Ultrasound diagnostic device and diagnostic support method

The ultrasound diagnostic apparatus stabilizes mark display by dynamically adjusting smoothing based on frame data changes, ensuring reliable and responsive lesion detection.

JP7595521B2Active Publication Date: 2024-12-06FUJIFILM CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2021087804
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-05-25
Publication Date
2024-12-06
Estimated Expiration
2041-05-25

AI Technical Summary

Technical Problem

In ultrasound diagnostic apparatuses with CADe or CAD functions, mark displays indicating lesions can become unstable due to changes in position and size from frame to frame, causing flickering and stress, while smoothing techniques may overlook instantaneous lesions.

Method used

An ultrasound diagnostic apparatus that identifies lesion locations in each frame, dynamically adjusts the degree of smoothing based on the rate of change in frame data content, and generates marks on the ultrasound image using a smoothed location data string.

Benefits of technology

The apparatus achieves stable and responsive mark display, reducing flickering and ensuring that lesions are not overlooked, thereby improving the reliability of lesion detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007595521000001
    Figure 0007595521000001
  • Figure 0007595521000002
    Figure 0007595521000002
  • Figure 0007595521000003
    Figure 0007595521000003
Patent Text Reader

Abstract

To perform a mark display conforming to a situation in a case where a detected lesion portion is notified by a mark.SOLUTION: An image analysis unit 28 performs detection of a lesion portion for each tomographic image. The image analysis unit 28 outputs a positional data string and a size data string indicting a position of the lesion portion and temporal change of the size in the lesion portion detection state. A change rate calculation unit 33 calculates a change rate indicating a degree of the temporal change of a tomographic image content. A smoothing unit 34 smoothes the positional data string and size data string according to the change rate. A mark is generated on the basis of the smoothed positional data string and size data string.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to an ultrasound diagnostic apparatus and a diagnostic support method, and in particular to a technique for displaying a mark indicating a lesion on an ultrasound image. [Background technology]

[0002] In an ultrasound examination of the breast, a probe is placed on the surface of the breast and scanned along the surface of the breast. During the scanning process, real-time cross-sectional images are displayed on a display and the presence or absence of a lesion is determined through the observation. If a lesion is found, the lesion and the surrounding tissue are examined in detail. This is the same for ultrasound examinations of other organs.

[0003] It is not easy to visually identify lesions that appear temporarily on cross-sectional images that change in real time. In particular, in breast ultrasound examinations, the tissues that appear on cross-sectional images have a multi-layer structure, and it is not easy for the examiner to instantly identify the lesions contained therein.

[0004] CADe (Computer Aided Detection) is a technology that assists in identifying lesions. For example, this technology detects lesions (more precisely, lesion candidates) in tomographic images for each frame, and notifies the user when a lesion is included in the tomographic image. For example, a mark encircling the lesion is displayed on the tomographic image. CADe is used together with CAD (Computer Aided Diagnosis) or is included in CAD.

[0005] Patent Document 1 discloses a medical device with a CAD function. The medical device has a function of indicating the probe scanning speed to the examiner by changing the color of a mark according to the probe scanning speed. Patent Document 1 does not disclose any technology related to smoothing the mark. In this specification, a lesion means a site that may be a disease site or a site that needs to be examined closely. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent Publication No. 2020-178989 Summary of the Invention [Problem to be solved by the invention]

[0007] In ultrasound diagnostic devices equipped with CADe or CAD functions, a mark is displayed on the ultrasound image to notify the presence of a lesion. The appearance and continuous display of the mark notifies the examiner of the presence of a lesion, thereby encouraging the examiner to perform a detailed examination of the lesion.

[0008] However, if marks are generated and displayed faithfully based on the results of individual lesion detection even when the content of the ultrasound image is barely changing, the display of the marks may become unstable depending on the situation. If the position and size of the marks change from frame to frame, the marks may flicker, causing stress and anxiety to the examiner who observes the marks. In response to this, it is possible to apply some kind of smoothing process before displaying the marks, but in that case, a problem may arise in that the marks are not displayed responsively to lesions that appear instantaneously under conditions in which the content of the ultrasound image is changing significantly. This may lead to lesions being overlooked.

