Image diagnostic support device, method of operating the image diagnostic support device, and program

Abstract

An image-diagnosis aiding device according to the present invention includes a processor and a memory, and can be carried with by a user. The processor executes: computer-aided diagnosis processing for a medical image; communication processing for receiving an image file including the medical image and accompanying information from an external device and transmitting information including the result of the computer-aided diagnosis processing to the external device; and personal-information deletion processing for deleting at least a portion of personal information from the image file.

Description

Technical Field

[0001] The technology of the present disclosure relates to an image diagnosis support device, an operation method of the image diagnosis support device, and a program.

Background Art

[0002] An image diagnosis support device that provides information useful for diagnosis, such as detection of lesions in a medical image, by executing an image analysis process for analyzing a medical image such as a radiation image by a computer is known. This image diagnosis support device is also called a computer-aided diagnosis (CAD) device.

[0003] The image diagnosis support device is configured as a stationary server and is connected to an image storage device such as a PACS (Picture Archiving and Communication Systems) via a network in a medical facility. Medical images taken by modalities such as a radiation imaging device are stored in the PACS. Then, the image diagnosis device executes CAD processing on a medical image based on a request from a terminal device operated by a doctor who performs diagnosis in a medical facility, for example, and transmits the execution result of the CAD processing to the terminal device that is the request source (Japanese Unexamined Patent Application Publication No. 2003-150714).

[0004] Further, Japanese Unexamined Patent Application Publication No. 2003-150714 discloses that, for example, an image diagnosis support device existing in a base hospital can be used by a regional hospital without an image diagnosis support device by connecting an image diagnosis device installed in a medical facility such as a base hospital and a terminal device of a regional hospital in a remote area via a network.

Summary of the Invention

Problems to be Solved by the Invention

[0005] In recent years, the need for medical diagnosis outside of hospitals, such as in disaster medicine or home healthcare, has increased, and portable modalities, such as portable radiography equipment, have been developed to meet this need. In such settings, there is a demand for the use of image diagnostic support devices to enable rapid medical diagnosis on-site.

[0006] However, in disaster medicine or home healthcare settings, it may not be possible to use networks such as the internet, making it difficult to remotely access image diagnostic support devices installed in facilities like those described in Japanese Patent Publication No. 2003-150714. Therefore, there is a need for image diagnostic support devices that can be used in disaster medicine or home healthcare settings.

[0007] Therefore, it is conceivable to make the image diagnostic support device portable so that it can be used in disaster medicine or home medical care settings. However, if the image diagnostic support device is portable, there is a risk of theft. The image diagnostic support device stores medical images, and the accompanying information of the medical images includes the patient's personal information, so there is a possibility that personal information may be leaked.

[0008] The purpose of this disclosure is to provide an image diagnostic support device, a method for operating the image diagnostic support device, and a program that can be used in disaster medicine or home medical care settings and that can prevent the leakage of personal information. [Means for solving the problem]

[0009] To achieve the above objectives, the image diagnostic support device of the present disclosure is an image diagnostic support device having a processor and memory and being portable by a user, wherein the processor performs computer-aided diagnostic processing on medical images, communication processing which receives an image file containing medical images and associated information from an external device and transmits information including the results of the computer-aided diagnostic processing to the external device, and personal information deletion processing which deletes at least a portion of personal information from the image file.

[0010] It is preferable for the processor to remove only personal information from the accompanying information.

[0011] The processor preferably removes personal information by converting the image file into image data that does not contain any accompanying information.

[0012] The processor preferably converts the image file into image data that does not contain any associated information, and then associates the converted image data with at least a portion of the associated information from which personal information has been removed.

[0013] The processor preferably performs computer-aided diagnostic processing using a pre-trained model that has been trained using medical images.

[0014] The processor preferably stores the image file, from which personal information has been removed, in memory in order to retrain the trained model.

[0015] The processor preferably deletes all image files received from external devices.

[0016] The processor preferably deletes all image files when the power is turned on.

[0017] The processor preferably deletes all image files in response to sending the results of the computer-aided diagnostic processing to an external device.

[0018] It is preferable that the processor deletes all image files containing the results of the computer-aided diagnostic processing after sending the results of the computer-aided diagnostic processing to an external device.

[0019] The operation method of the image diagnosis support device of the present disclosure is an operation method of an image diagnosis support device that can be carried by a user, and includes computer-aided diagnosis processing for medical images, receiving an image file including a medical image and attached information from an external device, and transmitting information including the result of the computer-aided diagnosis processing to the external device, and performing personal information deletion processing for deleting at least a part of the personal information from the image file.

[0020] The program of the present disclosure is a program for causing a processor to execute processing in an image diagnosis support device that has a processor and a memory and can be carried by a user, and includes computer-aided diagnosis processing for medical images, receiving an image file including a medical image and attached information from an external device, and transmitting information including the result of the computer-aided diagnosis processing to the external device, and causing the processor to perform personal information deletion processing for deleting at least a part of the personal information from the image file.

