Information processing apparatus, information processing method, and information processing program

Abstract

To provide an information processor, an information processing method and an information processing program for suppressing the deterioration of reading efficiency to a plurality of medical images photographed in one examination.SOLUTION: The information processing apparatus acquires a detection result of a lesion for a plurality of medical images obtained by imaging the same part at different timings in one examination, derives a detection rate of the lesion according to the number of medical images in which the same lesion is detected among the plurality of medical images, and performs control to display the detection result by changing a display mode of the detection result according to the detection rate or performs control to display the detection result and the detection rate.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Patent document 1 discloses a technology that determines the priority of lesion detection areas in medical images that have undergone detection processing for multiple types of lesions based on predetermined conditions, and changes the display format of the detection areas detected in the medical image depending on the priority. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2021-029387 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 determines the priority of lesion detection areas in the most recent medical images based on past examination results, so there is room for improvement in terms of preventing a decrease in the efficiency of interpretation of multiple medical images taken in a single examination.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to provide an information processing device, an information processing method, and an information processing program that can suppress a decrease in interpretation efficiency for multiple medical images taken in a single examination. [Means for solving the problem]

[0006] The information processing device of the first aspect includes at least one processor, which acquires lesion detection results for multiple medical images obtained by photographing the same area at different times during a single examination, derives a lesion detection rate according to the number of medical images in which the same lesion is detected among the multiple medical images, and controls the display of the detection results by changing the display mode according to the detection rate, or controls the display of the detection results together with the detection results.

[0007] In the information processing device of the second aspect, in the information processing device of the first aspect, the processor performs control to display the detection result using a line, and varies the display mode of the line representing the detection result depending on the detection rate.

[0008] In the information processing device of the third aspect, in the information processing device of the first aspect, the processor controls the display of the area of ​​the lesion detected from the medical image as the detection result in an identifiable manner, and changes the display mode of the area of ​​the lesion depending on the detection rate.

[0009] An information processing device of a fourth aspect is an information processing device of any one of the first to third aspects, in which the processor determines whether lesions detected in two or more medical images out of a plurality of medical images are the same lesion using the difference in the position of the lesions in the two or more medical images.

[0010] In a fifth aspect of the information processing method, a processor of an information processing device having at least one processor acquires lesion detection results for multiple medical images obtained by photographing the same area at different times during a single examination, derives a lesion detection rate according to the number of medical images in which the same lesion is detected among the multiple medical images, and performs control to display the detection results by changing the display mode of the detection results according to the detection rate, or performs control to display the detection rate together with the detection results.

[0011] The information processing program of the sixth aspect causes a processor of an information processing device having at least one processor to acquire lesion detection results for multiple medical images obtained by photographing the same area at different times in a single examination, derive a lesion detection rate according to the number of medical images in which the same lesion is detected among the multiple medical images, and perform control to display the detection results by changing the display mode of the detection results according to the detection rate, or to perform control to display the detection rate together with the detection results. [Effects of the Invention]

[0012] According to the present disclosure, it is possible to suppress a decrease in the efficiency of interpretation of multiple medical images captured in a single examination. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing a schematic configuration of a medical information system. [Figure 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of an information processing device. [Figure 3] FIG. 2 is a block diagram illustrating an example of a functional configuration of an information processing device. [Figure 4] FIG. 10 is a diagram illustrating an example of the number of lesions detected from a medical image. [Figure 5] FIG. 10 is a diagram illustrating an example of a lesion detected from a medical image. [Figure 6] FIG. 10 is a diagram illustrating an example of a display screen. [Figure 7] FIG. 10 is a diagram showing an example of a display screen according to a modified example. [Figure 8] FIG. 10 is a diagram showing an example of a display screen according to a modified example. [Figure 9] FIG. 10 is a diagram showing an example of a display screen according to a modified example. [Figure 10] 10 is a flowchart illustrating an example of medical image display processing. DETAILED DESCRIPTION OF THE INVENTION

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The present disclosure is also applicable to a program and a program product.

[0015] First, the configuration of a medical information system 1 according to this embodiment will be described with reference to Fig. 1. As shown in Fig. 1, the medical information system 1 includes an information processing device 10, an imaging device 12, and an image storage server 14. The information processing device 10, the imaging device 12, and the image storage server 14 are connected to each other in a communicable state via a wired or wireless network 18. The information processing device 10 is, for example, a computer such as a personal computer or a server computer.

[0016] The imaging device 12 is a device that captures an image of a diagnostic target region of a patient, which is an example of a subject, to generate a medical image representing the region. Examples of the imaging device 12 include a plain X-ray imaging device, an endoscope device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, and a PET (Positron Emission Tomography) device. In this embodiment, an example will be described in which the imaging device 12 is a CT device and the region to be imaged is the abdomen. That is, the imaging device 12 according to this embodiment generates a CT image of the patient's abdomen as a three-dimensional medical image consisting of multiple tomographic images. The medical image generated by the imaging device 12 is transmitted to the image storage server 14 via the network 18 and stored by the image storage server 14.

