Medical imaging processing apparatus, method, and program

Abstract

To display an analysis result for a medical image in an easily interpretable manner in medical image processing device, method, and program.SOLUTION: A medical image processing device includes at least one processor. The processor is configured so as to acquire a detection result for at least one region of interest included in a medical image detected by analyzing the medical image, specify a region of attention to which a user pays attention in the medical image, specify a non-attention region of interest, which is a region of interest on a structure different from a structure related to the attention region, out of the region of interest, and display a specification result for the non-attention region of interest on a display unit.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to a medical image processing apparatus, method, and program.

Background Art

[0002] In recent years, with the progress of medical devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices, it has become possible to perform image diagnosis using higher-quality and higher-resolution medical images. In particular, by image diagnosis using CT images, MRI images, etc., the lesion area can be accurately identified, and appropriate treatment is being carried out based on the identified results.

[0003] In addition, CAD (Computer-Aided Diagnosis) using a learning model obtained by machine learning such as deep learning is also used to analyze medical images, and disease areas such as lesions included in the medical images are detected from the medical images as regions of interest. Here, a plurality of CAD learning models are prepared for each organ or each disease. For this reason, CAD is configured to perform analysis processing capable of detecting all various diseases for various organs. Thus, the analysis results generated by the CAD analysis processing are associated with examination information such as patient name, gender, age, and the modality in which the medical image was obtained, stored in a database, and used for diagnosis. A doctor reads the medical image by referring to the distributed medical image and the analysis result on his / her own reading terminal. At this time, on the reading terminal, an annotation is added to the region of interest including the disease included in the medical image based on the analysis result. For example, a region surrounding the region of interest, an arrow indicating the region of interest, the type and size of the disease, etc. are added as annotations. The reading doctor creates a reading report by referring to the annotations added to the region of interest.

[0004] On the one hand, the analysis results of medical images by the above-mentioned CAD are often used as secondary reading (second reading) in the clinical field. For example, when reading images, first, a doctor reads the medical images without referring to the analysis results by CAD. Then, a medical image with annotations added based on the analysis results by CAD is displayed, and the doctor performs a secondary reading of the medical image while referring to the annotations. By performing such primary reading and secondary reading, it is possible to prevent overlooking the disease area.

[0005] In addition, methods for efficiently performing primary reading and secondary reading have been proposed. For example, Patent Documents 1 and 2 propose a method of comparing the analysis results by CAD with the reading results by a doctor and presenting to the doctor the reading results that the doctor has overlooked or overread.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] However, since CAD is configured to perform analysis processing capable of detecting all various diseases for various organs, the analysis results of CAD may include detection results of a very large number of diseases as regions of interest. Here, by using the methods described in Patent Documents 1 and 2, when displaying the analysis results of CAD, for the regions of interest read by the doctor, they are excluded from the analysis results and displayed. That is, for the read regions of interest, the annotations are deleted and displayed. However, in the methods described in Patent Documents 1 and 2, only the regions of interest read by the doctor are excluded from the analysis results of CAD. Therefore, in the medical images to be displayed, since there are still many regions of interest with annotations, it is difficult to perform reading with reference to the analysis results.

[0008] The present disclosure has been made in view of the above circumstances, and an object thereof is to display the analysis results for medical images in an easy-to-read manner.

Means for Solving the Problems

[0009] The medical image processing apparatus according to the present disclosure includes at least one processor, The processor acquires detection results of at least one region of interest included in a medical image detected by analyzing the medical image, identifies a region of interest that the user has focused on in the medical image, identifies non-focused regions of interest that are regions of interest having a structure different from the structure related to the region of interest among the regions of interest, and is configured to display the identification result of the non-focused regions of interest on a display.

[0010] Here, the "structure related to the region of interest" means a specific structure included in the medical image. Specifically, at least one of a disease and an organ can be set as the structure related to the region of interest.

[0011] In the medical image processing apparatus according to the present disclosure, the processor may be configured to display the identification result of the non-target region of interest by deleting the detection result of the region of interest regarding the structure related to the target region of interest among the regions of interest.

[0012] Further, in the medical image processing apparatus according to the present disclosure, the processor may be configured to identify the target region based on the user's operation during the reading of the medical image.

[0013] Further, in the medical image processing apparatus according to the present disclosure, the processor may be configured to identify the target region based on the document regarding the medical image.

[0014] Further, in the medical image processing apparatus according to the present disclosure, the processor may be configured to identify the target region based on the display manner of the medical image during the reading of the medical image.

[0015] Further, in the medical image processing apparatus according to the present disclosure, for the region of interest regarding the structure related to the target region, the processor may be configured to display the detection result of the region of interest for which the feature amount derived at the time of detection is equal to or greater than a predetermined threshold value.

[0016] Further, in the medical image processing apparatus according to the present disclosure, the region of interest may be a region of interest for a plurality of types of diseases.

[0017] Further, in the medical image processing apparatus according to the present disclosure, the region of interest may be a region of interest for a plurality of types of organs.

[0018] The medical image processing method according to the present disclosure acquires the detection result of at least one region of interest included in the medical image, which is detected by analyzing the medical image. Identifies the target region that the user has focused on in the medical image. Identify a non - attention - interested region, which is an interested region in the region of interest and has a structure different from the structure related to the region of interest, Display the identification result of the non - attention - interested region on a display.

[0019] Note that it may be provided as a program for causing a computer to execute the medical image processing method according to the present disclosure.

Advantages of the Invention

[0020] According to the present disclosure, the analysis result for a medical image can be displayed so as to be easy to read by a radiologist.

Brief Description of the Drawings

[0021]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0022] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. First, the configuration of the medical information system 1 to which the medical image processing apparatus according to the present embodiment is applied will be described. FIG. 1 is a diagram showing a schematic configuration of the medical information system 1. The medical information system 1 shown in FIG. 1 is based on an examination order from a doctor in a medical department using a known ordering system, and includes photographing of the subject's examination target site, storage of medical images obtained by the photographing, reading of the medical images by a radiologist and creation of a reading report, and viewing of the reading report by the doctor in the medical department of the requester and detailed observation of the medical images to be read. It is a system for performing

[0023] As shown in FIG. 1, the medical information system 1 includes a plurality of imaging devices 2, a plurality of reading WS (WorkStations) 3 that are reading terminals, a diagnostic WS 4, an image server 5, an image database (hereinafter referred to as an image DB (DataBase)) 6, a report server 7, and a report database (hereinafter referred to as a report DB) 8, which are connected to be communicable with each other via a wired or wireless network 10.

[0024] Each device is a computer installed with an application program for functioning as a component of the medical information system 1. The application program is stored in a storage device of a server computer connected to the network 10 or in network storage in a state accessible from the outside, and is downloaded and installed on the computer in response to a request. Alternatively, it is recorded on a recording medium such as a DVD (Digital Versatile Disc) and a CD-ROM (Compact Disc Read Only Memory) and distributed, and is installed on the computer from the recording medium.

[0025] The imaging device 2 is a device (modality) that generates a medical image representing a diagnostic target site by imaging a site of a subject to be diagnosed. Specifically, it is a simple X-ray imaging device, a CT device, an MRI device, a PET (Positron Emission Tomography) device, etc. The medical image generated by the imaging device 2 is transmitted to the image server 5 and stored in the image DB 6.