Advantages of the Invention

[0021] According to the technology of the present disclosure, it is possible to provide an image diagnosis support device, an operation method of the image diagnosis support device, and a program that can be used at the scene such as disaster medicine or home medicine and can prevent the leakage of personal information.

Brief Description of the Drawings

[0022] [Figure 1] It is a diagram showing an example of the configuration of an X-ray imaging system. [Figure 2] It is a block diagram showing an example of the hardware configuration of an X-ray imaging system. [Figure 3] It is a diagram showing an example of a console screen. [Figure 4] It is a diagram showing an example of the file format of an image file. [Figure 5] It is a diagram showing an example of personal information deletion processing. [Figure 6] It is a diagram conceptually showing an example of personal information deletion processing and CAD processing. [Figure 7]This is a diagram for explaining an example of a learning phase for training a detection model through machine learning. [Figure 8] This is a flowchart showing an example of the processing flow of an X-ray source, an electronic cassette, and a console. [Figure 9] This is a flowchart showing an example of the processing flow of an image diagnosis support device. [Figure 10] This is a flowchart showing a first modification example of personal information deletion processing. [Figure 11] This is a flowchart showing a second modification example of personal information deletion processing. [Figure 12] This is a flowchart showing a third modification example of personal information deletion processing. [Figure 13] This is a diagram showing an example of performing personal information deletion processing after CAD processing is performed. [Figure 14] This is a flowchart showing a first modification example of the processing of an image diagnosis support device. [Figure 15] This is a flowchart showing a second modification example of the processing of an image diagnosis support device.

Embodiments for Carrying Out the Invention

[0023] FIG. 1 shows an example of the configuration of an X-ray imaging system 2 that uses X-rays as radiation. The X-ray imaging system 2 that uses X-rays as radiation includes an X-ray source 10, an electronic cassette 20, a console 30, an image diagnosis support device 40, and a repeater 50. The console 30 communicates with the electronic cassette 20 and the image diagnosis support device 40 via the repeater 50. The repeater 50 functions as, for example, an access point.

[0024] The X-ray source 10 is an example of a radiation source that generates radiation. The electronic cassette 20 is an example of a radiation image detector that detects radiation and generates a radiation image. The image diagnosis support device 40 performs CAD processing to detect an area including an abnormal shadow from the radiation image.

[0025] <好 The X-ray source 10, electronic cassette 20, console 30, and image diagnostic support device 40 of this embodiment are all small, portable devices. The X-ray imaging system 2 can be carried to sites requiring emergency medical response, such as accidents and disasters, or to the homes of patients receiving home medical care, for X-ray imaging. With such a portable X-ray imaging system 2, the captured X-ray images can be immediately checked on-site, preventing the need for re-imaging requiring a follow-up visit. The X-ray image is an example of a "medical image" related to the technology of this disclosure.

[0026] In the X-ray imaging system 2, the electronic cassette 20 is positioned opposite the X-ray source 10. By placing the subject H between the X-ray source 10 and the electronic cassette 20, the area of ​​the subject H being examined (for example, the chest) can be X-rayed.

[0027] The X-ray source 10 is held by, for example, a holding device 60. The holding device 60 is, for example, a quadruped having four support legs 61 and a crossbar 62. The upper ends of the support legs 61 and both ends of the crossbar 62 are connected to a three-pronged joint 63, thereby assembling the holding device 60. The crossbar 62 is provided with a mounting fixture 64 for mechanically attaching the X-ray source 10. The X-ray source 10 is suspended by the mounting fixture 64 such that the direction of X-ray irradiation 4 is directed downwards.

[0028] An irradiation switch 11 is connected to the X-ray source 10 via cable 11A. A user such as a radiologist or physician using the X-ray imaging system 2 can start irradiating the X-ray source 10 with X-rays 4 by operating the irradiation switch 11.

[0029] The electronic cassette 20 has an automatic X-ray detection function that detects the start of irradiation of X-rays 4 emitted from the X-ray source 10. Therefore, the electronic cassette 20 does not need to be connected to the X-ray source 10. In addition, since the electronic cassette 20 has a built-in battery and wireless communication function, it does not need to be connected to a power supply or console 30 via a cable. The electronic cassette 20 is wirelessly connected to the repeater 50 and communicates with the console 30 via the repeater 50.

[0030] The console 30 is, for example, a personal computer and has a display unit 31 and an input operation unit 32. The console 30 is connected to the repeater 50 via, for example, a communication cable 51. The display unit 31 is a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The input operation unit 32 is an input device including a keyboard, mouse, or touch pad.

[0031] The user can input patient information and imaging conditions by operating the input unit 32. The display unit 31 shows the X-ray image received by the console 30 from the X-ray source 10. If the user observes the X-ray image and determines that CAD processing is necessary, they can input a request to execute CAD processing using the input unit 32.

