Program, information processing device and information processing method

Abstract

Provided are a program and the like capable of suitably estimating the cause of an image failure occurring in a medical image.　This program acquires a medical image generated according to a signal detected by a catheter, calculates a feature amount of a partial region that includes a part in the acquired medical image or of a major part region which is larger than the partial region, and causes a computer to execute processing for estimating, on the basis of the calculated feature amount, the presence or absence and the cause of an image failure for the medical image.

Description

[Technical Field]

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

[0002] Medical imaging diagnostic devices that image the inside of the human body, such as ultrasound diagnostic devices, X-ray photography devices, and X-ray CT devices, are widely used, and methods have been proposed for detecting malfunctions, damage, etc. of these imaging diagnostic devices. For example, Patent Document 1 discloses a medical imaging device malfunction diagnosis support device that compares medical images obtained from medical imaging devices with typical images in which abnormal phenomena occur due to device malfunctions, etc., and displays symptomatic cases if abnormal phenomena occur. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-172434 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the invention of Patent Document 1 detects abnormalities simply by pattern matching with a typical image, and does not suitably estimate failures, damage, etc. of the image diagnostic device.

[0005] An object of the present disclosure is to provide a program or the like that can suitably estimate the cause of image defects that occur in medical images. [Means for solving the problem]

[0006] A program according to one aspect of the present disclosure acquires a medical image generated based on a signal detected by a catheter, calculates features of a partial area including a part of the acquired medical image or a large area larger than the partial area, and causes a computer to execute a process of estimating the presence or absence of an image defect in the medical image and the cause thereof based on the calculated features. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to suitably estimate the cause of image defects occurring in medical images. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of the configuration of an image diagnostic system. [Figure 2] FIG. 1 is a block diagram illustrating an example of the configuration of an information processing device. [Figure 3] FIG. 1 is an explanatory diagram regarding image defects that occur in an image diagnostic apparatus. [Figure 4A] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 4B] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 4C] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 5A] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 5B] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 5C] FIG. 10 is an explanatory diagram of a method for estimating the cause of an image defect. [Figure 6] 10 is a flowchart illustrating an example of a processing procedure executed by an information processing device. [Figure 7] FIG. 2 is an explanatory diagram showing an example of a display screen of the imaging diagnostic apparatus. DETAILED DESCRIPTION OF THE INVENTION

[0009] The present invention will be specifically described with reference to the drawings showing embodiments thereof.

[0010] (First embodiment) Fig. 1 is an explanatory diagram showing an example of the configuration of an image diagnostic system. In this embodiment, an image diagnostic system will be described that estimates the presence or absence of image defects and their causes due to improper use or damage of an image diagnostic device 2 from medical images acquired from the image diagnostic device 2. The image diagnostic system includes an information processing device 1 and an image diagnostic device 2. The information processing device 1 and the image diagnostic device 2 are communicatively connected via a network N such as a LAN (Local Area Network) or the Internet.

[0011] The diagnostic imaging device 2 is a device unit for imaging the hollow organs of a subject. The diagnostic imaging device 2 is a device unit for generating medical images including ultrasonic tomographic images of the subject's blood vessels by, for example, an intravascular ultrasound (IVUS) method using a catheter 21, and for performing intravascular ultrasound examination and diagnosis. The diagnostic imaging device 2 includes the catheter 21, an MDU (Motor Drive Unit) 22, an image processing device 23, and a display device 24.

[0012] The catheter 21 is an imaging diagnostic catheter for obtaining an ultrasonic tomographic image of a blood vessel by the IVUS method. The ultrasonic tomographic image is an example of a catheter image generated using the catheter 21. The catheter 21 has a probe portion 211 and a connector portion 212 disposed at the end of the probe portion 211. The probe portion 211 is connected to the MDU 22 via the connector portion 212. A shaft 213 is inserted inside the probe portion 211. A sensor 214 is connected to the tip side of the shaft 213.

[0013] The sensor 214 is an ultrasonic transducer. The sensor 214 transmits ultrasonic waves based on a pulse signal within the blood vessel, and receives waves reflected by the biological tissue of the blood vessel or by a medical device. The shaft 213 and the sensor 214 are configured to be movable within the probe unit 211 in the longitudinal direction of the blood vessel while rotating in the circumferential direction of the blood vessel.