[0026] The reading WS3 is a computer used, for example, by a radiologist in the radiology department for reading medical images and creating reading reports, etc., and includes the medical image processing device 20 according to the first embodiment. In the reading WS3, a request to view a medical image with respect to the image server 5, various image processes on the medical image received from the image server 5, display of the medical image, and acceptance of input of findings sentences regarding the medical image are performed. Also, in the reading WS3, creation of a reading report, a registration request and a viewing request for the reading report with respect to the report server 7, and display of the reading report received from the report server 7 are performed. These processes are performed by the reading WS3 executing a software program for each process. Note that the reading report is an example of a document regarding the medical image of the present disclosure.

[0027] The medical treatment WS4 is a computer used by doctors in the medical department for detailed observation of images, viewing of radiology reports, creation of electronic medical records, etc., and is composed of a processing device, a display device such as a display, and an input device such as a keyboard and a mouse. In the medical treatment WS4, a request to view an image from the image server 5, display of the image received from the image server 5, a request to view a radiology report from the report server 7, and display of the radiology report received from the report server 7 are performed. These processes are carried out by the medical treatment WS4 executing software programs for each process.

[0028] The image server 5 is a general-purpose computer installed with a software program that provides the functions of a database management system (DBMS). In addition, the image server 5 is equipped with a storage in which the image DB6 is configured. This storage may be a hard disk device connected by the image server 5 and a data bus, or may be a disk device connected to a NAS (Network Attached Storage) and a SAN (Storage Area Network) connected to the network 10. Further, when the image server 5 receives a registration request for a medical image from the imaging device 2, it formats the medical image into a database format and registers it in the image DB6.

[0029] In the image DB6, the image data of the medical images acquired by the imaging device 2 and the attached information are registered. The attached information includes, for example, an image ID (identification) for identifying individual medical images, a patient ID for identifying the subject, an examination ID for identifying the examination, a unique ID (UID: unique identification) assigned to each medical image, the examination date on which the medical image was generated, the examination time, the type of imaging device used in the examination for acquiring the medical image, patient information such as the patient's name, age, gender, etc., the examination site (imaging site), imaging information (imaging protocol, imaging sequence, imaging method, imaging conditions, use of contrast agent, etc.), information such as a series number or a collection number when a plurality of medical images are acquired in one examination, and the like.

[0030] Also, when the image server 5 receives a viewing request from the reading WS3 and the medical treatment WS4 via the network 10, it searches for the medical images registered in the image DB6 and transmits the searched medical images to the reading WS3 and the medical treatment WS4 that are the request sources.

[0031] In the report server 7, a software program that provides the function of a database management system is incorporated into a general-purpose computer. When the report server 7 receives a registration request for a reading report from the reading WS3, it formats the reading report into a format for the database and registers it in the report DB8.

[0032] In the report DB8, the reading reports created by the reading doctor using the reading WS3 are registered. The reading report may include information such as, for example, the medical images to be read, the image ID for identifying the medical images, the reading doctor ID for identifying the reading doctor who performed the reading, the disease name, the position information of the disease, and information for accessing the medical images.

[0033] Also, when the report server 7 receives a viewing request for a reading report from the reading WS3 and the medical treatment WS4 via the network 10, it searches for the reading report registered in the report DB8 and transmits the searched reading report to the reading WS3 and the medical treatment WS4 that are the request sources.

[0034] In this embodiment, the subject to be diagnosed is the chest and abdomen of a human body, the medical image is a three-dimensional CT image composed of a plurality of tomographic images including the chest and abdomen, and by reading the CT image, a reading report including findings on diseases such as the lungs and liver included in the chest and abdomen is created. Note that the medical image is not limited to a CT image, and any medical image such as an MRI image and a simple two-dimensional image obtained by a simple X-ray imaging device can be used.

[0035] In this embodiment, when creating a reading report, the reading doctor first displays the medical image on the display 14 and reads the medical image with his own eyes. Then, by analyzing the medical image with the medical image processing device according to this embodiment, a region of interest included in the medical image is detected, and a second reading is performed using the detection result. The first reading is called the primary reading, and the second reading using the detection result of the region of interest by the medical image processing device according to this embodiment is called the secondary reading.

[0036] The network 10 is a wired or wireless local area network that connects various devices in the hospital. When the reading WS3 is installed in another hospital or clinic, the network 10 may be configured to connect the local area networks of each hospital with the Internet or a dedicated line.

[0037] Next, a medical image processing apparatus according to the first embodiment will be described. FIG. 2 illustrates the hardware configuration of the medical image processing apparatus according to the first embodiment. As shown in FIG. 2, the medical image processing apparatus 20 includes a CPU (Central Processing Unit) 11, a non-volatile storage 13, and a memory 16 as a temporary storage area. The medical image processing apparatus 20 also includes a display 14 such as a liquid crystal display, an input device 15 including a pointing device such as a keyboard and a mouse, and a network I / F (InterFace) 17 connected to the network 10. The CPU 11, the storage 13, the display 14, the input device 15, the memory 16, and the network I / F 17 are connected to a bus 18. Note that the CPU 11 is an example of the processor in the present disclosure.

[0038] The storage 13 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. A medical image processing program 12 is stored in the storage 13 as a storage medium. The CPU 11 reads the medical image processing program 12 from the storage 13, expands it in the memory 16, and executes the expanded medical image processing program 12.

[0039] Next, the functional configuration of the medical image processing apparatus according to the first embodiment will be described. FIG. 3 is a diagram showing the functional configuration of the medical image processing apparatus according to the first embodiment. As shown in FIG. 3, the medical image processing apparatus 20 includes an information acquisition unit 21, an analysis unit 22, a region of interest specification unit 23, a non-region of interest specification unit 24, a display control unit 25, a radiology report creation unit 26, and a communication unit 27. Then, by executing the medical image processing program 12, the CPU 11 functions as the information acquisition unit 21, the analysis unit 22, the region of interest specification unit 23, the non-region of interest specification unit 24, the display control unit 25, the radiology report creation unit 26, and the communication unit 27.

[0040] The information acquisition unit 21 acquires a target medical image G0 to be processed for creating a reading report from the image server 5 according to an instruction from the input device 15 by the reading doctor who is the operator. The target medical image G0 is, for example, a three-dimensional CT image composed of a plurality of tomographic images acquired by photographing the chest and abdomen of the human body. Also, when necessary, if a reading report has already been created for the target medical image G0 and registered in the report DB 8, the information acquisition unit 21 acquires the reading report from the report server 7.

[0041] The analysis unit 22 detects an abnormal shadow area included in the target medical image G0 as a region of interest, and derives an annotation for the detected region of interest. The analysis unit 22 uses a known computer-aided image diagnosis (i.e., CAD) algorithm to detect regions of shadows of multiple types of diseases from the target medical image G0 as regions of interest, derives the characteristics of the detected regions of interest, and derives an annotation based on the characteristics.