[0032] The console 30 communicates with the image diagnostic support device 40 via the repeater 50. The console 30 sends a CAD processing request to the image diagnostic support device 40 in response to an operation signal input by the user via the input operation unit 32. At this time, the console 30 sends the X-ray image to the image diagnostic support device 40 along with the CAD processing request. When the console 30 receives the CAD processing result from the image diagnostic support device 40, it displays the X-ray image reflecting the CAD processing result on the display unit 31.

[0033] The image diagnostic support device 40 has a housing 41 that is small enough to be carried by the user. The housing 41 is, for example, a box-shaped case with a length, width, and height of 20 cm or less. The housing 41 is provided with a power switch 42, a first connector 43A, a second connector 43B, and a third connector 43C. For example, the first connector 43A is a terminal having a USB (Universal Serial Bus) Type A interface (hereinafter referred to as USB-A I / F). The second connector 43B is a terminal having a LAN (Local Area Network) interface (hereinafter referred to as LAN I / F). The third connector 43C is a terminal having a USB Type C interface (hereinafter referred to as USB-C I / F).

[0034] The housing 41 does not have a display for displaying X-ray images. Furthermore, the housing 41 does not have a user interface operated by the user for inputting information. A user interface would be, for example, physical operation buttons or a touch panel. Thus, the housing 41 can be miniaturized as described above because it does not have a display or a user interface. The housing 41 may also be equipped with a connector for connecting an external display (e.g., an HDMI® (High-Definition Multimedia Interface) terminal) and a connector for connecting an external keyboard or the like (e.g., a USB terminal).

[0035] The image diagnostic support device 40 is connected to the repeater 50 wirelessly or by wire. For example, by connecting a wireless dongle 70 to the first connector 43A, the image diagnostic support device 40 is wirelessly connected to the repeater 50. The wireless dongle 70 is, for example, a WiFi_USB adapter that enables communication via WiFi. When the wireless dongle 70 is connected to the first connector 43A, the image diagnostic support device 40 communicates with the console 30 via the repeater 50. The console 30 is an example of an "external device" related to the technology of this disclosure.

[0036] Furthermore, the second connector 43B is used when the image diagnostic support device 40 and the repeater 50 are connected via a LAN cable (not shown). When a LAN cable is connected between the second connector 43B and the repeater 50, the image diagnostic support device 40 communicates with the console 30 via the repeater 50.

[0037] The third connector 43C supports the USB_PD (Power Delivery) power supply standard. A mobile battery 80 can be connected to the third connector 43C via a USB cable 81 that supports USB_PD. The mobile battery 80 can supply power to the inside of the image diagnostic support device 40 and to the built-in battery of the image diagnostic support device 40. The mobile battery 80 supplies DC power to the image diagnostic support device 40.

[0038] Furthermore, the third connector 43C can also be connected to an AC (Alternating Current) adapter (not shown) instead of the mobile battery 80. The third connector 43C can be connected to the AC adapter via the USB cable 81, and the AC adapter can be connected to a commercial AC power source such as a household. This allows the image diagnostic support device 40 to receive power from a commercial AC power source converted to DC by the AC adapter.

[0039] Figure 2 shows an example of the hardware configuration of the X-ray imaging system 2. The X-ray source 10 comprises a processor 12, an input control unit 13, a built-in battery 14, a high-voltage generator 15, an X-ray tube 16, and an irradiation field limiter 17. The processor 12 functions as a control unit that controls the operation of the high-voltage generator 15 and the irradiation field limiter 17. The irradiation switch 11 described above is connected to the processor 12. The input control unit 13 is also connected to the processor 12. The input control unit 13 includes buttons for adjusting the imaging conditions to set the tube voltage and tube current of the X-ray tube 16, an irradiation field button to adjust the size of the irradiation field of the irradiation field limiter 17, and a power button, etc.

[0040] The processor 12 controls the high-voltage generator 15 and the irradiation field limiter 17 based on the setting conditions set by the input operation unit 13. The processor 12 generates a high voltage in the high-voltage generator 15 in response to the operation of the irradiation switch 11. The built-in battery 14 is a secondary battery such as a lithium polymer battery and can be charged via a connector (not shown).

[0041] The X-ray tube 16 is a fixed-anode type X-ray tube without a target rotation mechanism. The X-ray tube 16 consists of a cold cathode electron source that emits electrons, an electron accelerator, a target that generates X-rays 4 by electron collisions, and an outer tube that houses these components. The cold cathode electron source does not require a filament or a heater to heat it, as is the case with a hot cathode. Because the X-ray tube 16 does not have a target rotation mechanism, a filament, or a heater, it is small and lightweight. Furthermore, since the X-ray tube 16 does not require filament preheating, it is possible to generate X-rays 4 immediately in response to the irradiation start command.

[0042] The irradiation field limiter 17 limits the irradiation field of the X-rays 4 generated by the X-ray tube 16. The X-rays 4 generated by the X-ray tube 16 are irradiated onto the inspection area of ​​the subject H with the irradiation field limited by the irradiation field limiter 17. The X-rays 4 that have passed through the inspection area of ​​the subject H are incident on the electronic cassette 20.