[0009] An object of the present disclosure is to enable the display of a mark suited to the situation when notifying a detected lesion area by a mark. [Means for solving the problem]

[0010] The ultrasound diagnostic device of the present disclosure includes an analysis unit that identifies the location of a lesion for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasound beam, and thereby outputs a location data sequence; a smoothing unit that smoothes the location data sequence while dynamically changing the degree of smoothing according to a rate of change indicating the degree of temporal change in the frame data content, and thereby outputs the smoothed location data sequence; and a generation unit that generates a mark indicating the lesion in accordance with the smoothed location data sequence, and the mark is displayed on an ultrasound image formed based on the frame data sequence.

[0011] The diagnostic support method of the present disclosure includes a step of identifying the location of the lesion for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasound beam, thereby generating a location data sequence; a step of smoothing the location data sequence while dynamically changing the degree of smoothing according to a rate of change indicating the degree of temporal change in the frame data content, thereby generating a smoothed location data sequence; and a step of generating a mark indicating the lesion according to the smoothed location data sequence, wherein the mark is displayed on an ultrasound image formed based on the frame data sequence.

[0012] The program disclosed herein is a program for executing a diagnostic support method in an information processing device, and includes a function for identifying the location of a lesion for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasound beam, thereby generating a location data sequence; a function for smoothing the location data sequence while dynamically changing the degree of smoothing according to a rate of change indicating the degree of temporal change in the frame data content, thereby generating a smoothed location data sequence; and a function for generating a mark indicating the lesion according to the smoothed location data sequence, wherein the mark is displayed on an ultrasound image formed based on the frame data sequence. Effect of the Invention

[0013] According to the present disclosure, when notifying a detected lesion area by a mark, the mark can be displayed in a manner appropriate to the situation. [Brief description of the drawings]

[0014] [Figure 1] 1 is a block diagram showing an ultrasound diagnostic apparatus according to an embodiment. [Diagram 2] FIG. 11 is a diagram illustrating a mark display process. [Diagram 3] FIG. 4 illustrates an example of the configuration of a smoothing unit; [Figure 4] FIG. 13 is a diagram illustrating the relationship between the rate of change and the smoothing number. [Diagram 5] An example of a weighting function is shown below. [Figure 6] FIG. 11 is a diagram showing a first display example. [Figure 7] FIG. 13 is a diagram showing a second display example. [Figure 8] FIG. 11 is a diagram illustrating an example of a smoothing process. [Figure 9] 11 is a flowchart showing a first operation example. [Figure 10] 13 is a flowchart showing a second operation example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment will be described with reference to the drawings.

[0016] (1) Overview of the embodiment An ultrasonic diagnostic device according to an embodiment has an analysis unit, a smoothing unit, and a generation unit. The analysis unit identifies the location of a lesion for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasonic beam, and outputs a location data sequence accordingly. The smoothing unit smoothes the location data sequence while dynamically changing the degree of smoothing according to a rate of change indicating the degree of temporal change in the frame data content, and outputs the smoothed location data sequence accordingly. The generation unit generates a mark indicating the lesion according to the smoothed location data sequence. The mark is displayed on an ultrasonic image formed based on the frame data sequence.

[0017] According to the above configuration, the mark is displayed according to the smoothed location data sequence. At that time, the smoothing degree is determined according to the rate of change indicating the degree of temporal change of the frame data content. When the rate of change is small, that is, when the content of the ultrasound image does not change much, the smoothing degree is increased to prevent or reduce the instability of the mark display. For example, the phenomenon of the mark being displayed flickering can be suppressed. On the other hand, when the rate of change is large, that is, when the content of the ultrasound image changes significantly, the smoothing degree is decreased to display the mark with good responsiveness, thereby preventing or reducing the overlooking of a lesion that appears momentarily. According to the configuration of the embodiment, the mark display adapted to the situation can be realized, and therefore the reliability of the mark display can be improved.

[0018] The location of the lesion means the place or part where the lesion exists in the ultrasound image. As the location of the lesion, multiple points representative of the lesion may be specified, or an area where the lesion exists or an area including the lesion may be specified. As the rate of change or when calculating the rate of change, probe movement information, difference information between frame data, transmission and reception frame rate, etc. may be referenced.