[0042] Examples of the types of diseases include tumors, pleural effusion, nodules, calcifications, and fractures, etc., according to the part of the subject included in the target medical image G0. Note that the analysis unit 22 detects regions of abnormal shadows included in a plurality of types of organs included in the target medical image G0 as regions of interest. In the present embodiment, since the target medical image G0 includes the chest and abdomen of the human body, examples of the organs include various organs included in the chest and abdomen of the human body such as the lungs, heart, liver, stomach, small intestine, pancreas, spleen, and kidneys.

[0043] For the detection of the region of interest and the derivation of the annotation, the analysis unit 22 has a learning model 22A in which machine learning is performed to detect regions of shadows of multiple types of diseases from the target medical image G0 as regions of interest and derive the characteristics. Also, the analysis unit 22 has a learning model 22B that derives an annotation by formulating the characteristics derived by the learning model 22A.

[0044] A plurality of learning models 22A are prepared according to the types of diseases and organs. The learning model 22A is a convolutional neural network (CNN (Convolutional Neural Network)) obtained by performing deep learning using teacher data so as to determine whether each pixel (voxel) in the target medical image G0 represents a shadow or abnormal shadow of various diseases.

[0045] The learning model 22A is constructed by learning a CNN using a large number of teacher data including, for example, teacher images including abnormal shadows, correct data representing the regions and properties of the abnormal shadows in the teacher images, and teacher data consisting of teacher images not including abnormal shadows. The learning model 22A derives a confidence level (likelihood) indicating that each pixel in the medical image is an abnormal shadow, and detects, as a region of interest, a region composed of pixels whose confidence level is equal to or higher than a predetermined first threshold. Here, the confidence level is a value between 0 and 1. Further, the learning model 22A derives the properties of the detected region of interest. The properties include the position and size of the abnormal shadow, the type of disease, and the like. The types of diseases include nodules, mesothelioma, calcification, pleural effusion, tumors, and cysts.

[0046] Note that the learning model 22A may detect abnormal shadows from three-dimensional medical images, or may detect abnormal shadows from each of a plurality of tomographic images constituting the target medical image G0.

[0047] In addition to the convolutional neural network, any learning model such as a support vector machine (SVM (Support Vector Machine)) can be used as the learning model 22A.

[0048] The learning model 22B derives an annotation based on the characteristics derived by the learning model 22A. The learning model 22B consists of, for example, a recurrent neural network in which machine learning is performed to formulate the input characteristics. If the characteristics derived by the learning model 22A are "upper lobe of the left lung", "nodule", and "1 cm", the learning model 22B derives, as an annotation, the sentence "A nodule of 1 cm in size is seen in the upper lobe of the left lung."

[0049] FIG. 4 is a diagram showing the detection result of the region of interest by the analysis unit 22. In the present embodiment, the target medical image G0 is a CT image of the chest and abdomen of a human body and consists of tomographic images of a plurality of axial sections. In FIG. 4, eight tomographic images 30A to 30H are shown in order from the head side of the human body. The tomographic images 30A to 30F include the left lung 31 and the right lung 32. The tomographic images 30E to 30H include the liver 33. The tomographic image 30H includes the left kidney 34 and the right kidney 35.

[0050] In FIG. 4, the abnormal shadows detected in each tomographic image are surrounded by rectangular marks. That is, as shown in FIG. 4, in the tomographic image 30A, the nodule region of the right lung 32 surrounded by the mark 41 is detected as the region of interest. In the tomographic image 30B, the nodule region of the left lung 31 surrounded by the mark 42A and the mesothelioma region of the left lung 31 surrounded by the mark 42B are detected as the regions of interest. In the tomographic image 30C, the pleural effusion region of the left lung 31 surrounded by the mark 43A is detected as the region of interest, and the nodule region of the right lung 32 surrounded by the mark 43B is detected as the region of interest. In the tomographic image 30D, the nodule region of the left lung 31 surrounded by the mark 44A and the pleural effusion region of the left lung 31 surrounded by the mark 44B are detected as the regions of interest, and the calcification region of the right lung 32 surrounded by the mark 44C is detected as the region of interest. Note that the nodule region of the right lung 32 has been missed in the detection. In the tomographic image 30E, the nodule region of the left lung 31 surrounded by the mark 45 is detected as the region of interest. In the tomographic image 30F, the tumor region of the liver 33 surrounded by the mark 46 is detected as the region of interest. In the tomographic image 30G, the two tumor regions of the liver 33 surrounded by the marks 47A and 47B are detected as the regions of interest. In the tomographic image 30H, the cyst region of the liver 33 surrounded by the mark 48 is detected as the region of interest. Note that the tomographic images 30A to 30H shown in FIG. 4 show a state in which many regions of interest have been detected for the purpose of explanation, and are different from the actual appearance of the regions of interest in the human body.

[0051] In addition, the analysis unit 22 also derives annotations for the detected regions of interest. For example, for the tomographic image 30C, the analysis unit 22 derives annotations such as "pleural effusion in the posterior part of the left middle lobe of the lung" and "a 1-cm nodule in the middle lobe of the right lung". Also, for the tomographic image 30F, the analysis unit 22 derives an annotation of "a 1-cm tumor in the liver".

[0052] When the display control unit 25 displays the detection result of the region of interest detected by the analysis unit 22 and the derived annotation (hereinafter simply referred to as the analysis result) on the display 14 as described later, a mark is given to the region of interest detected by the analysis unit 22, and the annotation is displayed.

[0053] The region of interest specifying unit 23 specifies the region of interest that the radiologist has focused on in the target medical image G0. Specifically, as a primary reading, the radiologist displays the target medical image G0 on the display 14, reads the target medical image G0 with his own eyes, and specifies the region of the abnormal shadow found as the region of interest. FIG. 5 is a diagram showing a display screen of the target medical image. As shown in FIG. 5, the display screen 50 includes an image display area 51 and a text display area 52. In the image display area 51, a tomographic image representing the tomographic plane of the target medical image G0 is switchably displayed. In FIG. 5, the tomographic image 30C shown in FIG. 4 is displayed in the image display area 51. In addition, in the text display area 52, a finding text by the radiologist who has read the displayed tomographic image is described. The finding text is also an example of a document related to a medical image.

[0054] The radiologist can switch the tomographic image displayed in the image display area 51 by using the input device 15. In addition, the input device 15 can give a mark to the abnormal shadow included in the tomographic image or measure the size of the abnormal shadow. The region of interest specifying unit 23 specifies the region of the abnormal shadow to which the mark is given as the region of interest. As the mark, a rectangle surrounding the abnormal shadow, an arrow indicating the abnormal shadow, or the like can be used. In FIG. 5, a rectangular mark 55 is given to the nodule included in the right lung of the tomographic image 30C displayed in the image display area 51.

[0055] Note that even if the radiologist does not give a mark, the abnormal shadow whose size has been measured can be regarded as having been read. Therefore, the region of interest specifying unit 23 also specifies the region of the abnormal shadow whose size has been measured as the region of interest.

[0056] In addition, the radiologist can input a finding statement about the target medical image G0 into the text display area 52 using the input device 15. In FIG. 5, a finding statement "A nodule about 1 cm in size is found in the right lung." is described in the text display area 52.