[0017] The image storage server 14 is a computer that stores and manages various data, and is equipped with a large-capacity external storage device and database management software. The image storage server 14 receives medical images generated by the imaging device 12 via the network 18 and stores the received medical images. The storage format of image data by the image storage server 14 and communication with other devices via the network 18 are based on protocols such as DICOM (Digital Imaging and Communication in Medicine).

[0018] Next, a hardware configuration of an information processing device 10 according to this embodiment will be described with reference to Fig. 2. As shown in Fig. 2, the information processing device 10 includes a CPU (Central Processing Unit) 20, a memory 21 as a temporary storage area, and a non-volatile storage unit 22. The information processing device 10 also includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and a mouse, and a network I / F (Interface) 25 connected to a network 18. The CPU 20, the memory 21, the storage unit 22, the display 23, the input device 24, and the network I / F 25 are connected to a bus 27. The CPU 20 is an example of a processor according to the disclosed technology.

[0019] The storage unit 22 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 22 serving as a storage medium stores an information processing program 30. The CPU 20 reads the information processing program 30 from the storage unit 22, expands it in the memory 21, and executes the expanded information processing program 30.

[0020] Furthermore, a plurality of medical images 32 are stored in the storage unit 22. For example, when a radiologist or other radiologist specifies the identification information of a patient and the identification information of an examination to be interpreted, a plurality of medical images 32 corresponding to the patient identification information and the examination identification information are acquired from the image storage server 14 via the network 18 and stored in the storage unit 22.

[0021] In this embodiment, an example will be described in which a group of tomographic images obtained by a single scan using a CT device is applied as the medical image 32. The group of tomographic images is obtained by reconstructing projection data obtained by irradiating a patient with radiation at multiple positions in a single scan using the CT device.

[0022] The plurality of medical images 32 are obtained by capturing the same region of the same patient at different times during a single examination. Specifically, the plurality of medical images 32 include a group of tomographic images captured by a CT device without administering a contrast agent to the patient (hereinafter referred to as "plain CT images"). The plurality of medical images 32 also include a group of tomographic images captured at different times after administering a contrast agent to the patient. Examples of the group of tomographic images captured after administering a contrast agent to the patient include a group of tomographic images in the early arterial phase (hereinafter referred to as "early arterial phase images"), a group of tomographic images in the late arterial phase (hereinafter referred to as "late arterial phase images"), a group of tomographic images in the portal venous phase (hereinafter referred to as "portal venous phase images"), and a group of tomographic images in the equilibrium phase (hereinafter referred to as "equilibrium phase images"), depending on the time elapsed since the start of administration of the contrast agent.

[0023] Next, the functional configuration of the information processing device 10 will be described with reference to Fig. 3. As shown in Fig. 3, the information processing device 10 includes an acquisition unit 40, a detection unit 42, a derivation unit 44, and a display control unit 46. The CPU 20 executes the information processing program 30, thereby functioning as the acquisition unit 40, the detection unit 42, the derivation unit 44, and the display control unit 46.

[0024] The acquisition unit 40 acquires a plurality of medical images 32 from the storage unit 22. The acquisition unit 40 may acquire a plurality of medical images 32 from the image storage server 14 via the network 18.

[0025] The detection unit 42 executes a lesion detection process on the multiple medical images 32 acquired by the acquisition unit 40. For example, the detection unit 42 inputs the medical images 32 to a trained model that receives a CT image as input and outputs a lesion detection result, the trained model being obtained by machine learning using a large amount of training data. The trained model outputs a lesion detection result corresponding to the input medical images 32. The detection unit 42 may execute a lesion detection process on the multiple medical images 32 using a known lesion detection algorithm.

[0026] The lesion detection results are expressed in the form of a heat map in which each pixel is assigned a confidence level, and an area containing consecutive pixels with a confidence level equal to or greater than a threshold is treated as a lesion area.

[0027] The derivation unit 44 acquires the lesion detection results for the multiple medical images 32 from the detection unit 42. Note that the lesion detection process for the multiple medical images 32 may be executed in advance by an external device. In this case, the lesion detection results may be stored in the image storage server 14 in association with each of the multiple medical images 32. In this case, the derivation unit 44 may acquire the lesion detection results for the multiple medical images 32 from the image storage server 14 via the network 18.

[0028] The derivation unit 44 derives a lesion detection rate according to the number of medical images 32 in which the same lesion is detected, based on the lesion detection results for the multiple medical images 32. A specific example of the process of deriving the lesion detection rate by the derivation unit 44 will be described with reference to Figures 4 and 5. Figure 4 shows the number of lesions detected in each of the multiple medical images 32. Figure 5 shows the lesions detected in the medical images 32 in which the lesions are detected, among the multiple medical images 32.