[0019] In an embodiment, the analysis unit identifies the position and size of the lesion as the location of the lesion, and outputs a position data string and a size data string as a location data string. The smoothing unit includes a first smoothing unit that smoothes the position data string and a second smoothing unit that smoothes the size data string. The generation unit generates a mark according to the smoothed position data string and the smoothed size data string. In an embodiment, each piece of position data is data indicating a center position of an area including the lesion, and each piece of size data is data indicating a corner position of the area.

[0020] Factors that cause the mark display to become unstable include temporal fluctuations in the position detected for the lesion and temporal fluctuations in the size detected for the lesion. These are smoothed individually. This allows the mark as a whole to be displayed stably even in a situation where the content of the ultrasound image is not changing much. A variant in which the mark itself is smoothed is also conceivable.

[0021] In an embodiment, the smoothing unit reduces the degree of smoothing as the rate of change increases. With this configuration, the greater the degree of change in the frame data content, the more importance is placed on responsiveness, and the smaller the degree of change in the frame data content, the more importance is placed on smoothness or stability.

[0022] In an embodiment, the smoothing unit increases or decreases the number of frame data used in the smoothing when increasing or decreasing the degree of smoothing. A weighting function may be used in the smoothing. A value indicating the degree of smoothing or the number of frames used in the smoothing may be displayed on the screen. A mode may be provided in which the degree of smoothing is fixed to a predetermined value by user selection or automatically.

[0023] In an embodiment, the smoothing unit determines a temporal discontinuity for the lesion based on the output of the analysis unit, and restricts the generation of a mark when a temporal discontinuity is determined. In an embodiment, the smoothing unit determines a spatial discontinuity for the lesion based on the output of the analysis unit, and restricts the generation of a mark when a spatial discontinuity is determined. When a temporal discontinuity or a spatial discontinuity is determined, the generation of the mark may be restricted to make the mark invisible, or the display of the mark related to the smoothing may be restricted. The determination of non-satisfaction of a temporal continuity condition described later corresponds to the determination of a temporal discontinuity. The determination of non-satisfaction of a spatial continuity condition described later corresponds to the determination of a spatial discontinuity.

[0024] The diagnostic support method according to the embodiment includes an analysis step, a smoothing step, and a generation step. In the analysis step, the location of the lesion is identified for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasonic beam, thereby generating a location data sequence. In the smoothing step, the location data sequence is smoothed while dynamically changing the degree of smoothing according to a rate of change indicating the degree of temporal change in the frame data content, thereby generating a smoothed location data sequence. In the generation step, a mark indicating the lesion is generated according to the smoothed location data sequence. The mark is displayed on an ultrasound image formed based on the frame data sequence.

[0025] The above-mentioned diagnostic support method can be realized by a hardware function or a software function. In the latter case, a program for executing the diagnostic support method is installed in an information processing device via a portable storage medium or a network. The concept of an information processing device includes an ultrasonic diagnostic device, an ultrasonic image processing device, and a computer.

[0026] (2) Details of the embodiment 1 shows a block diagram of an ultrasonic diagnostic device according to an embodiment. The ultrasonic diagnostic device is a medical device that is installed in a medical institution such as a hospital and forms an ultrasonic image based on a reception signal obtained by transmitting and receiving ultrasonic waves to a living body (subject). In the embodiment, an organ to be subjected to ultrasonic diagnosis is, for example, a breast.

[0027] In mass breast screening, it is necessary to identify lesions in a short time without overlooking them. The ultrasound diagnostic device according to the embodiment has a CADe function that automatically detects lesions (e.g., low-brightness tumor images) included in ultrasound images to support the examiner in identifying the lesions. This will be described in detail later.

[0028] The probe 10 functions as a means for transmitting and receiving ultrasonic waves. The probe 10 is a portable transducer that is held and operated by an examiner (such as a doctor or a medical technician). In an ultrasonic diagnosis of the breast, the transmitting and receiving surface of the probe 10 (specifically, the acoustic lens surface) is brought into contact with the chest surface of the examinee. The probe 10 is manually scanned along the chest surface while observing the tomographic images displayed in real time.