[0043] The electronic cassette 20 comprises a processor 21, an X-ray detection panel 22, a memory 23, a communication interface 24, and a built-in battery 25. The processor 21 functions as a control unit that controls each part within the electronic cassette 20. The X-ray detection panel 22 is, for example, a flat panel detector having a matrix substrate in which multiple pixels, each consisting of thin-film transistors (TFTs) and X-ray detection elements, are arranged in two dimensions.

[0044] The X-ray detection panel 22 converts incident X-rays into charge using an X-ray detection element and stores it in the charge storage state when the TFT is turned off. Then, in the charge readout state when the TFT is turned on, the charge stored in the X-ray detection element is read out to the signal processing circuit. In the signal processing circuit, the readout charge is converted into a voltage signal using an integrating amplifier, and the converted voltage signal is converted to digital by an A / D converter to generate digital image data. Hereinafter, this image data will be referred to as the X-ray image XP.

[0045] Memory 23 is a non-volatile memory such as flash memory, and stores the X-ray image XP generated by the X-ray detection panel 22. The communication interface 24 is wirelessly connected to the repeater 50. The processor 21 transmits the X-ray image XP stored in memory 23 to the console 30 via the repeater 50. It is also possible to connect the electronic cassette 20 to the repeater 50 via a communication cable.

[0046] The built-in battery 25 is a rechargeable battery such as a lithium polymer battery, and can be charged via a connector (not shown).

[0047] The console 30 includes a display unit 31, an input operation unit 32, a processor 33, RAM (Random Access Memory) 34, non-volatile memory (NVM) 35, and a communication interface 36. The processor 33 is, for example, a CPU (Central Processing Unit). The RAM 34 is work memory for the processor 33 to execute processing. The NVM 35 is a storage device such as flash memory and stores the program 37.

[0048] The processor 33 loads the program 37 stored in the NVM 35 into the RAM 34 and executes processing according to the program 37, thereby functioning as a console control unit 38 that comprehensively controls each part of the console 30. The console control unit 38 displays a GUI (Graphical User Interface) screen on the display unit 31, enabling input of patient information and imaging conditions using the input operation unit 32. The console control unit 38 also displays the X-ray image XP received from the electronic cassette 20 on the display unit 31. The physician can make a diagnosis based on the X-ray image XP displayed on the display unit 31, but can also input a request to execute CAD processing using the input operation unit 32 in order to narrow down the candidates for abnormal shadows, including lesions, from the X-ray image XP.

[0049] Furthermore, the console control unit 38 creates an image file PF by adding supplementary information, including patient information and imaging conditions, to the X-ray image XP.

[0050] The communication interface 36 is wired to the repeater 50 via a communication cable 51 (see Figure 1). The console control unit 38 transmits the image file PF, which includes the X-ray image XP, along with the CAD processing request, to the image diagnostic support device 40 via the communication interface 36. It is also possible to connect the console 30 to the repeater 50 wirelessly. Furthermore, the console 30 may be, for example, a laptop computer equipped with a battery, or a mobile device such as a tablet or smartphone.

[0051] The image diagnostic support device 40 includes, within its housing 41, the aforementioned power switch 42, first connector 43A, second connector 43B, and third connector 43C, as well as a processor 44, RAM 45, NVM 46, power supply unit 47, and built-in battery 48. The processor 44 is composed of, for example, a CPU and a GPU (Graphics Processing Unit). The RAM 45 is work memory for the processor 44 to execute processing. The NVM 46 is a storage device such as flash memory and stores the program 90 and the detection model 91. The NVM 46 also stores data such as image files PF transmitted from the console 30. The NVM 46 is an example of "memory" related to the technology of this disclosure.

[0052] The processor 44 loads the program 90 stored in the NVM 46 into the RAM 45 and executes processing according to the program 90, thereby functioning as a communication processing unit 92, a personal information deletion processing unit 93, and a CAD processing unit 94.

[0053] The communication processing unit 92 controls communication with the console 30 via the first connector 43A or the second connector 43B. Specifically, the communication processing unit 92 receives the image file PF from the console 30 and performs communication processing to send information including the CAD processing results to the console 30. The personal information deletion processing unit 93 performs personal information deletion processing to delete personal information from the image file PF.

[0054] The CAD processing unit 94 performs CAD processing on the X-ray image XP contained in the image file PF using the detection model 91 stored in the NVM46. The detection model 91 is a trained model that has been trained using machine learning.

[0055] The detection model 91 is constructed using a neural network. For example, the detection model 91 is constructed using a deep neural network (DNN), which is a multilayer neural network targeted by deep learning. As the DNN, for example, a convolutional neural network (CNN) that targets images is used.

[0056] The power supply unit 47 supplies power from the mobile battery 80 via the third connector 43C to the processor 44 and the like. The power supply unit 47 includes, for example, a power supply circuit and a charging control circuit. The power supply circuit regulates the power supplied from the mobile battery 80 and supplies it to the processor 44 and the like. The charging control circuit controls the charging of the built-in battery 48 using power supplied from the mobile battery 80. The built-in battery 48 is a secondary battery such as a lithium polymer battery.