[0014] The MDU 22 is a drive unit to which the catheter 21 is detachably attached. The MDU 22 controls the operation of the catheter 21 inserted into the blood vessel by driving a built-in motor in response to operation by the user. The MDU 22 rotates the shaft 213 and the sensor 214 in the circumferential direction while moving them longitudinally from the distal end to the proximal end. The sensor 214 continuously scans the inside of the blood vessel at predetermined time intervals and outputs reflected wave data of the detected ultrasound to the imaging diagnostic device 2.

[0015] The image processing device 23 is a processing device that generates ultrasonic tomographic images (medical images) of blood vessels based on reflected wave data output from the ultrasonic probe of the catheter 21. The image processing device 23 generates one image per rotation of the sensor 214. The generated image is a transverse image centered on the probe portion 211 and approximately perpendicular to the probe portion 211. The image processing device 23 successively generates multiple transverse images at predetermined intervals by a pullback operation that rotates the sensor 214 while pulling it toward the MDU 22 at a constant speed. The image processing device 23 displays the generated ultrasonic tomographic images on the display device 24 and also includes an input interface for receiving input of various setting values ​​when performing an examination.

[0016] The display device 24 is a liquid crystal display panel, an organic EL (Electro Luminescence) display panel, etc. The display device 24 displays the medical images generated by the image processing device 23, the estimation results received from the information processing device 1, etc.

[0017] In this embodiment, intravascular examination is described as an example, but the luminal organ to be examined is not limited to a blood vessel and may be, for example, an internal organ such as the intestine. Furthermore, the catheter 21 may be a catheter for generating optical tomographic images, such as for OCT (Optical Coherence Tomography) or OFDI (Optical Frequency Domain Imaging), which generate optical tomographic images using near-infrared light. In this case, the sensor 214 is a transceiver that emits near-infrared light and receives reflected light. The catheter 21 may have both an ultrasonic transducer and an OCT or OFDI transceiver 214, and may be used to generate catheter images including both ultrasonic tomographic images and optical tomographic images.

[0018] The information processing device 1 is an information processing device capable of various information processing and transmitting and receiving information, and is, for example, a server computer, a personal computer, etc. The information processing device 1 may be a local server installed in the same facility (hospital, etc.) as the image diagnostic device 2, or may be a cloud server communicatively connected to the image diagnostic device 2 via the Internet, etc. The information processing device 1 functions as an estimation device that estimates the presence or absence of image defects and their causes from medical images generated by the image diagnostic device 2. The information processing device 1 provides the estimation results to the image diagnostic device 2.

[0019] 2 is a block diagram showing an example of the configuration of the information processing device 1. The information processing device 1 includes a control unit 11, a main memory unit 12, a communication unit 13, and an auxiliary memory unit 14. The information processing device 1 may be a multi-computer consisting of multiple computers, or may be a virtual machine virtually constructed by software.

[0020] The control unit 11 has one or more arithmetic processing devices such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), etc., and performs various information processing, control processing, etc. by reading and executing a program P stored in the auxiliary storage unit 14. The main storage unit 12 is a temporary storage area such as an SRAM (Static Random Access Memory), a DRAM (Dynamic Random Access Memory), or a flash memory, and temporarily stores data necessary for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information to and from the outside.

[0021] The auxiliary storage unit 14 is a non-volatile storage area such as a large-capacity memory or a hard disk. The auxiliary storage unit 14 stores programs and data referenced by the control unit 11, including the program P. The auxiliary storage unit 14 may be an external storage device connected to the information processing device 1.

[0022] The program P may be written to the auxiliary storage unit 14 during the manufacturing stage of the information processing device 1, or may be distributed by a remote server device and acquired by the information processing device 1 via communication and stored in the auxiliary storage unit 14. The program P may be readably recorded on a recording medium 1a such as a magnetic disk, an optical disk, or a semiconductor memory.

[0023] In this embodiment, the information processing device 1 is not limited to the above configuration, and may include, for example, an input unit that accepts operation input, a display unit that displays images, and the like.