[0057] FIG. 6 is a diagram showing the result of identifying the regions of interest by the radiologist for tomographic images. As shown in FIG. 6, in the tomographic image 30A, the region of the nodule in the right lung 32 surrounded by the mark 61 is identified as the region of interest. In the tomographic image 30B, the region of the nodule in the left lung 31 surrounded by the mark 62 is identified as the region of interest. In the tomographic image 30C, the region of the nodule in the right lung 32 surrounded by the mark 63 is identified as the region of interest. In the tomographic image 30D, the region of the nodule in the left lung 31 surrounded by the mark 64A and the region of the nodule in the right lung 32 surrounded by the mark 64B are identified as the regions of interest. Note that the region of the nodule in the right lung 32 is a region that was missed from the detection result of the region of interest by the analysis unit 22. In the tomographic image 30E, the region of the nodule in the left lung 31 surrounded by the mark 65 is identified as the region of interest. Note that in the tomographic images 30F to 30H, the regions of interest are not identified.

[0058] When the radiologist finishes the primary reading, the radiologist selects the confirmation button 57 on the display screen 50. Thereby, the secondary reading is started. In the secondary reading, the non-target region of interest identification unit 24 identifies non-target regions of interest among the regions of interest detected by the analysis unit 22. The non-target region of interest is a region of interest for a structure different from the structure related to the above-described region of interest. The structure can be at least one of the disease that becomes the region of interest and the organ containing the region of interest. In the first embodiment, the non-target region of interest is a region of interest for an organ different from the organ related to the region of interest. Note that in the present embodiment, the non-target region of interest identification unit 24 identifies, as non-target regions of interest, the regions of interest detected in the organ in which the radiologist did not identify the region of interest during the primary reading.

[0059] Here, when comparing FIG. 4 showing the analysis result of the analysis unit 22 with FIG. 6 which is the reading result by the radiologist, in the reading result by the radiologist, no attention area is specified in the liver. Therefore, the non-attention area specifying unit 24 specifies the area of interest specified by the analysis unit 22 in the liver as a non-attention area of interest. That is, the non-attention area specifying unit 24 specifies, as shown in FIG. 4, the tumor area of the liver 33 surrounded by the mark 46 in the tomographic image 30F, the tumor areas of the liver 33 surrounded by the marks 47A and 47B in the tomographic image 30G, and the cyst area of the liver 33 surrounded by the mark 48 in the tomographic image 30H as non-attention areas of interest.

[0060] In addition, in the present embodiment, as shown in FIG. 6, the attention area specifying unit 23 does not specify the mesothelioma (mesothelioma surrounded by the mark 42B in the tomographic image 30B shown in FIG. 4) included in the left lung 31 as an attention area for the tomographic image 30B. Also, the attention area specifying unit 23 does not specify the pleural effusion (pleural effusion surrounded by the mark 43A in the tomographic image 30C shown in FIG. 4) included in the left lung 31 as an attention area for the tomographic image 30C. Also, the attention area specifying unit 23 does not specify the pleural effusion (pleural effusion surrounded by the mark 44B in the tomographic image 30D shown in FIG. 4) included in the left lung 31 and the calcification (calcification surrounded by the mark 44C in the tomographic image 30D shown in FIG. 4) included in the right lung 32 as attention areas for the tomographic image 30D. However, diseases not specified as attention areas in the lungs will be described later.

[0061] FIG. 7 is a diagram showing the identification result of non-target regions of interest in the tomographic image. Note that FIG. 7 shows the tomographic image displayed on the display 14. For this purpose, among the regions of interest detected by the analysis unit 22, the marks given to the target regions as shown in FIG. 4 are erased, and marks are given only to the non-target regions of interest. As shown in FIG. 7, in the tomographic images 30A to 30E, no non-target regions of interest are identified. In the tomographic image 30F, the tumor region of the liver 33 surrounded by the rectangular mark 71 is identified as a non-target region of interest. In the tomographic image 30G, the tumor regions of the liver 33 surrounded by the rectangular marks 72A and 72B are identified as non-target regions of interest. In the tomographic image 30H, the cyst region of the liver 33 surrounded by the rectangular mark 73 is identified as a non-target region of interest.

[0062] The display control unit 25 displays the identification result of the non-target region of interest on the display 14. FIG. 8 is a diagram showing the display screen of the identification result of the non-target region of interest. The identification result of the non-target region of interest is the mark given to the non-target region of interest and the annotation derived for the non-target region of interest. Note that in FIG. 8, the same components as those in FIG. 5 are given the same reference numerals, and detailed descriptions are omitted here.

[0063] As shown in FIG. 8, the tomographic image 30F is displayed in the image display area 51 of the display screen 80 for the identification result of the non-target region of interest. A rectangular mark 71 is given to the tumor of the liver, which is a non-target region of interest, in the tomographic image 30F.

[0064] In addition, an annotation display area 53 for displaying the annotation for the non-target region of interest is displayed on the display screen 80. As shown in FIG. 8, the annotation "tumor of 1 cm in size in the liver" derived by the analysis unit 22 for the tomographic image 30F is displayed in the annotation display area 53.

[0065] When the tomographic images 30A to 30E in which all the regions of interest detected by the analysis unit 22 are specified as the regions of interest are displayed in the image display area 51, no mark is given to the abnormal shadow and no annotation is displayed. On the other hand, the radiologist has not specified the abnormal shadow included in the liver as the region of interest. For this reason, when the tomographic images 30F to 30H in which the regions of interest are detected in the liver are displayed in the image display area 51, a mark is given to the abnormal shadow included in the liver and an annotation is displayed.

[0066] The radiologist can confirm the existence of an abnormal shadow that may have been overlooked during the primary reading based on the mark given to the non-target region of interest and the displayed annotation. For example, as shown in FIG. 8, a mark 71 is given to the tumor included in the liver included in the tomographic image 30F and an annotation is displayed. Thereby, the radiologist can easily confirm the existence of the tumor included in the liver that was overlooked during the primary reading, and for the confirmed tumor, a finding statement can be described in the text display area 52. For example, in FIG. 8, a finding statement of "A tumor of about 1 cm is seen in the liver." can be described.

[0067] The reading report creation unit 26 creates a reading report including the finding statement input in the text display area 52. Then, when the confirmation button 58 is selected on the display screen 80, the reading report creation unit 26 stores the created reading report together with the target medical image G0 and the detection result in the storage 13.

[0068] The communication unit 27 transfers the created reading report together with the target medical image G0 and the detection result to the report server 7. In the report server 7, the transferred reading report is stored together with the target medical image G0 and the detection result.

[0069] Next, the processing performed in the first embodiment will be described. FIG. 9 is a flowchart showing the processing performed during primary reading in the first embodiment, and FIG. 10 is a flowchart showing the processing performed during secondary reading in the first embodiment. It is assumed that the target medical image G0 to be read is acquired from the image server 5 by the information acquisition unit 21 and stored in the storage 13. When an instruction to create a reading report is given by the reading doctor, the processing is started, and the display control unit 25 displays the target medical image G0 on the display 14 (step ST1). Next, the attention area specifying unit 23 specifies the attention area that the reading doctor has focused on in the target medical image G0 based on an instruction using the input device 15 by the reading doctor (step ST2). The reading doctor inputs a finding statement regarding the attention area into the text display area 52.