[0057] Figure 3 shows an example of a console screen displayed on the display unit 31 of the console 30 by the console control unit 38. The console screen 100 shown in Figure 3 is displayed on the display unit 31 after X-ray imaging is performed by the X-ray source 10 and the electronic cassette 20, and the console 30 receives the image from the electronic cassette 20. The console screen 100 is provided with an image display area 101 for displaying the X-ray image XP.

[0058] The console screen 100 also displays a shooting completion button 102 to complete the shooting, a next shooting button 103 to perform the next shooting, and a CAD processing button 104 to request CAD processing. To request CAD processing, the doctor or other user presses the CAD processing button 104 by operating the input operation unit 32, for example, with a mouse.

[0059] Furthermore, the console control unit 38 stores the X-ray image XP in the NVM46 as an image file PF in a format compliant with the DICOM (Digital Imaging and Communication in Medicine) standard, as shown in Figure 4. The image file PF is a file in which the X-ray image XP and the accompanying information AD are associated with a single image ID. The accompanying information AD includes patient information, reception number, examination site, imaging conditions, etc. Among the accompanying information AD of the image file PF shown in Figure 4, items 3 to 9 (patient name, patient ID, gender, date of birth, age, height, and weight) are the patient's personal information. Personal information refers to information unique to the person being diagnosed from whom the medical image was acquired. Personal information is not limited to the information shown in items 3 to 9.

[0060] Figure 5 shows an example of personal information deletion processing performed by the personal information deletion processing unit 93 of the image diagnostic support device 40. In this embodiment, the personal information deletion processing unit 93 generates an image file PFD from which personal information has been deleted by deleting all personal information contained in the supplementary information AD of the image file PF. In other words, the personal information deletion processing unit 93 deletes only personal information from the supplementary information AD.

[0061] In Figure 5, the personal information deletion processing unit 93 deletes the data of items 3 to 9 corresponding to personal information. The personal information deletion processing unit 93 may also add dummy data to items 3 to 9 from which personal information has been deleted. In other words, personal information may be deleted by replacing it with dummy data. In this embodiment, the image file PFD from which personal information has been deleted is a DICOM format file, just like the image file PF before the personal information was deleted.

[0062] Figure 6 conceptually illustrates an example of personal information deletion processing and CAD processing performed by the image diagnostic support device 40. When the communication processing unit 92 receives the image file PF from the console 30 along with a CAD processing request, the image file PF is input to the personal information deletion processing unit 93. The personal information deletion processing unit 93 deletes personal information from the image file PF using the personal information deletion processing described above. The image file PFD, from which personal information has been deleted by the personal information deletion processing unit 93, is input to the CAD processing unit 94.

[0063] The CAD processing unit 94 inputs the X-ray image XP contained in the image file PFD to the detection model 91. The detection model 91 detects the region containing abnormal shadows from the input X-ray image XP and outputs the detection result R. The detection result R includes location information of the region containing abnormal shadows within the X-ray image XP.

[0064] The CAD processing unit 94 generates a processed X-ray image XPC by performing image processing on the X-ray image XP based on the detection result R. For example, the CAD processing unit 94 generates a processed X-ray image XPC by superimposing a circular mark M surrounding the abnormal shadow on the X-ray image XP based on the detection result R. The CAD processing unit 94 transmits the processed X-ray image XPC to the console 30 via the communication processing unit 92 as a CAD processing result.

[0065] The CAD processing unit 94 may also send only information representing the detection result R to the console 30 as a result of CAD processing. In this case, the console 30 can perform image processing on the X-ray image XP based on the detection result R.

[0066] Figure 7 illustrates an example of a learning phase in which the detection model 91 is trained using machine learning. The detection model 91 is trained using training data TD. Training data TD includes multiple X-ray images XP as training images, each with a ground truth label L. The X-ray images XP included in training data TD are sample images containing various abnormal shadows. The ground truth label L is, for example, the location information of the abnormal shadow within the X-ray image XP.

[0067] During the learning phase, the detection model 91 receives an X-ray image XP as a training image. The detection model 91 outputs a detection result R based on the input X-ray image XP. Based on this detection result R and the correct label L, a loss calculation is performed using a loss function. Then, according to the result of the loss calculation, various coefficients (weight coefficients, bias, etc.) of the detection model 91 are updated, and the detection model 91 is updated according to the update settings.

[0068] During the learning phase, a series of processes are repeatedly performed: inputting training images into the detection model 91, outputting detection results R from the detection model 91, calculating loss, setting update parameters, and updating the detection model 91. This repetition of processes ends when the detection accuracy reaches a predetermined set level. The detection model 91, having reached the set level of detection accuracy, is then stored in the NVM 46 and used by the CAD processing unit 94 in the CAD processing, which is the operation phase (also called the inference phase).