[0024] FIG. 3 is an explanatory diagram of image defects that occur in the diagnostic imaging device 2. Various image defects can occur in medical images captured by the diagnostic imaging device 2 due to improper use, damage, or malfunction of the diagnostic imaging device 2. If an image defect occurs during use of the diagnostic imaging device 2, it is preferable to eliminate the cause of the image defect, as this may hinder accurate diagnosis. The time required for analyzing the cause of the image defect and taking appropriate measures to eliminate it increases the total surgical time for endovascular treatment. This embodiment focuses particularly on image defects that occur before the examination and supports efficient elimination of the cause of image defects before the examination begins. An example of an image defect that is the target of estimation in this embodiment will be described based on FIG. 3. FIG. 3 illustrates typical image defects that occur in the diagnostic imaging device 2, contrasted with the location of the cause of the image defect.

[0025] Poor images may be caused by, for example, an air trap, a broken wire in the shaft 213 inside the catheter 21, a poor connection between the catheter 21 and the MDU 22, or a malfunction of the MDU 22.

[0026] Image defects caused by air traps occur when air bubbles remain in the air trap at the tip of the catheter 21. If air bubbles in the air trap are not sufficiently removed by priming before the examination, the bubbles will attenuate the ultrasound, causing part or all of the image to become dark. Furthermore, if air bubbles are present on the sensor 214 (vibrator) at the tip side of the shaft 213, a phenomenon occurs in which dark parts of the image rotate in accordance with the rotation of the shaft 213. Note that in Figure 3, for convenience, the darkened parts of the image are shown hatched.

[0027] If the shaft 213 inside the catheter 21 breaks, the entire image will darken and the ring-down (a white ring-shaped image that appears near the center of the image) near the center will disappear. There are various reasons for a break, but for example, when the catheter 21 is inserted into a stenosis in a blood vessel (a region narrowed by plaque or the like), the shaft 213 will kink (become bent, twisted, crushed, etc.). If the catheter 21 is forcibly moved back and forth while the shaft 213 is kinked, there is a risk of the shaft breaking.

[0028] If there is a connection failure between the catheter 21 and the MDU 22, the entire image may become dark, or a radial or sandstorm-like image (hereinafter collectively referred to as "sandstorm") may appear. Also, due to a malfunction of the MDU 22 (for example, a malfunction of the encoder, a loose ferrite core, etc.), the entire image may become dark, or the brightness of a part of the image (the hatched area shown at the bottom right in Figure 3) may become high.

[0029] The information processing device 1 estimates the presence or absence of the above-mentioned image defects and their causes (types) from the medical images, and outputs the estimation results via the image diagnostic device 2. Note that the above-mentioned image defects and their causes are merely examples and are not limited to the above.

[0030] Figures 4 and 5 are explanatory diagrams of a method for estimating the cause of an image defect. Figure 4 is a diagram showing an image region related to the estimation method. Figure 5 is a diagram showing a graph of brightness values ​​related to the estimation method. The method for estimating the cause of an image defect will be specifically described using Figures 4 and 5.

[0031] A user of the imaging diagnostic device 2 performs a single pullback operation on the catheter 21 before an examination, i.e., before inserting the catheter 21 into the subject. The imaging diagnostic device 2 generates a medical image including multiple frames in response to a single pullback operation. The control unit 11 of the information processing device 1 acquires the medical image from the imaging diagnostic device 2 and estimates the presence or absence of an image defect and its cause based on the luminance values ​​of pixels included in various regions of the acquired medical image.

[0032] As described above, the medical image (tomographic image) obtained by the IVUS method is an image obtained by rotating the sensor 214, and therefore is a circular image centered on the axis of rotation. The control unit 11 identifies the cause of the image defect by calculating the brightness value in an image region that includes a part or the whole of the circular image and that differs depending on the type of image defect to be estimated.

[0033] First, the sum of the luminance values ​​(first feature X1) of each pixel included in a first region 31, which is a portion of a medical image in one frame, is calculated. FIG. 4A shows the first region 31, which includes a portion of the medical image, hatched. In the example of FIG. 4A, the first region 31 is an annular region including the periphery of a circular image. In a normal state before the examination, there are few factors that reflect ultrasound waves in the surrounding area, so the luminance value of the first region 31 is low. On the other hand, if sandstorms due to poor connections are present, the luminance value of the first region 31 is high. Therefore, if the first feature X1 is equal to or greater than a predetermined value (first threshold T1), it is estimated that the medical image contains an image defect and that the cause of the image defect is poor connections that result in sandstorms. In this embodiment, an example is described in which estimation is based on the luminance value of the first region 31 for any one frame. However, estimation may also be based on the sum of the luminance values ​​of the first region 31 for all frames.