[0070] Subsequently, using the finding statement input by the reading doctor into the text display area 52, the reading report creation unit 26 creates a reading report by primary reading (step ST3). Next, when the confirmation button 57 is selected, it is determined whether an instruction to start secondary reading has been given (step ST4). If step ST4 is negative, the process returns to step ST1. If step ST4 is affirmative, the primary reading is terminated and the secondary reading is started.

[0071] During secondary reading, first, the analysis unit 22 analyzes the target medical image G0 to detect at least one region of interest included in the target medical image G0 (step ST11). Also, an annotation regarding the region of interest is derived (step ST12). Note that the analysis of the target medical image G0 may be performed immediately after the information acquisition unit 21 acquires the target medical image G0 from the image server 5.

[0072] Next, the non-target region of interest specifying unit 24 specifies a non-target region of interest, which is a region of interest regarding an organ different from the organ associated with the target region, among the regions of interest detected by the analysis unit 22 (step ST13). Then, the display control unit 25 displays the specification result of the non-target region of interest on the display 14 (step ST14). The radiologist inputs a finding text into the text display area 52 if necessary while viewing the specification result of the non-target region of interest.

[0073] Next, using the finding text input by the radiologist, the radiology report creation unit 26 creates a radiology report (step ST15). Then, the radiology report creation unit 26 stores the created radiology report together with the target medical image G0 and the detection result in the storage 13 (step ST16). Further, the communication unit 27 transfers the created radiology report together with the target medical image G0 and the detection result to the report server 7 (step ST17), and the process of the second reading is terminated.

[0074] As described above, in the first embodiment, the radiologist, who is the user, specifies the target region of interest in the target medical image G0, and the analysis unit 22 specifies a non-target region of interest, which is a region of interest regarding an organ different from the organ associated with the target region, among the regions of interest detected from the target medical image G0, and the specification result of the non-target region of interest is displayed on the display 14. As a result, instead of the extraction results of all the regions of interest detected by the analysis unit 22, only the regions of interest detected in the organs for which the radiologist did not specify the target region of interest are displayed as non-target regions of interest on the display 14. Therefore, the analysis results for the target medical image G0 can be reduced, and thus, the analysis results for the target medical image G0 can be displayed in an easy-to-read manner.

[0075] Next, a second embodiment of the present disclosure will be described. Note that the configuration of the medical image processing apparatus according to the second embodiment is the same as the configuration of the medical image processing apparatus according to the first embodiment shown in FIG. 3, and only the performed processes are different. Therefore, detailed description of the apparatus will be omitted here.

[0076] In the above-described first embodiment, the non-target region of interest specifying unit 24 specifies a non-target region of interest, which is a region of interest for an organ different from the organ related to the target region, among the regions of interest detected by the analysis unit 22 from the target medical image G0. In the second embodiment, the difference from the first embodiment is that the non-target region of interest specifying unit 24 specifies, as non-target regions of interest, regions of interest for diseases different from the disease related to the target region, among the regions of interest detected by the analysis unit 22 from the target medical image G0.

[0077] For example, when reading the tomographic image 30B, as shown in FIG. 6, the radiologist does not specify the mesothelioma (the mesothelioma surrounded by the mark 42B in the tomographic image 30B shown in FIG. 4) included in the left lung 31 as the target region. Also, for the tomographic image 30C, the pleural effusion (the pleural effusion surrounded by the mark 43A in the tomographic image 30C shown in FIG. 4) included in the left lung 31 is not specified as the target region. Also, for the tomographic image 30D, the pleural effusion (the pleural effusion surrounded by the mark 44B in the tomographic image 30D shown in FIG. 4) included in the left lung 31 and the calcification (the calcification surrounded by the mark 44C in the tomographic image 30D shown in FIG. 4) included in the right lung 32 are not specified as the target regions. In such a case, there is a possibility that the radiologist may overlook the mesothelioma and pleural effusion included in the left lung 31 and the calcification included in the right lung 32.

[0078] Therefore, in the second embodiment, the non-target region of interest specifying unit 24 specifies, as non-target regions of interest, regions of interest for diseases different from the disease related to the target region. Here, the disease related to the target region is a nodule, and the different diseases are mesothelioma, pleural effusion, and calcification. The non-target region of interest specifying unit 24 specifies, for the tomographic image 30B, the region of interest of the mesothelioma included in the left lung 31 as a non-target region of interest. Also, the non-target region of interest specifying unit 24 specifies, for the tomographic image 30C, the region of interest of the pleural effusion included in the left lung 31 as a non-target region of interest. Also, the non-target region of interest specifying unit 24 specifies, for the tomographic image 30D, the region of interest of the pleural effusion included in the left lung 31 and the region of interest of the calcification included in the right lung 32 as non-target regions of interest.

[0079] As a result, as shown in FIG. 11, when the tomographic image 30C is displayed in the image display area 51 on the display screen 81 of the specific result of the non-target region of interest, the display control unit 25 assigns a rectangular mark 74 to the pleural effusion contained in the left lung 31, and in the annotation display area 53, displays the annotation of "pleural effusion in the posterior part of the middle lobe of the left lung" derived for the pleural effusion. In addition, in the tomographic image 30C displayed in the image display area 51, the mark 43B given as shown in FIG. 4 is erased. On the other hand, when the tomographic image 30B is displayed on the display screen 81 of the specific result of the non-target region of interest, the display control unit 25 assigns a mark to the mesothelioma contained in the left lung 31, and in the annotation display area 53, displays the annotation regarding the mesothelioma of the left lung derived by the analysis unit 22 for the tomographic image 30B. In addition, in the tomographic image 30B displayed in the image display area 51, the mark 42A given as shown in FIG. 4 is erased. Further, when the tomographic image 30D is displayed on the display screen 81 of the specific result of the non-target region of interest, the display control unit 25 assigns marks to the pleural effusion contained in the left lung 31 and the calcification contained in the right lung 32, and in the annotation display area 53, displays the annotation regarding the pleural effusion of the left lung and the calcification of the right lung derived by the analysis unit 22 for the tomographic image 30D. In addition, in the tomographic image 30D displayed in the image display area 51, the marks 44A, 44C given as shown in FIG. 4 are erased.

[0080] By checking the mark 74 in the tomographic image 30C displayed on the display screen 81 shown in FIG. 11 and the annotation displayed in the annotation display area 53, the radiologist can confirm the presence of pleural effusion in the left lung. Therefore, the radiologist can add the finding sentence of "pleural effusion is seen in the posterior part of the middle lobe of the left lung." to the finding sentence of "a nodule about 1 cm is seen in the right lung." described in the text display area 52.

[0081] On the contrary, in the case where the region of interest of the nodule in the right lung detected by the analysis unit 22 is not specified as the region of interest in the tomographic image 30C in the second embodiment, the non-target region of interest specifying unit 24 specifies the region of interest of the nodule in the right lung among the regions of interest detected by the analysis unit 22 as the non-target region of interest. In this case, as shown in FIG. 12, when the tomographic image 30C is displayed in the image display region 51 on the display screen 82 of the specification result of the non-target region of interest, a rectangular mark 75 is given to the abnormal shadow of the nodule in the right lung. Further, in the annotation display region 53, "A nodule with a size of 1 cm in the right lung", which is an annotation regarding the nodule in the right lung derived by the analysis unit 22 with respect to the tomographic image 30C, is displayed. Therefore, the radiologist can add a finding sentence "A nodule of about 1 cm is found in the right lung." to the finding sentence "Pleural effusion is seen in the posterior part of the middle lobe of the left lung." described in the text display region 52.