[0069] The learning phase is performed, for example, on a different computer from the image diagnostic support device 40. The detection model 91 generated on the other computer is sent to the image diagnostic support device 40 and stored in the NVM 46. Alternatively, the learning phase may be performed within the image diagnostic support device 40.

[0070] Furthermore, during the learning phase, a detection model 91 may be generated for each examination site (chest, abdomen, etc.). In other words, the NVM 46 may store multiple detection models 91 generated for each examination site. In this case, the CAD processing unit 94 can refer to the examination site included in the accompanying information AD (see Figure 5) of the image file PFD to be processed by CAD and select the detection model 91 corresponding to the examination site.

[0071] Next, the operation of the X-ray imaging system 2 with the above configuration will be explained with reference to the flowcharts shown in Figures 8 and 9. Figure 8 shows an example of the processing flow of the X-ray source 10, electronic cassette 20, and console 30. Figure 9 shows an example of the processing flow of the image diagnostic support device 40.

[0072] Prior to imaging, the user, such as a physician, inputs imaging conditions and patient information to the X-ray source 10 and console 30. Next, the subject H is placed between the X-ray source 10 and the electronic cassette 20. Once the imaging preparation is complete, the user operates the irradiation switch 11 to start irradiating the X-ray source 10 with X-rays 4.

[0073] The processor 12 of the X-ray source 10 determines whether or not the irradiation switch 11 has been pressed by the user (step S10). If the processor 12 determines that the irradiation switch 11 has been pressed (step S10: YES), it generates a high voltage in the high voltage generator 15, thereby generating X-rays 4 in the X-ray tube 16 (step S11). As a result, X-rays 4 are irradiated from the X-ray source 10 to the electronic cassette 20 via the subject H.

[0074] The processor 21 of the electronic cassette 20 determines whether or not X-ray irradiation has been detected by the automatic X-ray detection function (step S20). If the processor 21 determines that X-ray irradiation has been detected (step S20: YES), it causes the X-ray detection panel 22 to generate an X-ray image XP (step S21). Then, the processor 21 transmits the X-ray image XP to the console 30 via the communication I / F 24 (step S22).

[0075] The console control unit 38 of the console 30 determines whether or not it has received the X-ray image XP from the electronic cassette 20 (step S30). If the console control unit 38 determines that it has received the X-ray image XP (step S30: YES), it displays the X-ray image XP on the console screen 100 (see Figure 3) (step S31). Next, the console control unit 38 determines whether or not the CAD processing button 104 has been pressed by the user (step S32). If the console control unit 38 determines that the CAD processing button 104 has not been pressed (step S32: NO), it terminates the process.

[0076] On the other hand, if the console control unit 38 determines that the CAD processing button 104 has been pressed (step S32: YES), it sends the image file PF along with the CAD processing request to the image diagnostic support device 40 (step S33). The console control unit 38 then determines whether or not it has received the CAD processing result from the image diagnostic support device 40 (step S34). If the console control unit 38 determines that it has received the CAD processing result from the image diagnostic support device 40 (step S34: YES), it displays the processed X-ray image XPC (see Figure 6) received as the CAD processing result from the image diagnostic support device 40 on the console screen 100 (step S35).

[0077] As shown in Figure 9, in the image diagnostic support device 40, the communication processing unit 92 determines whether or not it has received a CAD processing request from the console 30 (step S40). If the communication processing unit 92 determines that it has received a CAD processing request (step S40: YES), the personal information deletion processing unit 93 deletes personal information from the image file PF that the communication processing unit 92 received along with the CAD processing request (step S41).

[0078] Next, the CAD processing unit 94 performs CAD processing on the X-ray image XP contained in the image file PFD from which personal information has been removed (step S42). Here, the CAD processing unit 94 generates a processed X-ray image XPC by performing CAD processing using the detection model 91 (see Figure 6). Then, the communication processing unit 92 transmits the processed X-ray image XPC as a result of the CAD processing to the console 30 (step S43).

[0079] As described above, the X-ray imaging system 2 is portable by the user and includes an image diagnostic support device 40 that can be powered by a mobile battery 80, so it can be used in disaster medicine or home medical care settings to support image diagnostics. Support This can be done. The image diagnostic support device 40 is portable and therefore at risk of theft, but the image diagnostic support device 40 deletes personal information from the image file PF received from the console 30, thus preventing the leakage of personal information.

[0080] [Differentiation] Next, various modified examples of the X-ray imaging system 2 according to the above embodiment will be described.

[0081] In the above embodiment, the personal information deletion processing unit 93 deletes all personal information from the supplementary information AD of the image file PF, but it is sufficient to delete at least a portion of the personal information. For example, the personal information deletion processing unit 93 may delete only the information that can identify the person being diagnosed, from among the personal information unique to the person being diagnosed.