[0034] Although the position and shape of the first region 31 described above are not limited to the example in Fig. 4A, it is preferable to make it a region including the edge of the circular image, from the viewpoint that the luminance value is more likely to be lower in the region having fewer reflection factors than in the center, where the luminance value is more likely to be higher due to ring-down, etc. In addition, by making it annular in shape, it is possible to equalize the luminance value in the circumferential direction.

[0035] Next, the sum of the luminance values ​​of each pixel included in the second region 32, which is the majority region of the medical image, for all frames (second feature X2) is calculated. The majority region is a region that includes a range wider than a partial region of the medical image, for example, the entire region including the entire medical image. In FIG. 4B, the second region 32 including the entire medical image is indicated by hatching. In the example of FIG. 4B, the entire area excluding the central sensor 214 is defined as the second region 32, but the entire interior of the circular image including the sensor 214 may also be defined as the second region.

[0036] The large region is not limited to one that includes the entire medical image, but may be any region that includes most of the medical image. The large region may be any region that is larger than a portion of the medical image and that includes a range in which a feature value that has a high correlation with the feature value of the entire medical image can be calculated.

[0037] The second feature amount X2 is not limited to being calculated for all frames of the medical image, but may be calculated for a plurality of frames selected by, for example, preprocessing from among all frames of the medical image acquired from the image diagnostic apparatus 2.

[0038] FIG. 5A is a graph showing the luminance value (second feature value X2) of the second region 32 for each frame depending on whether or not there is an image defect. The vertical axis of FIG. 5A represents the second feature value X2, and the horizontal axis represents the frame. For example, as shown in FIG. 5A, when there is no image defect and the image is normal, the second feature value X2 is greater than a predetermined value (second threshold value T2) and remains substantially constant for all frames. On the other hand, when there is an image defect due to a connection defect or disconnection, the second feature value X2 is smaller than the predetermined value for all frames. Furthermore, when there is an image defect due to an air trap, the value of the second feature value X2 changes for each frame. For example, the second feature value X2 for a frame in which an air bubble is present is smaller than the predetermined value, and the second feature value X2 for a frame in which no air bubble is present is greater than the predetermined value. Therefore, when the second feature value X2 for all frames is equal to or greater than the predetermined value (second threshold value T2), it is estimated that there is no image defect and the image is normal. The fifth threshold value in FIG. 5A will be described later.

[0039] If the second feature value X2 in all frames is not equal to or greater than the predetermined value, i.e., if the second feature value X2 in any frame is less than the predetermined value, it is determined that there is an image defect. In this case, the cause of the image defect is further identified based on the amount of change in various luminance values.

[0040] First, the presence or absence of air traps is determined based on the sum of the luminance values ​​(third feature X3) of each pixel included in a third region 33, which is a partial region of the medical image, in all frames. FIG. 4C shows the third region 33, which includes part of the medical image, by hatching. As shown in the figure, the third region 33 is part of a circular image and is a sector-shaped region with a central angle θ and a radius r. The radius r of the sector is approximately the same as the radius of the circle. The third region 33 is an area that has the same position and shape in all frames. FIG. 4C shows an example where the central angle θ is 30°.

[0041] FIG. 5B is a graph showing the brightness value (third feature X3) of the third region 33 for each frame depending on whether or not there is an image defect. The vertical axis of FIG. 5B represents the third feature X3, and the horizontal axis represents the frame. As described above, if an air bubble is present on the sensor 214 (vibrator), a portion of the image periodically darkens as the sensor 214 rotates. Therefore, as shown in FIG. 5B, the value of the third feature X3 changes for each frame when there is an image defect due to an air trap. On the other hand, the third feature X3 when there is an image defect due to a connection defect or disconnection is approximately constant and small for all frames. When there is no image defect and the image is normal, the third feature X3 is approximately constant and large for all frames.