[0082] As described above, in the second embodiment, the radiologist as the user specifies the region of interest noted in the target medical image G0, and among the regions of interest detected by the analysis unit 22 from the target medical image G0, the non-target region of interest, which is the region of interest regarding a disease different from the disease related to the region of interest, is specified, and the specification result of the non-target region of interest is displayed on the display 14. As a result, instead of the extraction results of all the regions of interest detected by the analysis unit 22, only the regions of interest related to the diseases for which the radiologist did not specify the regions of interest are displayed on the display 14 as the non-target regions of interest. Therefore, the analysis results for the target medical image G0 can be reduced and the analysis results for the target medical image G0 can be displayed in an easy-to-read manner for reading the analysis results.

[0083] In addition, in the above-described first and second embodiments, in the display screen 81 of the identification result of the non-target region of interest, marks are given only to the non-target region of interest, but the present invention is not limited to this. Different marks may be given to each of the target region and the non-target region of interest. For example, as shown in FIG. 6, in the tomographic image 30C, when a nodule included in the right lung 32 is identified as the target region, the pleural effusion included in the left lung 31 is identified as the non-target region of interest. In this case, as shown in FIG. 13, when the tomographic image 30C is displayed on the display screen 81 of the identification result of the non-target region of interest, a solid-line rectangular mark 55 may be given to the nodule included in the right lung 32, and a dashed-line rectangular mark 74 may be given to the pleural effusion included in the left lung 31.

[0084] Also, in the above-described first and second embodiments, the target region specifying unit 23 specifies the target region based on the radiologist specifying an abnormal shadow included in the target medical image G0, but the present invention is not limited to this. The radiologist may specify the target region included in the target medical image G0 based on the findings text input in the text display region 52, that is, the content of the radiology report. In this case, the target region specifying unit 23 analyzes the character string included in the radiology report using natural language processing technology, and extracts information representing the characteristics of the lesion, such as the location, type, and size of the lesion included in the radiology report, as character information.

[0085] Note that natural language processing is a series of technologies that enable a computer to process natural languages commonly used by humans in daily life. Through natural language processing, it is possible to perform tasks such as splitting a sentence into words, parsing the syntax, and analyzing the meaning. The attention area identification unit 23 uses natural language processing technology to split the character strings included in the radiology report into words and parse the syntax, thereby obtaining character information and identifying the attention area. For example, when the sentence in the radiology report is "A 1-cm nodule is observed in the upper lobe of the right lung.", the attention area identification unit 23 obtains the terms "right lung", "upper lobe", "nodule", and "1 cm" as character information. Then, based on the obtained character information, the attention area identification unit 23 identifies the attention area. For example, when the character information is "right lung", "upper lobe", "nodule", and "1 cm", the nodule in the upper lobe of the right lung is identified as the attention area.

[0086] In this case, in the tomographic image 30A shown in FIG. 4, the nodule included in the right lung 32 is identified as the attention area. If the abnormal shadow identified as the attention area is only the nodule in the right lung included in the tomographic image 30A, the non-attention area of interest identification unit 24 identifies the areas of interest other than the nodules in the right lung included in the tomographic images 30A to 30H as non-attention areas of interest.

[0087] Regarding the target medical image G0, the information acquisition unit 21 may acquire the radiology report stored in the report DB8, analyze the acquired radiology report, identify the already-read abnormal shadow, and identify the attention area.

[0088] For example, assume that the description in the obtained radiology report is as follows: "Compared with the chest CT performed on January 1, 2010, a solid nodule measuring φ35×28 mm is observed in S1 of the right lung. There is a ground-glass opacity at the edge, and the boundary is unclear. A pleural indentation sign is also seen. Calcification and cavities are not included. It is considered to be primary lung cancer. An enlarged lymph node measuring φ1.4 cm is observed around the B1 bronchus in the right hilar region. No pleural effusion is seen. A right renal calculus is observed. No enlarged lymph nodes are seen in the abdomen. No ascites is seen." By analyzing such a radiology report, the analysis results of "a nodule measuring φ35×28 mm in S1 of the right lung", "an enlarged lymph node measuring φ1.4 cm around the B1 bronchus", "no pleural effusion", "a right renal calculus", "no enlarged lymph nodes in the abdomen", and "no ascites" can be obtained.

[0089] In this case, the target area specifying unit 23 may specify, as the target area, the area of interest related to the analysis result among the areas of interest detected by the analysis unit 22. Also, the non-target area of interest specifying unit 24 may specify, as the non-target area of interest, the area of interest not related to the analysis result among the areas of interest detected by the analysis unit 22.

[0090] Further, the region of interest specifying unit 23 may specify the region of interest based on the position of the cursor during the input of the findings sentence into the sentence display area 52 when the radiologist reads the target medical image G0. For example, as shown in FIG. 14, for the tomographic image 30C displayed in the image display area 51, although no mark or the like is given to the tomographic image 30C, assume that the sentence being input in the sentence display area 52 is "Pleural effusion is seen in the posterior part of the middle lobe of the left lung. A nodule measuring 1 cm in size is seen in the right lung." And assume that in the sentence display area 52, the cursor 90 is positioned before the character "pleural effusion". In this case, the region of interest specifying unit 23 specifies the region of the pleural effusion 91 included in the tomographic image 30C as the region of interest. In this case, the analysis result for the target medical image G0 may be stored in the storage 13 after being analyzed by the analysis unit 22 in advance. The region of interest specifying unit 23 specifies the region of interest in the displayed tomographic image 30C based on the character at the position of the cursor 90 in the sentence display area 52 and the analysis result by the analysis unit 22. Note that the position of the cursor 90 is an example of the user's operation.

[0091] Further, the region of interest specifying unit 23 may specify the region of interest based on the position of the pointer on the target medical image G0 displayed in the image display area 51 when the radiologist reads the target medical image G0. For example, as shown in FIG. 15, assume that the pointer 92 is positioned at the position of the nodule in the right lung included in the tomographic image 30C displayed in the image display area 51. In this case, the region of interest specifying unit 23 specifies the region of the nodule in the right lung included in the tomographic image 30C as the region of interest. In this case, the analysis result for the target medical image G0 may be stored in the storage 13 after being analyzed by the analysis unit 22 in advance. The region of interest specifying unit 23 specifies the region of interest in the displayed tomographic image 30C based on the position of the pointer 92 in the displayed tomographic image 30C and the analysis result by the analysis unit 22. Note that the position of the pointer 92 is an example of the user's operation.

[0092] In addition, when the radiologist reads the target medical image G0, the region of interest specifying unit 23 may specify the region of interest based on the paging operation of the target medical image G0 displayed in the image display area 51. The paging operation is an operation of sequentially switching the tomographic images displayed in the image display area 51. Here, when the radiologist switches the tomographic images to be displayed, if there is no disease, the tomographic images are switched by a relatively fast paging operation. On the other hand, when a disease is found in a tomographic image, in the vicinity of the tomographic image where the disease is found, the paging operation becomes relatively slow, the tomographic image is switched back and forth, or a specific tomographic image is displayed for a relatively long time.