[0029] In the illustrated configuration example, the probe 10 includes a transducer element array consisting of a plurality of transducer elements arranged one-dimensionally. The transducer element array forms an ultrasonic beam (transmit beam and receive beam) 12, and a scan plane 14 is formed by electronically scanning the ultrasonic beam 12. The scan plane 14 is an observation plane, that is, a two-dimensional data acquisition area. As electronic scanning methods for the ultrasonic beam 12, electronic sector scanning method, electronic linear scanning method, etc. are known. Convex scanning of the ultrasonic beam 12 may be performed. A 2D transducer element array may be provided in the ultrasonic probe 10, and volume data may be acquired from within a living body by two-dimensional scanning of the ultrasonic beam. By repeating scanning of the ultrasonic beam, a received frame data sequence, which will be described later, is generated.

[0030] In the illustrated configuration example, a positioning system is provided that determines position information of the probe 10. The positioning system is composed of a magnetic sensor 18, a magnetic field generator 20, and a positioning controller 21. The magnetic sensor 18 is provided on the probe (more precisely, the probe head) 10. The magnetic field generated by the magnetic field generator 20 is detected by the magnetic sensor 18. This provides three-dimensional coordinate information of the magnetic sensor 18. The position and attitude of the probe 10 are identified based on the three-dimensional coordinate information. The position information is sent from the positioning controller to the mark generating unit 30 and the main control unit 38.

[0031] The transmission circuit 22 functions as a transmission beamformer. Specifically, during transmission, the transmission circuit 22 supplies multiple transmission signals in parallel to the transducer element array. This forms a transmission beam. During reception, when a reflected wave from inside the living body reaches the transducer element array, multiple reception signals are output in parallel from the multiple transducer elements. The reception circuit 24 functions as a reception beamformer, and generates beam data by phasing and adding (also called delay and addition) the multiple reception signals.

[0032] Incidentally, multiple beam data aligned in the electronic scanning direction are generated per electronic scan, and these constitute received frame data corresponding to the scan plane 14. Each beam data is composed of multiple echo data aligned in the depth direction. A beam data processing unit is provided downstream of the receiving circuit 24, but is not shown in the figure.

[0033] The image forming unit 26 is an electronic circuit that generates a tomographic image (B-mode tomographic image) based on the received frame data. It has a DSC (Digital Scan Converter). The DSC has a coordinate conversion function, a pixel interpolation function, a frame rate conversion function, and the like. More specifically, in the image forming unit 26, a display frame data string is formed based on the received frame data string. The multiple display frame data constituting the display frame data string are multiple tomographic image data, and a real-time moving image is composed of these data. An ultrasound image other than a tomographic image may be generated. For example, a color flow mapping image may be formed, or a three-dimensional image that stereoscopically represents tissue may be formed. The display frame data string is sent to the image analysis unit 28 and the display processing unit 32.

[0034] The image analysis unit 28 is a module that performs CADe functions. The image analysis unit 28 executes a lesion detection process for each display frame data, that is, for each tomographic image. Specifically, a machine learning network such as CNN is used to search for an area having a feature amount similar to any of the lesion feature amounts previously learned from within the tomographic image. The lesion area to be detected is determined in advance by the designer of the network. For example, the lesion area to be detected includes a tumorous lesion area, a non-tumorous lesion area, and the like. In the lesion detection process, processes such as a binarization process, an edge detection process, and the like may be applied to the tomographic image.

[0035] When a lesion is detected, lesion information is output from image analysis unit 28. The lesion information includes a lesion detection flag, the reliability of the lesion, position information (position data) of the lesion, and size information (size data) of the lesion. The lesion information is sent from image analysis unit 28 to mark generation unit 30 for each display frame data. In other words, a position data string and a size data string are sent from image analysis unit 28 to mark generation unit 30.