[0042] Therefore, if the difference between the maximum and minimum values ​​of the third feature amount X3 in multiple frames obtained by one pullback operation is equal to or greater than a predetermined value (third threshold T3), the medical image has an image defect, and the cause of the image defect is estimated to be an air trap where an air bubble exists on the sensor 214. If the difference between the maximum and minimum values ​​of the third feature amount X3 is not equal to or greater than the predetermined value (third threshold T3), the medical image has an image defect, and the cause of the image defect is estimated to be a poor connection or a broken wire.

[0043] Furthermore, based on the second feature amount X2 for all frames, the presence or absence of an air trap is estimated except for when an air bubble is present on the sensor 214. Specifically, for each of the multiple frames obtained by one pullback operation, the difference (fourth feature amount X4) between the second feature amount X2 of the previous and next frames in the time series is calculated.

[0044] FIG. 5C is a graph showing the difference (fourth feature X4) in the second feature X2 between frames before and after the image defect for each frame depending on whether or not there is an image defect. The vertical axis of FIG. 5C represents the fourth feature X4, and the horizontal axis represents the frame. As described above, the second feature X2 decreases in frames in which an air bubble is present, and increases in frames in which no air bubble is present (see FIG. 5A). Thus, as shown in FIG. 5C, the value of the fourth feature X4 when there is an image defect due to an air trap changes significantly between a frame in which an air bubble is present and the frame before or after the frame in which the air bubble is present. On the other hand, the fourth feature X4 when there is an image defect due to a connection failure or disconnection remains approximately constant.

[0045] Therefore, if the maximum value of the fourth feature amount X4 among multiple frames obtained by one pullback operation is equal to or greater than a predetermined value (fourth threshold T4), the medical image has an image defect, and the cause of the image defect is estimated to be an air trap where no air bubbles exist on the sensor 214. If the maximum value of the fourth feature amount X4 is not equal to or greater than the predetermined value (fourth threshold T4), the medical image has an image defect, and the cause of the image defect is estimated to be a poor connection or a broken wire.

[0046] If it is determined that the cause of the image defect is not an air trap, it is further determined whether the cause of the image defect is a poor connection or a broken connection. This determination is made based on the second feature value X2 for all frames. As shown in FIG. 5A, when the cause of the image defect is a broken connection, the second feature value X2 is smaller than a predetermined value (fifth threshold T5) and is a substantially constant value for all frames. On the other hand, when the cause of the image defect is a poor connection, the second feature value X2 is larger than the predetermined value (fifth threshold T5) and is a substantially constant value for all frames. Therefore, when the second feature value X2 for all frames is equal to or greater than the predetermined value (fifth threshold T5), it is determined that the medical image contains an image defect and that the cause of the image defect is a poor connection other than static. When the second feature value X2 for all frames is not equal to or greater than the predetermined value (fifth threshold T5), it is determined that the medical image contains an image defect and that the cause of the image defect is a broken connection.

[0047] In the above, an example was described in which the sum of the luminance values ​​of the pixels contained in each corresponding region was calculated as each feature, but the method of calculating each feature is not limited thereto, and for example, the average luminance values ​​of the pixels contained in each corresponding region may be calculated.

[0048] The information processing device 1 uses the rule-based method described above to estimate the presence or absence of image defects and their causes based on various feature quantities. The information processing device 1 outputs the estimation results to the image diagnostic device 2. Note that, in this embodiment, the estimation results are described as being output to the image diagnostic device 2, but it goes without saying that the estimation results may be output to a device (e.g., a personal computer) other than the image diagnostic device 2 from which the medical images were acquired.

[0049] 6 is a flowchart showing an example of a processing procedure executed by the information processing device 1. For example, before an examination, when the MDU 22 executes a pullback operation and a medical image is output from the image diagnostic device 2, the control unit 11 of the information processing device 1 executes the following processing in accordance with the program P.

[0050] The control unit 11 of the information processing device 1 acquires a medical image from the image diagnostic device 2 (step S11). The medical image includes multiple frames generated by one pullback operation.

[0051] The control unit 11 calculates the sum of the luminance values ​​(first feature value X1) of each pixel included in a first region 31, which is a partial region of the medical image, for any one of the multiple frames (step S12). The first region 31 is, for example, an annular region including the periphery of a circular image. The control unit 11 determines whether the calculated first feature value X1 is larger or smaller than a preset first threshold value T1, and determines whether the calculated first feature value X1 is smaller than the first threshold value T1 (step S13).