[0093] Therefore, in the paging operation using the input device 15 by the radiologist, the region of interest specifying unit 23 detects that the paging operation becomes relatively slow, the tomographic image is switched back and forth, or the image is displayed for a relatively long time, and specifies the abnormal shadow included in the tomographic image displayed at the time of detection as the region of interest. For example, among the tomographic images 30A to 30H shown in FIG. 4, if the tomographic image 30C is displayed for a longer time compared to other tomographic images, the region of interest specifying unit 23 specifies the pleural effusion in the left lung and the nodules in the right lung included in the tomographic image 30C as the region of interest. In this case, the analysis result for the target medical image G0 may be analyzed in advance by the analysis unit 22 and stored in the storage 13. The region of interest specifying unit 23 specifies the region of interest in the currently displayed tomographic image 30C based on the analysis result by the analysis unit 22 in the tomographic image 30C that is displayed for a longer time compared to other tomographic images. Note that the paging operation is an example of a user operation.

[0094] In addition, when the radiologist reads the target medical image G0, the region of interest specifying unit 23 may specify the region of interest based on the radiologist's line of sight. In this case, a sensor for detecting the line of sight is provided on the display 14, and based on the detection result by the sensor, the radiologist's line of sight with respect to the tomographic image being displayed on the display 14 is detected. For example, if the position of the line of sight is at the nodule in the right lung during the display of the tomographic image 30C, the region of interest specifying unit 23 specifies the region of the nodule in the right lung included in the tomographic image 30C as the region of interest. In this case, the analysis result for the target medical image G0 may be stored in the storage 13 after performing analysis processing in advance by the analysis unit 22. The region of interest specifying unit 23 specifies the region of interest in the displayed tomographic image 30C based on the detected radiologist's line of sight and the analysis result by the analysis unit 22. Note that the line of sight is an example of a user operation.

[0095] On the other hand, when the target medical image G0 is a CT image, the gradation conditions are set so as to have an appropriate density and contrast for easily reading the target organ, and are displayed on the display 14. The gradation conditions are the window value and the window width when the target medical image G0 is displayed on the display 14. The window value is the CT value that is the center of the part to be observed among the gradations that the display 14 can display. The window width is the width between the lower limit value and the upper limit value of the CT values of the part to be observed. For example, when the lung field conditions are set as the gradation conditions so that the lungs can be easily observed, the window value is the CT value of the lungs, and the window width is the lower limit value and the upper limit value of the CT values that make the lungs easy to see. When the lung field conditions are set as the gradation conditions, the target medical image G0 in which the abnormal shadow of the lungs can be easily read can be displayed on the display 14. Note that the window value and the window level are an example of the display method.

[0096] Here, when a plurality of organs are included in the target medical image G0 and gradation conditions are set to make it easier to read a specific organ, other organs are often not read. Therefore, the region of interest specifying unit 23 may acquire the gradation conditions of the target medical image G0 and specify the region of interest according to the gradation conditions. For example, when the lung field conditions are set as the gradation conditions for the target medical image G0, all abnormal shadows included in the lungs in the target medical image G0 may be specified as the region of interest. In this case, the non-target region of interest specifying unit 24 may specify the region of interest specified by the analysis unit 22 in the liver as the non-target region of interest. Note that the gradation conditions are an example of a display method.

[0097] Also, when the target medical image G0 is a CT image, the CT image is reconstructed by an appropriate reconstruction method that makes it easier to read the target organ. Reconstruction is a process performed when generating a CT image from projection images acquired by photographing a subject with a CT device. Examples of reconstruction methods include a reconstruction method that makes it easier to observe the lungs and a reconstruction method that makes it easier to observe the liver.

[0098] Here, when a plurality of organs are included in the target medical image G0 and the target medical image G0 is generated by a reconstruction method that makes it easier to read a specific organ, other organs are often not read. Therefore, the region of interest specifying unit 23 may acquire the reconstruction method of the target medical image G0 and specify the region of interest according to the reconstruction method. For example, when a reconstruction method that makes it easier to observe the lungs is used when generating the target medical image G0, all abnormal shadows included in the lungs in the target medical image G0 may be specified as the region of interest. In this case, the non-target region of interest specifying unit 24 may specify the region of interest specified by the analysis unit 22 in the liver as the non-target region of interest. Note that the reconstruction method is an example of a display method.

[0099] Further, when the target medical image G0 is displayed on the display 14, the region of interest specifying unit 23 may detect organs included in the displayed tomographic image and specify an abnormal shadow included in the detected organs as the region of interest. In this case, the non-region-of-interest specifying unit 24 may specify, in the target medical image G0, the region of interest specified in the organs not detected by the region of interest specifying unit 23 as the non-region-of-interest. For example, when the region of interest specifying unit 23 detects the lungs from the displayed tomographic image, the region of interest specifying unit 23 specifies an abnormal shadow included in the lungs as the region of interest. Further, the non-region-of-interest specifying unit 24 may specify, as the non-region-of-interest, the region of interest specified in organs other than the lungs included in the target medical image G0.

[0100] Also, in each of the above embodiments, the non-region-of-interest specifying unit 24 specifies, as the non-region-of-interest, the region of interest other than the region of interest specified by the region of interest specifying unit 23 among the regions of interest detected by the analysis unit 22, but is not limited thereto. The analysis unit 22 detects an abnormal shadow based on the confidence level of being an abnormal shadow by the learning model 22A. Therefore, among the regions of interest other than the region of interest specified by the region of interest specifying unit 23, a region of interest whose confidence level is equal to or higher than a predetermined threshold Th1 may be specified as the non-region-of-interest. Thereby, it becomes possible to perform a secondary reading in addition to the primary reading for a region of interest with a high possibility of a disease. Note that the confidence level is an example of a feature amount.

[0101] Also, the learning model 22A in the analysis unit 22 may be configured to derive the malignancy of the abnormal shadow, and the non-region-of-interest may be specified according to the malignancy. That is, the non-region-of-interest specifying unit 24 may specify, as the non-region-of-interest, a region of interest among the regions of interest other than the region of interest specified by the region of interest specifying unit 23, whose malignancy output by the learning model 22A is equal to or higher than a predetermined threshold Th2. Thereby, it becomes possible to perform a secondary reading in addition to the primary reading for a region of interest with a high possibility of a disease. Note that the malignancy is an example of a feature amount.

[0102] In the above-described embodiment, the analysis unit 22 detects the region of interest from the target medical image G0 and derives the annotation, but the present invention is not limited thereto. The target medical image G0 may be analyzed by an analysis device provided separately from the medical image processing apparatus 20 according to the present embodiment, and the analysis result obtained by the analysis device may be acquired by the information acquisition unit 21. Further, in some cases, the medical WS4 may analyze the medical image. In such a case, the analysis result obtained by the medical WS4 may be acquired by the information acquisition unit 21 of the medical image processing apparatus 20 according to the present embodiment. Further, when the analysis result is registered in the image database 6 or the report database 8, the information acquisition unit 21 may acquire the analysis result from the image database 6 or the report database 8.