[0082] Figure 10 shows an example of deleting some personal information from the accompanying information AD of an image file PF. In the example shown in Figure 10, data for items other than "date of birth" and "age" from the personal information is deleted. In this case, for example, let's assume that NVM46 stores a detection model that supports pediatric diagnosis and a detection model that does not support pediatric diagnosis. The CAD processing unit 94 can determine whether or not to use the detection model that supports pediatric diagnosis by referring to the "age" contained in the accompanying information AD of the image file PFD from which the personal information has been deleted. For example, the CAD processing unit 94 will use the detection model that supports pediatric diagnosis if the age is under 15 years old.

[0083] The personal information deletion processing unit 93 may delete the personal information to be deleted from the accompanying information AD of the image file PF by referring to a table in which the personal information to be deleted is recorded. This table is stored, for example, in NVM46.

[0084] Furthermore, in the above embodiment, the personal information deletion processing unit 93 converts the DICOM format image file PF into a DICOM format image file PFD that does not contain personal information. Alternatively, the personal information deletion processing unit 93 may convert the image file PF into image data that does not contain the accompanying information AD by deleting all of the accompanying information AD of the image file PF. Figure 11 shows an example of converting the image file PF into image data that does not contain the accompanying information AD (i.e., X-ray image XP). For example, the personal information deletion processing unit 93 converts the DICOM format image file PF into image data such as BMP (bitmap) format or JPEG (Joint Photographic Experts Group) format.

[0085] Furthermore, the personal information deletion processing unit 93 may, after converting the image data to one that does not include the supplementary information AD, obtain at least a portion of the information from the supplementary information AD from which personal information has been deleted and associate it with the converted image data. For example, as shown in Figure 12, the personal information deletion processing unit 93 obtains information on the examination site, tube voltage, tube current, and irradiation time from the supplementary information AD, and associates these as text data with the BMP image data that does not include the supplementary information AD.

[0086] Furthermore, in the above embodiment, as shown in Figure 6, the personal information deletion processing unit 93 deletes personal information from the image file PF before inputting the image file PF to the CAD processing unit 94. In contrast, as shown in Figure 13, the personal information deletion processing unit 93 may delete personal information from the image file PF after CAD processing has been performed by the CAD processing unit 94.

[0087] In this case, the personal information deletion processing unit 93 may delete personal information by deleting all image files PF that have been received from the console 30 and processed by CAD. Alternatively, in this case, the personal information deletion processing unit 93 may delete the image files PF in response to the communication processing unit 92 sending the CAD processing results to the console 30.

[0088] Furthermore, as shown in the flowchart of Figure 14, step S41 may be executed after step S43. That is, the personal information deletion processing unit 93 may delete the image file PF after the communication processing unit 92 has sent the CAD processing result to the console 30. In this case, it is preferable that the personal information deletion processing unit 93 deletes all image files PF containing the CAD processing result.

[0089] Furthermore, when the personal information deletion processing unit 93 deletes the image file PF in response to or after sending the CAD processing results to the console 30, it is preferable to delete the entire image file PF, including the CAD processing results.

[0090] Alternatively, the image diagnostic support device 40 may retain the image file PF containing personal information by storing it in the NVM 46 after the communication processing unit 92 has transmitted the CAD processing results to the console 30. In this case, the image diagnostic support device 40 deletes the image file PF containing personal information when the power is turned off and then turned on again. Specifically, as shown in Figure 15, the personal information deletion processing unit 93 deletes the personal information by deleting all image files PF stored in the NVM 46 after the power is turned on in step S50 when the power switch 42 (Figures 1 and 2) is operated by the user (step S41).

[0091] Furthermore, the CAD processing unit 94 may store the image file PF from which personal information has been removed by the personal information removal processing unit 93 in the NVM46 in order to retrain the detection model 91. The image file PF from which personal information has been removed is stored in the NVM46 each time CAD processing is performed, and is accumulated as a training image.

[0092] Furthermore, in the above embodiment, in the learning phase (see Figure 7) in which the detection model 91 is trained by machine learning, the detection model 91 is trained using training data TD which includes the X-ray image XP and the correct label L. In addition, the detection model 91 may be trained using training data TD which includes a portion of personal information (for example, gender, age, height, and weight). In this case, the CAD processing unit 94 inputs a portion of the personal information to the detection model 91 in addition to the X-ray image XP during CAD processing.

[0093] In the above embodiment, the X-ray source 10 is portable, but the X-ray source 10 may be an X-ray source used in a general X-ray imaging system. In this case, the X-ray source 10 is held movably by, for example, a ceiling-mounted holding device. In a general X-ray imaging system, the electronic cassette 20 is used mounted on an imaging table.

[0094] Furthermore, the X-ray imaging system 2 may be a so-called mobile medical cart. In addition, the X-ray imaging system 2 may be a mammography device or a CT (Computed Tomography) device, etc.

[0095] Furthermore, the technology disclosed herein can be applied not only to X-rays but also to systems that use other types of radiation, such as gamma rays, to image subjects.

