found that emergency treatment is necessary due to additional post-stage work, an emergency alert will be sent without requesting a diagnosis from a remote radiologist. Therefore, it is possible to reduce unnecessary interpretation by remote radiologists, and reduce the number of radiologists assigned as remote radiologists.

Moreover, the diagnosis support system 100 according to the present embodiment can further notify that emergency treatment is unnecessary based on the result of the pursuit process. For example, when the degree of certainty of a fatal disease is 0 and the condition for denying a fatal disease is satisfied, it is presented that emergency treatment is unnecessary. By confirming this notification, the attending physician can immediately deny the suspicion of a fatal disease. As a result, the time required for diagnosis can be shortened.

Further, the diagnosis support system 100 according to the present embodiment determines a process that can be executed in a short time as a pursuit process for a higher certainty factor, and a process for performing an evaluation with a higher accuracy for a lower certainty factor as a pursuit process. decide. For example, when the confidence is 0.70, the confidence is relatively large, so the accuracy of CAD using the obtained image is low, but the time required for processing, such as noise reduction processing for the reconstructed image A task with a short time is determined as a subsequent task. On the other hand, for example, when the certainty is 0.10, the certainty is relatively small, so the processing time is long but the accuracy of CAD using the obtained image is high, such as acquisition of past images. is determined as the subsequent work. Accordingly, appropriate work for diagnosing a suspected fatal disease can be performed according to the degree of urgency.

Further, the diagnosis support system 100 according to the present embodiment determines, as the next pursuit process, a process for performing an evaluation with higher precision than the already executed evaluation results. Further, the diagnosis support system 100 determines the next pursuit process each time the determined pursuit process is executed. Suspicion of a lethal disease can be reliably denied by sequentially performing the subsequent steps to improve the diagnostic accuracy.

(Modification of the first embodiment)
A modification of the first embodiment will be described. This modification is obtained by modifying the configuration of the first embodiment as follows. Descriptions of configurations, operations, and effects that are the same as those of the embodiment are omitted.

The processing circuit 15 uses the determination function 153 to determine a plurality of post-stage tasks according to the evaluation result of the evaluation function 152 . Specifically, the processing circuit 15 extracts two or more appropriate post-stage tasks from among the plurality of post-stage task candidates stored in the memory 11 according to the values of the degrees of certainty.

The processing circuit 15 causes the display 13 to display the determined plurality of post-stage tasks by the display control function 155 .

FIG. 7 is a diagram showing an example of a diagnostic support screen 600 displayed on the display 13 in the diagnostic support processing of this modified example. As shown in FIG. 7 , in this modified example, a plurality of subsequent tasks are determined for one disease and displayed on the status display section 624 . The user can select and execute a necessary task from among the multiple displayed post-stage tasks. Also, the determined multiple post-stage tasks may be automatically and simultaneously executed. In this case, it is possible to reduce the time required to deny the suspicion of a fatal disease by repeating the subsequent steps.

(Second embodiment)
A second embodiment will be described. This embodiment is obtained by modifying the configuration of the first embodiment as follows. Descriptions of configurations, operations, and effects that are the same as those of the embodiment are omitted. In the diagnostic support system 2 of the present embodiment, a plurality of functions of the diagnostic support system 100 of the first embodiment are distributed and installed in different devices and applications. Here, the diagnostic support system 2 used for radiographic examination will be described.

The diagnosis support system 2 includes a work navigator, cockpit service, pathway service, data service, processing service, and scanner (imaging device). These services are placed on the network and cooperate through standardized interfaces. The work navigator navigates the work of the radiology department using scanning, reconstruction, image analysis, image interpretation services, etc. by the imaging device. The cockpit service escorts the user by providing the best working space according to the situation. The pathway service publishes and notifies information on the patient's medical care status to the user so that the patient's medical care status can be checked at any time. Data services provide users with all patient data.

Each of the work navigator, cockpit service, pathway service, data service, and processing service may be implemented by hardware such as a server or device having a processor, or may be implemented by software such as an application.

FIG. 8 is a diagram showing the configuration of the diagnosis support system 2 of this embodiment. The diagnosis support system 2 includes a storage unit 21 , an imaging unit 22 , an evaluation unit 23 , a determination unit 24 , a notification unit 25 , a display unit 26 , a reconstruction unit 27 and an update unit 28 .

The storage unit 21 has functions similar to those of the memory 11 of the first embodiment. A portion of the storage unit 21 is installed in a data service that stores medical records. Part of the storage unit 21 is installed in a pathway data service that stores information on the history, progress, and plans of medical practices.

The imaging unit 22 has the same function as the function of imaging the subject of the medical image diagnostic apparatus 400 of the first embodiment. The imaging unit 22 is mounted as, for example, a scanner (imaging device).

The evaluation unit 23 has the same function as the evaluation function 152 of the first embodiment. The evaluation unit 23 is installed in, for example, a processing service.