[0052] If it is determined that the first feature amount X1 is not less than the first threshold value T1, that is, if it is determined that the first feature amount X1 is equal to or greater than the first threshold value T1 (S13: NO), the control unit 11 estimates that the medical image has an image defect and that the cause of the image defect is a connection defect resulting in the appearance of static (step S14).Then, the control unit 11 proceeds to step S27.

[0053] If it is determined that the first feature amount X1 is less than the first threshold value T1 (S13: YES), the control unit 11 calculates the sum of the luminance values ​​(second feature amount X2) of each pixel included in the second region 32, which is the entire region (large region) of the medical image, for all frames (step S15).The control unit 11 determines whether the calculated second feature amount X2 for all frames is larger than a preset second threshold value T2, and determines whether the calculated second feature amount X2 for all frames is equal to or larger than the second threshold value T2 (step S16).

[0054] If it is determined that the second feature X2 for all frames is not equal to or greater than the second threshold T2 (S16: NO), the control unit 11 calculates the sum of the luminance values ​​of each pixel included in a sector-shaped third region 33, which is a partial region of the medical image, for all frames (third feature X3) (step S17). Furthermore, the control unit 11 extracts the maximum and minimum values ​​from the third feature X3 for all frames and calculates the difference between the extracted maximum and minimum values. The control unit 11 determines whether the difference between the maximum and minimum values ​​of the third feature X3 is larger or smaller than a preset third threshold T3, and determines whether the calculated difference between the maximum and minimum values ​​of the third feature X3 is smaller than the third threshold T3 (step S18).

[0055] If it is determined that the difference between the maximum and minimum values ​​of the third feature amount X3 is not less than the third threshold value T3, i.e., that the difference between the maximum and minimum values ​​of the third feature amount X3 is equal to or greater than the third threshold value T3 (S18: NO), the control unit 11 estimates that the medical image has an image defect and that the cause of the image defect is an air trap (step S19). More specifically, it estimates that the cause is an air trap where an air bubble exists above the sensor 214. The control unit 11 then proceeds to step S27.

[0056] The control unit 11 also generates a subprocess and performs the processing of step S20 in parallel with the processing of step S17 and subsequent steps. For all frames, the control unit 11 calculates the difference in the second feature amount X2 between two adjacent frames in time series, i.e., the difference in the second feature amount X2 between previous and next frames in time series (fourth feature amount X4) (step S20). Furthermore, the control unit 11 extracts the maximum value from the fourth feature amounts X4 between all frames. The control unit 11 determines whether the maximum value of the extracted fourth feature amount X4 is larger than a preset fourth threshold value T4, and determines whether the maximum value of the extracted fourth feature amount X4 is smaller than the fourth threshold value T4 (step S21).

[0057] If it is determined that the maximum value of the fourth feature amount X4 is not less than the fourth threshold value T4, i.e., that the maximum value of the fourth feature amount X4 is equal to or greater than the fourth threshold value T4 (S21: NO), the control unit 11 estimates that the medical image has an image defect and that the cause of the image defect is an air trap (step S22). More specifically, it determines that the cause is an air trap, which means that no air bubbles exist above the sensor 214. The control unit 11 then proceeds to step S27.

[0058] If the difference between the maximum and minimum values ​​of the third feature amount X3 is less than the third threshold value T3 (S18: YES), or if the maximum value of the fourth feature amount X4 is less than the fourth threshold value T4 (S21: YES), the control unit 11 estimates that the cause of the poor image quality is either a poor connection or a broken wire. Specifically, the control unit 11 determines whether the second feature amount X2 for all frames is larger than a predetermined fifth threshold value T5, and determines whether the calculated second feature amount X2 for all frames is equal to or larger than the fifth threshold value T5 (step S23).

[0059] If it is determined that the second feature amount X2 in all frames is not equal to or greater than the fifth threshold value T5 (S23: NO), the control unit 11 estimates that the medical image has an image defect and that the cause of the image defect is a broken wire (step S24). On the other hand, if it is determined that the second feature amount X2 in all frames is equal to or greater than the fifth threshold value T5 (S23: YES), the control unit 11 estimates that the medical image has an image defect and that the cause of the image defect is a poor connection (step S25). The control unit 11 then proceeds to step S27.