[0029] The derivation unit 44 derives, for each lesion, the ratio of the number of medical images 32 in which at least one lesion is detected to the number of medical images 32 in which the same lesion is detected, as the lesion detection rate. In the examples of FIGS. 4 and 5, the number of medical images 32 in which at least one lesion is detected is 4, and the number of medical images 32 in which lesion 1 is detected is 3. In this case, the derivation unit 44 derives the detection rate of lesion 1 as 0.75 (= 3 ÷ 4). Note that the denominator when deriving the detection rate may be the number of all medical images 32, including medical images 32 in which no lesion is detected. In this case, the derivation unit 44 derives the detection rate of lesion 1 as 0.6 (= 3 ÷ 5).

[0030] Similarly, the derivation unit 44 derives the detection rate of lesion 2 as 1.0 (=4÷4), and the detection rate of lesion 3 as 0.5 (=2÷4).

[0031] When deriving the lesion detection rate, the derivation unit 44 determines whether lesions detected in two or more medical images 32 out of the plurality of medical images 32 are the same lesion by using the difference in the positions of the lesions in the two or more medical images 32. For example, the derivation unit 44 treats the coordinates of the center of gravity of the lesion in the medical image 32 as the position of the lesion, and determines whether the distance between the positions of the lesions in the two or more medical images 32 is equal to or less than a threshold (for example, a distance equivalent to 10 [mm]), thereby determining whether the lesions are the same lesion.

[0032] The display control unit 46 controls the display of the lesion detection results on the display 23 by changing the display mode of the lesion detection results depending on the detection rate derived by the derivation unit 44. In this embodiment, the display control unit 46 controls the display of the lesion area detected from the medical image 32 as the lesion detection result in an identifiable manner, and changes the display mode of the lesion area depending on the lesion detection rate. Figure 6 shows an example of a screen displayed on the display 23 under the control of the display control unit 46. Figure 6 shows an example of a display when the interpreter specifies lesion 1 in the early arterial phase image as the subject of interpretation.

[0033] As shown in Fig. 6, the display control unit 46 performs control to display a plurality of medical images 32 side by side. Fig. 6 shows an example in which five images, namely, a plain CT image, an early arterial phase image, a late arterial phase image, a portal venous phase image, and an equilibrium phase image, are arranged in a tiled pattern and displayed on the display 23. The display control unit 46 also performs control to display a character string below each medical image 32 to identify the medical image 32.

[0034] The display control unit 46 also controls the display of the lesion area designated by the radiologist as the area to be interpreted by the radiologist in a predetermined transparency and a preset color (e.g., red), thereby enabling the lesion area to be displayed in a identifiable state superimposed on the medical image 32. In this case, the display control unit 46 lightens the color density as the detection rate of the lesion area decreases. This allows the radiologist to determine the percentage of the lesion to be interpreted that has been detected in the multiple medical images 32. In the example of FIG. 6, the area filled with diagonal lines indicates the lesion area.

[0035] The display control unit 46 also controls the display of a slider SD and a slider bar SB on the right side of each medical image 32. The slider bar SB is rectangular with its long sides extending in the vertical direction of the medical image 32 and its short sides extending in the horizontal direction, with the upper end of the slider bar SB representing the head side of the subject and the lower end representing the leg side. The slider SD also represents the cross-sectional position of the medical image 32 currently being displayed on the display 23. The radiologist moves the slider SD in the vertical direction to switch between cross-sectional images to be displayed on the display 23.

[0036] As shown in FIG. 7, the display control unit 46 may control the display of the lesion detection results using lines, and may vary the display mode of the lines representing the detection results depending on the detection rate derived by the derivation unit 44. FIG. 7 illustrates an example in which the display control unit 46 controls the display of a bounding box BB so as to surround the lesion, thereby controlling the display of the lesion detection results using lines. During this control, the display control unit 46 may vary the line thickness or type depending on the lesion detection rate. For example, the display control unit 46 may make the line of the bounding box BB thicker as the lesion detection rate increases.

[0037] Furthermore, the display control unit 46 may perform control to display the detection rate together with the lesion detection results, as shown in Fig. 8. Fig. 8 shows an example in which the interpreter specifies lesion 1 in the early arterial phase image, and the detection rate is displayed near a bounding box BB that represents the detection result of lesion 1 in the early arterial phase image.

[0038] 9, the display control unit 46 may perform control to display a mark M as a lesion detection result to the right of the slider bar SB, at a position in the vertical direction of the slider bar SB that corresponds to the tomographic position of the tomographic image in which the lesion is detected. This mark M allows the radiologist to grasp the tomographic position of the lesion. In this case, the display control unit 46 may change the display mode of the mark M depending on the detection rate. For example, the display control unit 46 may increase the size of the mark M as the detection rate increases.