[0103] In the above-described first embodiment, the non-target region of interest specifying unit 24 specifies a non-target region of interest that is a region of interest for an organ different from the organ related to the target region among the regions of interest detected by the analysis unit 22 from the target medical image G0. In the second embodiment, the non-target region of interest specifying unit 24 specifies, as a non-target region of interest, a region of interest for a disease different from the disease related to the target region among the regions of interest detected by the analysis unit 22 from the target medical image G0. However, in the non-target region of interest specifying unit 24, both a region of interest for an organ different from the organ related to the target region and a region of interest for a disease different from the disease related to the target region among the regions of interest detected by the analysis unit 22 from the target medical image G0 may be specified as non-target regions of interest.

[0104] In each of the above-described embodiments, the technique of the present disclosure is applied when creating a reading report using a medical image having a lung or liver as a diagnosis target, but the diagnosis target is not limited to the lung or liver. In addition to the lung, any part of the human body such as the heart, brain, kidney, and limbs can be used as a diagnosis target. In this case, a diagnosis guideline corresponding to the part of the diagnosis target may be acquired, and a corresponding part corresponding to the item of the diagnosis guideline in the reading report may be specified.

[0105] Also, in each of the above embodiments, for example, as the hardware structure of a processing unit (Processing Unit) that executes various processes such as the information acquisition unit 21, the analysis unit 22, the attention area specifying unit 23, the non-attention interest area specifying unit 24, the display control unit 25, the radiology report creation unit 26, and the communication unit 27, the following various processors (Processor) can be used. As described above, among the above various processors, in addition to the CPU, which is a general-purpose processor that executes software (program) and functions as various processing units, there are programmable logic devices (Programmable Logic Device: PLD) such as FPGA (Field Programmable Gate Array), which are processors whose circuit configuration can be changed after manufacturing, and dedicated electric circuits, which are processors having a circuit configuration specifically designed to execute specific processes such as ASIC (Application Specific Integrated Circuit).

[0106] One processing unit may be composed of one of these various processors, or may be composed of a combination of two or more processors of the same type or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Also, a plurality of processing units may be composed of one processor.

[0107] As an example of configuring a plurality of processing units with one processor, first, as represented by computers such as clients and servers, there is a form in which one processor is configured by a combination of one or more CPUs and software, and this processor functions as a plurality of processing units. Second, as represented by a system on chip (System On Chip: SoC), there is a form in which a processor that realizes the functions of an entire system including a plurality of processing units with one IC (Integrated Circuit) chip is used. Thus, as a hardware structure, the various processing units are configured using one or more of the above various processors.

[0108] Furthermore, as a hardware structure of these various processors, more specifically, an electric circuit (Circuitry) combined with circuit elements such as semiconductor elements can be used.

Explanation of Signs

[0109] 1 Medical information system 2 Imaging device 3 Reading WS 4 Diagnosis WS 5 Image server 6 Image DB 7 Report server 8 Report DB 10 Network 11 CPU 12 Medical image processing program 13 Storage 14 Display 15 Input device 16 Memory 17 Network I / F 18 Bus 20 Medical image processing device 21 Information acquisition unit 22 Analysis unit 22A, 22B Learning model 23 Region of interest specification unit 24 Non-target region of interest specification unit 25 Display control unit 26 Reading report creation unit 27 Communication unit 30A~30H Tomographic image 31 Left lung 32 Right lung 33 Liver 34, 35 Kidneys 50 Display screen 51 Image display area 52 Text display area 53 Annotation display area 41, 42, 43A, 43B, 44A~44C, 45, 46, 47A, 47B, 48, 55, 56, 59, 61, 62, 63, 63B, 64A, 64B, 65, 71, 72, 73, 74A, 74B, 75 Marks 57 Confirmation Button 58 Finalization Button 80~82 Display Screen 90 Cursor 91 Pleural Effusion 92 Pointer

Claims

1. At least one processor; The processor, Obtain medical image interpretation reports, Obtaining an analysis result by analyzing the image interpretation report; Identifying a region of interest that a user has focused on in the medical image based on a region of interest related to the analysis result and an input position of a finding in the image interpretation report; Identifying a region of interest that is not related to the analysis result as a non-attention region of interest that is a region of interest for a structure different from a structure related to the region of interest; A medical imaging device configured to display the non-attention region of interest on a display device.

2. At least one processor; The processor, Obtain medical image interpretation reports, By analyzing the image interpretation report, character information is obtained as an analysis result from a character string included in the image interpretation report; Identifying a region of interest associated with the analysis result as a region of interest noted by a user in the medical image; Identifying a region of interest that is not related to the analysis result as a non-attention region of interest that is a region of interest for a structure different from a structure related to the region of interest; A medical imaging device configured to display the non-attention region of interest on a display device.

3. The medical image processing apparatus according to claim 2 , wherein the processor acquires at least one piece of information regarding a position, a type, and a size of a lesion included in the image interpretation report as the character information.

4. The medical image processing device according to claim 1 , wherein the processor is configured to display the non-attention regions of interest by erasing detection results of regions of interest for structures related to the regions of interest from among the regions of interest.

5. The medical image processing apparatus according to claim 1 , wherein the processor is further configured to display the region of interest.

6. The medical imaging apparatus of claim 5 , wherein the processor is configured to display the non-attention regions of interest and the attention regions differently.

7. The medical image processing apparatus according to claim 1 , wherein the region of interest is a region of interest for a plurality of types of diseases.

8. The medical image processing apparatus according to claim 1 , wherein the region of interest is a region of interest for a plurality of types of organs.

9. The computer obtains the interpretation report of the medical image, Obtaining an analysis result by analyzing the image interpretation report; Identifying a region of interest that a user has focused on in the medical image based on a region of interest related to the analysis result and an input position of a finding in the image interpretation report; Identifying a region of interest that is not related to the analysis result as a non-attention region of interest that is a region of interest for a structure different from a structure related to the region of interest; The medical image processing method further comprises displaying the non-attention region of interest on a display device.

10. The computer obtains the interpretation report of the medical image, By analyzing the image interpretation report, character information is obtained as an analysis result from a character string included in the image interpretation report; Identifying a region of interest associated with the analysis result as a region of interest noted by a user in the medical image; Identifying a region of interest that is not related to the analysis result as a non-attention region of interest that is a region of interest for a structure different from a structure related to the region of interest; The medical image processing method further comprises displaying the non-attention region of interest on a display device.

11. Procedures for obtaining medical image interpretation reports; obtaining an analysis result by analyzing the image interpretation report; A step of identifying a region of interest that a user has focused on in the medical image based on a region of interest related to the analysis result and an input position of a finding statement in the image interpretation report; identifying regions of interest not related to the analysis results as non-attention regions of interest, which are regions of interest for structures different from the structures related to the regions of interest; and a procedure for displaying the non-attention region of interest on a display device.

12. Procedures for obtaining medical image interpretation reports; a step of analyzing the image interpretation report to obtain character information from a character string included in the image interpretation report as an analysis result; identifying a region of interest associated with the analysis result as a region of interest noted by a user in the medical image; identifying regions of interest not related to the analysis results as non-attention regions of interest, which are regions of interest for structures different from the structures related to the regions of interest; and a procedure for displaying the non-attention region of interest on a display device.

Images