[0060] If it is determined that the second feature amount X2 in all frames is equal to or greater than the second threshold value T2 (S16: YES), the control unit 11 determines that there is no image defect in the medical image (step S26).

[0061] The control unit 11 generates estimation result information according to each estimation result (step S27). The control unit 11 outputs the generated estimation result information to the imaging diagnostic device 2 (step S28), and ends the series of processes. The imaging diagnostic device 2 displays a display screen based on the estimation result information received from the information processing device 1 on the display device 24. Note that the information processing device 1 may output estimation result information and display an alert on the display device 24 only when it is estimated that there is an image defect.

[0062] In the above-described processing, the processing from step S17 onwards and the processing from step S20 onwards are not limited to being executed in parallel, but may be executed sequentially. The control unit 11 may execute the processing from step S17 onwards and then the processing from step S20 onwards, or may execute the processing from step S17 onwards after the processing from step S20 onwards.

[0063] 7 is an explanatory diagram showing an example of a display screen of the image diagnostic apparatus 2. The display screen includes information such as a medical image, the presence or absence of an image defect and an estimated result of the cause, and countermeasures for eliminating the cause of the image defect.

[0064] The information processing device 1 generates estimation result information including countermeasures according to the estimation result of the image defect. For example, if it is estimated that the image defect is caused by an air trap, the information processing device 1 outputs estimation result information that prompts priming. In this case, by displaying detailed information on the state of the air bubbles (presence or absence of air bubbles on the sensor 214), more specific countermeasures can be supported.

[0065] If it is estimated that a connection failure has occurred, the information processing device 1 outputs inference result information that prompts the user to check the connection between the catheter 21 and the MDU 22. If a failure has occurred in the MDU 22, an image failure similar to that caused by a connection failure will be observed. In this case, the image failure will not be resolved even if the catheter 21 and the MDU 22 are reconnected. Therefore, if the above-described inference process is repeated after the catheter 21 and the MDU 22 are reconnected and it is estimated that a connection failure has occurred repeatedly, the information processing device 1 can infer that the cause of the image failure is a failure of the MDU 22. If it is estimated that a failure has occurred in the MDU 22, the information processing device 1 outputs inference result information that prompts the user to contact the manufacturer, since the user cannot repair the MDU 22.

[0066] If it is estimated that the catheter 21 is broken, the information processing device 1 outputs estimation result information that prompts the user to replace the catheter 21.

[0067] The display screen may further include information indicating an image region of particular interest for estimating the cause of the connection failure. The control unit 11 generates screen information for displaying the image region related to the estimation of the cause of the image failure on the medical image using a display mode such as highlighting. For example, if the cause of the image failure is estimated to be an air trap with an air bubble on the sensor 214, the control unit 11 displays a guide image indicating the third region 33 superimposed on the medical image using a display mode such as highlighting.

[0068] According to this embodiment, the presence or absence of image defects and their causes can be suitably estimated using various feature quantities based on the brightness values ​​of specific regions in a medical image. By identifying the cause of the image defects, the cause can be efficiently eliminated, thereby reducing the total surgery time. In addition, costs associated with unnecessary catheter replacement and device repairs can be reduced.

[0069] The embodiments disclosed herein are illustrative in all respects and are not restrictive. The scope of the present invention is defined by the claims, and includes all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0070] 1. Information processing equipment 11 Control section 12 Main memory 13 Communications Department 14 Auxiliary storage P Program 2. Diagnostic imaging equipment 21 Catheter 211 Probe section 212 Connector part 213 Shaft 214 Sensors 22 MDU 23 Image processing device 24 Display device

Claims

1. Acquiring medical images including tomographic images consisting of multiple frames generated based on signals detected by the catheter; calculating feature amounts of a partial region in one or more frames of the acquired medical image, the partial region including the annular region of the tomographic image, and a large region in two or more frames of the medical image that is wider than the partial region; The presence or absence of an image defect in the medical image and its cause are estimated based on the calculated feature amount of the partial region in one or more frames of the medical image and the feature amount of the large region in two or more frames of the medical image. A program that causes a computer to execute a process.

2. determining whether a feature amount of the partial region in one frame of the medical image is less than a first threshold; If the difference is not less than the first threshold, the cause of the image defect is assumed to be a connection defect. The program according to claim 1.