[0096] Furthermore, the image diagnostic support device 40 can also be applied to ultrasound imaging systems that generate images using ultrasound. In other words, the image diagnostic support device 40 may perform CAD processing on ultrasound images as medical images.

[0097] Furthermore, in the above embodiment, the CAD processing unit 94 performs CAD processing using a detection model 91, which is a trained model generated by machine learning. However, it is not limited to machine learning methods, and may be software that performs CAD processing by image analysis. Also, in the above embodiment, the CAD processing unit 94 detects abnormal shadows by CAD processing, but it may also detect areas other than abnormal shadows. For example, when the CAD processing unit 94 performs CAD processing on an ultrasound image, it may detect blood vessels from the ultrasound image.

[0098] Furthermore, in the above embodiment, the X-ray imaging system 2 is equipped with a repeater 50, but the repeater 50 is not essential, and the console 30 may also have the function of a repeater.

[0099] In the above embodiment, the hardware structure of the processing unit that performs various processes, such as the communication processing unit 92, the personal information deletion processing unit 93, and the CAD processing unit 94, is the following type of processor.

[0100] Various types of processors include CPUs, programmable logic devices (PLDs), and dedicated electrical circuits. A CPU, as is well known, is a general-purpose processor that executes software (programs) and functions as various processing units. A PLD, such as an FPGA (Field Programmable Gate Array), is a processor whose circuit configuration can be changed after manufacturing. Dedicated electrical circuits are processors with circuit configurations specifically designed to perform particular processing, such as an ASIC (Application Specific Integrated Circuit).

[0101] A single processing unit may be composed of one of these various processors, or it may be composed of a combination of two or more processors of the same or different types (for example, multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor. This is also possible. Examples of configuring multiple processing units with a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as multiple processing units. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC chip, as exemplified by System-on-a-Chip (SoC). Thus, various processing units are configured as hardware structures using one or more of the above-mentioned processors.

[0102] Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit composed of circuit elements such as semiconductor devices.

[0103] The present invention is not limited to the embodiments described above, and various configurations can be adopted as long as they do not depart from the spirit of the invention. Furthermore, the present invention extends not only to programs but also to computer-readable storage media for non-temporarily storing programs.

Claims

1. A diagnostic imaging support device having a processor and memory, and being portable by the user, The aforementioned processor, Computer-aided diagnostic processing of medical images, Communication processing that receives a computer-aided diagnostic processing request and an image file containing the medical image and associated information from the console, and transmits information including the results of the computer-aided diagnostic processing to the console, The system determines whether or not the computer-assisted diagnostic processing request has been received from the console, and if it determines that the computer-assisted diagnostic processing request has been received, it performs a personal information deletion process to delete at least a portion of the personal information from the image file. An image diagnostic support device that performs this function.

2. The processor deletes only personal information from the associated information. The image diagnostic support device according to claim 1.

3. The processor deletes personal information by converting the image file into image data that does not include the associated information. The image diagnostic support device according to claim 1.

4. The processor converts the image file into image data that does not include the associated information, and then associates the converted image data with at least a portion of the associated information from which personal information has been removed. The image diagnostic support device according to claim 1.

5. The processor performs the computer-aided diagnostic processing using a trained model that has been trained using the medical images. The image diagnostic support device according to any one of claims 1 to 4.

6. The processor stores the image file from which personal information has been removed in the memory in order to retrain the trained model. The image diagnostic support device according to claim 5.

7. The processor deletes all of the image files received from the console. The image diagnostic support device according to any one of claims 1 to 6.

8. The processor deletes all of the image files when the power is turned on. The image diagnostic support device according to claim 7, comprising:

9. The processor deletes all of the image files in response to sending the results of the computer-aided diagnostic process to the console. The image diagnostic support device according to claim 7.

10. After the processor transmits the results of the computer-aided diagnostic process to the console, it deletes all of the image files containing the results of the computer-aided diagnostic process. The image diagnostic support device according to claim 7.

11. A method for operating a portable image diagnostic support device, The processor, Computer-aided diagnostic processing of medical images, Communication processing that receives a computer-aided diagnostic processing request and an image file containing the medical image and associated information from the console, and transmits information including the results of the computer-aided diagnostic processing to the console, The system determines whether or not the computer-assisted diagnostic processing request has been received from the console, and if it determines that the computer-assisted diagnostic processing request has been received, it performs a personal information deletion process to delete at least a portion of the personal information from the image file. A method for operating an image diagnostic support device.

12. In an image diagnostic support device having a processor and memory and being portable by a user, a program that causes the processor to perform processing, Computer-aided diagnostic processing of medical images, Communication processing that receives a computer-aided diagnostic processing request and an image file containing the medical image and associated information from the console, and transmits information including the results of the computer-aided diagnostic processing to the console, The system determines whether or not the computer-assisted diagnostic processing request has been received from the console, and if it determines that the computer-assisted diagnostic processing request has been received, it performs a personal information deletion process to delete at least a portion of the personal information from the image file. A program that causes the aforementioned processor to execute.

Images