The determination unit 24 has the same function as the determination function 153 of the first embodiment. The determination unit 24 is installed in, for example, a work navigator.

The notification unit 25 has the same function as the notification function 154 of the first embodiment. The notification unit 25 is installed in the cockpit service, for example.

The display unit 26 has the same functions as the display 13 and the display control function 155 of the first embodiment. The display unit 26 is installed in the cockpit service.

The reconstruction unit 27 has the same function as the reconstruction function 151 of the first embodiment. The reconstruction unit 27 is installed in, for example, a processing service.

The updating unit 28 has the same function as the updating function 156 of the first embodiment. The updating unit 28 is installed in, for example, a processing service.

The diagnosis support system 2 of the present embodiment has a plurality of functions provided in the diagnosis support system 100 of the first embodiment distributed in different devices and applications. Therefore, according to the diagnosis support system 2 of this embodiment, the same effects as those of the diagnosis support system 100 of the first embodiment can be obtained.

The diagnosis support system 2 may include a modality composed of a console cockpit application, a cockpit Web terminal, a scanner (imaging device), a processing service, and a data service. In this case, each of the services constituting the diagnostic support system 2 has an independent standard API (Application Programming Interface), is connected by a network or virtual network, and is separated as an independent service.

(Modified example of the first embodiment and the second embodiment)
If the reliability of diagnostic results by CAD is sufficiently high, interpretation by a remote radiologist is not always necessary. For example, if the confidence level by CAD is 0, it may be determined that emergency treatment is not necessary without interpretation by a remote radiologist.

Further, in the above embodiment, the case of diagnosing a suspected fatal disease in emergency medical care was described as an example, but the present invention is not limited to this. For example, it can be applied to the diagnosis of suspected diseases other than fatal diseases.

According to at least one embodiment described above, it is possible to reduce oversight of diseases in diagnosis of medical images.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

100... Diagnosis support system 200... Network 300... Hospital information system (HIS)
400 Medical image diagnostic apparatus 500 Radiology department information management system (RIS)
DESCRIPTION OF SYMBOLS 10... Diagnosis support apparatus 11... Memory 12... Communication interface 13... Display 14... Input interface 15... Processing circuit 151... Reconfiguration function 152... Evaluation function 153... Decision function 154... Notification function 155... Display control function 156... Update function 600 ... Diagnosis support screen 610 ... Image display section 611 ... Area display section 620 ... Post-stage work display section 621 ... Disease name display section 622 ... Attention position display section 623 ... Certainty display section 624 ... Status display section 625 ... Update time display section 626 ... icon 627 ... display field 2 ... diagnosis support system 21 ... storage section 22 ... photographing section 23 ... evaluation section 24 ... determination section 25 ... notification section 26 ... display section 27 ... reconstruction section 28 ... updating section

Claims (14)

an evaluation unit that evaluates the possibility of disease based on the medical image of the subject;
a determination unit that determines a follow-up process for re-evaluating the possibility of the disease according to the evaluation result by the evaluation unit;
A medical support system. Further comprising a display control unit that causes a display unit to display the determined pursuit process,
The medical support system according to claim 1. The determination unit causes the determined pursuit process to be executed.
The medical support system according to claim 1 or 2. Further comprising a notification unit that notifies a warning based on the evaluation result and the result of the pursuit process,
The medical support system according to any one of claims 1 to 3. The notification unit further notifies that emergency treatment is unnecessary based on the result of the pursuit process.
The medical support system according to claim 4. The determination unit determines, as the next pursuit process, a process for performing an evaluation with a higher precision than the precision of the evaluation result that has already been executed,
The medical support system according to any one of claims 1 to 5. The determination unit determines the next pursuit process each time the determined pursuit process is executed.
A medical support system according to any one of claims 1 to 6. the follow-up process includes performing CAD or proposing an additional inspection order;
The decision unit decides the follow-up treatment based on typical findings or pitfalls associated with the disease.
The medical support system according to any one of claims 1 to 7. the disease is a fatal disease;
The medical support system according to any one of claims 1 to 8. The evaluation unit calculates a degree of certainty indicating a degree of suspicion of the disease based on the medical image,
The determination unit determines the pursuit process based on the certainty,
The evaluation unit recalculates the confidence using the result of the pursuit process.
A medical support system according to any one of claims 1 to 9. The determination unit determines a process that can be executed in a short time as the pursuit process as the confidence factor is higher, and determines a process for performing an evaluation with higher accuracy as the confidence factor is lower as the pursuit process.
The medical support system according to claim 10. The determination unit determines a plurality of pursuit processes according to the evaluation result,
The display control unit causes the display unit to display the plurality of determined pursuit processes.
The medical support system according to claim 2. The determination unit simultaneously executes the determined plurality of pursuit processes.
The medical support system according to claim 12. assessing the likelihood of disease based on medical images of a subject;
Determining a follow-up process to re-evaluate the possibility of the disease according to the evaluation result from the evaluation;
A medical assistance method comprising:

Images