3. determining whether the feature amounts of the large area regions in the plurality of frames of the medical image are equal to or greater than a second threshold value based on the feature amounts of the large area regions in the plurality of frames of the medical image; determining whether a difference between a maximum value and a minimum value of the feature amounts of the partial region in the plurality of frames of the medical image is less than a third threshold value based on the feature amounts of the partial region in the plurality of frames of the medical image; If the feature amount of the majority region in the multiple frames of the medical image is not equal to or greater than a second threshold value and the difference between the maximum and minimum values ​​of the feature amount of the partial region is not less than a third threshold value, the cause of the image defect is estimated to be air trapping. The program according to claim 1 or 2.

4. determining whether the feature amounts of the large area regions in the plurality of frames of the medical image are equal to or greater than a second threshold value based on the feature amounts of the large area regions in the plurality of frames of the medical image; determining whether a maximum value of a difference in the feature amounts of the large area region between adjacent frames in time series is less than a fourth threshold value based on each of the feature amounts of the large area region in the plurality of frames of the medical image; If the feature amount of the large area in the plurality of frames of the medical image is not equal to or greater than a second threshold value, and the maximum value of the difference in the feature amount of the large area between adjacent frames in time series is not less than a fourth threshold value, the cause of the image defect is estimated to be air trapping. The program according to any one of claims 1 to 3.

5. determining whether the feature amounts of the large area regions in the plurality of frames of the medical image are equal to or greater than a second threshold value based on the feature amounts of the large area regions in the plurality of frames of the medical image; determining whether a difference between a maximum value and a minimum value of the feature amounts of the partial region in the plurality of frames of the medical image is less than a third threshold value based on the feature amounts of the partial region in the plurality of frames of the medical image; If the feature amount of the majority region in the multiple frames of the medical image is not equal to or greater than a second threshold value and the difference between the maximum value and the minimum value of the feature amount of the partial region is less than a third threshold value, the cause of the image defect is estimated to be a connection defect or a disconnection. The program according to any one of claims 1 to 4.

6. determining whether the feature amounts of the large area regions in the plurality of frames of the medical image are equal to or greater than a second threshold value based on the feature amounts of the large area regions in the plurality of frames of the medical image; determining whether a maximum value of a difference in the feature amounts of the large area region between adjacent frames in time series is less than a fourth threshold value based on each of the feature amounts of the large area region in the plurality of frames of the medical image; If the feature amount of the large area in the plurality of frames of the medical image is not equal to or greater than a second threshold value and the maximum value of the difference in the feature amount of the large area between adjacent frames in time series is less than a fourth threshold value, the cause of the image defect is estimated to be a connection defect or a disconnection. The program according to any one of claims 1 to 5.

7. determining whether the feature amounts of the large area regions in the plurality of frames of the medical image are equal to or greater than a fifth threshold value based on the feature amounts of the large area regions in the plurality of frames of the medical image; If the feature amount of the large area in the plurality of frames of the medical image is equal to or greater than a fifth threshold, the cause of the image defect is estimated to be a connection defect; If the feature amount of the large area in the plurality of frames of the medical image is not equal to or greater than a fifth threshold, the cause of the image defect is estimated to be a broken line. The program according to claim 5 or 6.

8. an acquisition unit that acquires medical images including tomographic images consisting of multiple frames generated based on signals detected by the catheter; a calculation unit that calculates feature amounts of a partial region that is a part of one or more frames of the medical image acquired by the acquisition unit and includes an annular region of the tomographic image, and a large region that is wider than the partial region in two or more frames of the medical image; an estimation unit that estimates the presence or absence of an image defect in the medical image and the cause thereof based on the feature amount of the partial region in one or more frames of the medical image and the feature amount of the large region in two or more frames of the medical image calculated by the calculation unit; An information processing device comprising:

9. Acquiring medical images including tomographic images consisting of multiple frames generated based on signals detected by the catheter; calculating feature amounts of a partial region in one or more frames of the acquired medical image, the partial region including the annular region of the tomographic image, and a large region in two or more frames of the medical image that is wider than the partial region; The presence or absence of an image defect in the medical image and its cause are estimated based on the calculated feature amount of the partial region in one or more frames of the medical image and the feature amount of the large region in two or more frames of the medical image. Information processing methods.

Images