[0036] The position information of the lesion is, for example, information indicating the coordinates of the center point (or center of gravity) of a closed area corresponding to the lesion, or information indicating the coordinates of the center point (or center of gravity) of a figure surrounding the lesion. The size information of the lesion is, for example, information indicating the size of a figure surrounding the lesion. For example, a rectangle that circumscribes the lesion and surrounds it may be defined, and the size of the lesion may be identified from the coordinates of its center point and the coordinates of its upper left corner point. On the premise that the coordinates of the center point have been identified, the coordinates of the upper left corner point may be regarded as the size information of the lesion. The area of ​​a closed area corresponding to the lesion may be calculated as the size information of the lesion. Multiple lesions may be detected in parallel. The position information and size information of the lesion may be collectively referred to as the location information of the lesion.

[0037] The mark generating unit 30 generates a mark for each display frame data based on the lesion information. The mark is a display element that indicates the location of the lesion. Specifically, the mark has a shape that surrounds the lesion, and the center position and size of the lesion can be identified by observing the mark. When the marks are observed continuously on the time axis, the marks correspond to dynamic figures (moving images). When the marks are observed individually for each display frame data, the marks correspond to static figures (still images).

[0038] The mark generating unit 30 according to the embodiment includes a change rate calculation unit 33 and a smoothing unit 34. The change rate calculation unit 33 calculates a change rate for each display frame data as information indicating the degree of temporal change in the display frame data content. For example, a difference or correlation value may be calculated between display frame data, and the calculation result may be used as the change rate. The change rate may be calculated based on a temporal change in position information output from a positioning system. This is because when the probe movement amount (probe movement speed) is large, the temporal change in the display frame data content is estimated to be large, and when the probe movement amount is small, the temporal change in the display frame data content is estimated to be small. The change rate may be calculated based on multiple pieces of information indicating the degree of temporal change in the display frame data content.

[0039] When calculating a correlation value between display frame data, a reference area may be set for each display frame data based on the center position of the lesion, and a correlation value may be calculated between the two reference areas. In this case, the correlation value may be calculated by calculating the difference in pixel values ​​for each coordinate and normalizing the sum of the differences by the number of pixels (area). The change rate may be calculated based on the correlation value of a histogram between the two reference areas, the optical flow calculated between the two reference areas, etc. Prior to the calculation of the change rate, pre-processing such as segmentation and binarization may be applied to each display frame data.

[0040] The rate of change may be calculated based on the wave transmission / reception frame rate, or the wave transmission / reception frame rate itself may be used as the rate of change. When the wave transmission / reception frame rate is high, the temporal change in the display frame data content is usually large, while when the wave transmission / reception frame rate is low, the temporal change in the display frame data content is usually small. However, when the probe 10 is completely stationary, the content of the display frame data is stable regardless of the wave transmission / reception frame rate. Therefore, it is desirable to use the wave transmission / reception frame rate as auxiliary information.

[0041] The smoothing unit 34 executes a smoothing process. In the embodiment, the smoothing process is applied individually to the position data string and the size data string generated and output by the image analysis unit 28. In the embodiment, as will be described later using a specific example, the smoothing process is applied to the center coordinates and the upper left corner coordinates of a rectangular area circumscribing the lesion.

[0042] The smoothing unit 34 increases the degree of smoothing as the rate of change decreases, and decreases the degree of smoothing as the rate of change increases. By adaptively varying the degree of smoothing in this manner, it is possible to achieve both stable display of marks when the content of the ultrasound image is not changing much, and responsive display of marks when the content of the ultrasound image is changing significantly.

[0043] In practice, the smoothing unit 34 increases the number of data items (smoothing number) referred to in the smoothing process when the rate of change is small, and decreases the number of data items referred to in the smoothing process when the rate of change is large. Here, the number of data items means the number of frames, which corresponds to a time window as a certain period going back from the present to the past. The maximum and minimum values ​​of the number of frames referred to may be determined by the user or automatically.

[0044] The mark generating unit 30 generates a mark as a still image for each display frame data based on the smoothed position data string and the smoothed size data string. The mark generating unit 30 includes a memory for storing data required for the smoothing process.

[0045] More specifically, the mark generating unit 30 generates a mark only when the temporal continuity condition and the spatial continuity condition are satisfied. If either the temporal continuity condition or the spatial continuity condition is not satisfied, the mark is hidden. The temporal continuity condition is satisfied when lesions are continuously detected in m (where m is an integer equal to or greater than 2) display frame data including the current display frame data as a whole. The spatial continuity condition is satisfied when the distance between the lesion center in the reference display frame data and the lesion center in the current display frame data is equal to or less than a predetermined value. The reference display frame data is, for example, the display frame data acquired at the time when the lesion is first detected in a situation where lesions are continuously detected. The reference display frame data may be the display frame data immediately preceding the one in question.