[0039] The display control unit 46 may also perform control to highlight the outer frames of medical images 32 in which no lesions have been detected among the plurality of medical images 32. The display control unit 46 may also perform control to display on the display 23 only medical images 32 in which lesions have been detected among the plurality of medical images 32.

[0040] Next, the operation of the information processing device 10 will be described with reference to Fig. 10. The CPU 20 executes the information processing program 30, thereby executing the medical image display process shown in Fig. 10. The medical image display process is executed, for example, when an instruction to start execution is input by the radiologist.

[0041] 10, the acquisition unit 40 acquires a plurality of medical images 32 from the storage unit 22. In step S12, the detection unit 42 executes a lesion detection process on the plurality of medical images 32 acquired in step S10, as described above.

[0042] In step S14, the derivation unit 44 derives a lesion detection rate corresponding to the number of medical images 32 in which the same lesion is detected, based on the lesion detection results obtained in step S12 for the multiple medical images 32, as described above.

[0043] In step S16, as described above, the display control unit 46 performs control to change the display mode of the lesion detection results depending on the detection rate derived in step S16 and display the detection results on the display 23. When the processing of step S16 ends, the medical image display processing ends.

[0044] As described above, according to this embodiment, it is possible to suppress a decrease in the efficiency of interpretation of a plurality of medical images captured in a single examination.

[0045] In the above embodiment, a case has been described in which a plain CT image, an early arterial phase image, a late arterial phase image, a portal venous phase image, and an equilibrium phase image are applied as the multiple medical images 32, but the disclosed technology is not limited to this. For example, a configuration may be adopted in which multiple medical images obtained by dynamic breast MRI are applied as the multiple medical images 32. In this configuration example, the multiple medical images 32 include plain images obtained by imaging without administering a contrast agent to the patient, and early phase images and late phase images corresponding to the elapsed time from the start of contrast agent administration.

[0046] Furthermore, thick slice images and thin slice images of chest CT images may be applied as the multiple medical images 32. For example, thick slice images are a group of tomographic images with a slice thickness of 5 [mm], and thin slice images are a group of tomographic images with a slice thickness of 1 [mm].

[0047] Furthermore, in the above embodiment, for example, the following various processors can be used as the hardware structure of a processing unit that executes various processes such as each functional unit of the information processing device 10. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to execute specific processes, such as a programmable logic device (PLD) that is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0048] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0049] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0050] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0051] In the above embodiment, the information processing program 30 is pre-stored (installed) in the storage unit 22, but the present invention is not limited to this. The information processing program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The information processing program 30 may also be downloaded from an external device via a network. [Explanation of symbols]

[0052] 1 Medical Information System 10 Image processing device 12 Imaging equipment 14 Image storage server 18 Network 20 CPU 21 Memory 22 Memory section 23 Display 24 Input Devices 25 Network I / F 27 Bus 30 Information Processing Program 32 Medical Imaging 40 Acquisition Department 42 Detection unit 44 Derivation part 46 Display control unit BB Bounding Box M mark SB slider bar SD Slider

Claims

1. at least one processor; The processor: Obtaining lesion detection results for multiple medical images taken at different times of the same area during a single examination; deriving a lesion detection rate according to the number of medical images in which the same lesion is detected among the plurality of medical images; Control is performed to display the detection result in a different display mode depending on the detection rate, or control is performed to display the detection rate together with the detection result. Information processing device.

2. The processor: The detection result is displayed using a line, and the display mode of the line representing the detection result is changed according to the detection rate. The information processing device according to claim 1 .

3. The processor: Control is performed to display the lesion area detected from the medical image as the detection result in a distinguishable manner, and the display mode of the lesion area is changed depending on the detection rate. The information processing device according to claim 1 .

4. The processor: Determining whether or not the lesions detected in two or more of the plurality of medical images are the same lesion based on the difference in the positions of the lesions in the two or more medical images. The information processing device according to any one of claims 1 to 3.

5. An information processing device including at least one processor, Obtaining lesion detection results for multiple medical images taken at different times of the same area during a single examination; deriving a lesion detection rate according to the number of medical images in which the same lesion is detected among the plurality of medical images; Control is performed to display the detection result in a different display mode depending on the detection rate, or control is performed to display the detection rate together with the detection result. An information processing method that performs processing.

6. An information processing device including at least one processor, Obtaining lesion detection results for multiple medical images taken at different times of the same area during a single examination; deriving a lesion detection rate according to the number of medical images in which the same lesion is detected among the plurality of medical images; Control is performed to display the detection result in a different display mode depending on the detection rate, or control is performed to display the detection rate together with the detection result. An information processing program for executing processing.

Images