[0046] If lesion detection is interrupted within a certain time range, the display of the mark is restricted. Also, if the movement of the lesion corresponds to an unnatural jump, the display of the mark is restricted. This makes it possible to avoid displaying the mark when no lesion is detected, or the sudden display of the mark based on erroneous detection.

[0047] However, since lesion detection may be temporarily interrupted due to changes in the probe contact state, noise, etc., the mark display conditions or the mark display restriction conditions may be changed by the examiner or automatically. When any of the continuity conditions is not satisfied, instead of not displaying the mark, a mark may be generated and displayed based on unsmoothed position data and size data.

[0048] In the mark generating unit 30, when determining the degree of smoothing from the rate of change, a conversion table or a conversion function may be used. In the smoothing process, a weighting function in which the weighting changes along the time axis may be used. In the mark generating unit 30, graphic data including a mark is generated for each display frame data, and the graphic data is sent to the display processing unit 32.

[0049] The image forming unit 26, the image analysis unit 28, and the mark generating unit 30 may each be configured by a processor. A single processor may function as the image forming unit 26, the image analysis unit 28, and the mark generating unit 30. A CPU, which will be described later, may function as the image forming unit 26, the image analysis unit 28, and the mark generating unit 30.

[0050] The display processing unit 32 has a color calculation function, an image synthesis function, etc. In the display processing unit 32, graphic data including marks is synthesized with the display frame data (tomographic image), thereby generating an image to be displayed on the display 36. The display unit 36 ​​is configured with an LCD, an organic EL display device, etc. The display unit 36 ​​displays the tomographic image as a moving image in real time, and also displays marks as part of the graphic image. The display processing unit 32 is configured with, for example, a processor.

[0051] The main control unit 38 controls the operation of each element shown in Fig. 1. In the embodiment, the main control unit 38 is configured by a CPU and a program. An operation panel 40 is connected to the main control unit 38. The operation panel 40 is an input device, and has a plurality of switches, a plurality of buttons, a trackball, a keyboard, etc. In the embodiment, the display frame data string is provided to the image analysis unit 28, but the received frame data string may also be provided to the image analysis unit 28 (see reference numeral 42). In that case, a second image formation unit may be provided that simply generates the display frame data string from the received frame data string.

[0052] 2 shows the mark display process. A lesion 46 is included in a tomographic image 44. The lesion 46 is detected by an image analysis unit. When detecting the lesion 46, for example, a rectangle (or area) 52 circumscribing the lesion 46 is defined. In practice, the coordinates of a center point 48 and an upper left corner point 50 of the rectangle 52 are specified. The lesion may be detected based on image features such as edge detection.

[0053] A rectangle 54 is defined as a figure with fixed margins 56, 58 in the horizontal and vertical directions outside the rectangle 52. The rectangle 54 is displayed as a marker 64 on the tomographic image. The marker 64 is a figure that surrounds the lesion 46 and its periphery. In the illustrated example, the marker 64 is configured with a dashed line. The display mode of the marker 64 can be freely selected. For example, a marker configured with a solid line may be displayed, or a marker consisting of four elements representing only the four corners may be displayed. A circular or elliptical marker may also be displayed.

[0054] If the position and size of the displayed marker 64 change from frame to frame even though the contents of the display frame data are hardly changing, that is, even though the lesion is hardly changing, the examiner feels stress or anxiety. On the other hand, it is also important to effectively prevent the overlooking of a lesion that suddenly appears under a situation where the contents of the display frame data are changing significantly. From this perspective, in the embodiment, as already described and as will be described in a specific example below, an adaptive smoothing process based on the rate of change is performed.

[0055] 3 shows the configuration of the smoothing unit 34. The smoothing unit 34 has a first smoothing unit 34A and a second smoothing unit 34B. The first smoothing unit 34A smoothes the position data string. The second smoothing unit 34B smoothes the size data string. In addition, a third smoothing unit may be provided that smoothes the reliability of lesion detection.

[0056] 4 shows the relationship between the rate of change R and the number of reference data (smoothing number) N in the smoothing process. As shown by linear function 66A, the number of reference data N may be monotonically decreased with an increase in the rate of change R. The number of reference data N may be determined from the rate of change R according to non-linear function 66B.

[0057] Weighting function 106 is shown in FIG. 5. The horizontal axis is the time axis, with n indicating the current frame number and n-1 to n-5 indicating past frames. The vertical axis indicates weighting w. As shown in weighting function 106, a larger weighting w may be given to newer data. Weighting function 106 may be stretched or contracted to fit a time window determined from the rate of change R. A uniform weighting may be set within the time window, or the weighting may be changed linearly within the time window.

[0058] A first mark display example is shown in Fig. 6, and a second mark display example is shown in Fig. 7. The first display example shows, for example, a state in which the probe movement speed is high and a large change rate is calculated. The second display example shows, for example, a state in which the probe movement speed is high and a small change rate is calculated. In Figs. 6 and 7, the horizontal axis is the time axis.

[0059] The first mark display example shown in Fig. 6 includes cross-sectional images 70A-70D at each time, which include lesions 72A-72D. On the time axis, the state (content, position, etc.) of the lesions changes significantly over time. In such a case, a small smoothing degree is set, and marks 74A-74D surrounding the lesions 72A-72D are generated and displayed with good responsiveness at each time. This makes it possible to prevent or reduce overlooking of the lesions.

[0060] The second display example shown in Fig. 7 includes cross-sectional images 76A-76D at each time, which include lesions 78A-78D. The state of the lesions does not change much on the time axis. In such a case, a large degree of smoothing is set, and changes in the marks 79A-79D surrounding the lesions 78A-78D at each time are suppressed. This prevents the marks from flickering.

[0061] An example of the smoothing process is shown in Fig. 8. The vertical axis is the time axis. Reference numeral 80 indicates one data set. A plurality of data sets are arranged along the time axis. Along the horizontal axis, frame number 82, presence or absence of lesion detection 84, probe movement speed as a rate of change 86, smoothing number (number of reference data) 88, center point coordinate 90, center point coordinate after smoothing 92, upper left corner point coordinate 94, and upper left corner point coordinate after smoothing 96 are shown.

[0062] At the time specified by frame number 11, a lesion has not been detected. No smoothing process is performed. At the time specified by frame number 12, a lesion has been detected and a smoothing number of 5 has been determined from the moving speed of 10, but no smoothing is performed at that time, and a mark is generated based on the center point coordinate C12 and the upper left corner point coordinate L12. At the time specified by frame number 13, a lesion has been detected and a smoothing number of 5 has been determined from the moving speed of 11. At that time, a center point coordinate C13' after smoothing has been calculated based on the two center point coordinates C12 and C13 (see reference numeral 98. The two coordinates in parentheses indicate the smoothing range). Similarly, a top left corner point coordinate L13' after smoothing has been calculated based on the two top left corner point coordinates L12 and L13 (see reference numeral 100). A mark is generated based on the center point coordinate C13' after smoothing and the top left corner point coordinate L13' after smoothing.

[0063] At the time point identified by frame number 18, a lesion has been detected (continuously detected across frames 12-18), and a smoothed center point coordinate C18' is calculated based on the five center point coordinates C14-C18 (see reference numeral 102). Similarly, a smoothed upper left corner point coordinate L18' is calculated based on the five upper left corner point coordinates L14-L18. A mark is generated based on the smoothed center point coordinate C18' and the smoothed upper left corner point coordinate L18' (see reference numeral 104).

[0064] The lesion detection continues from the time point specified by frame number 31 to the time point specified by frame number 34, but the moving speed is relatively high during that period and the smoothing number is small during that period. In this embodiment, the smoothing degree is adaptively determined according to the fluctuation of the rate of change in this manner, which includes adaptively switching smoothing on and off.

[0065] 9 shows a first operation example of the mark generating unit. In S10, it is determined whether or not a lesion is detected. For example, if the reliability is equal to or greater than a predetermined value, it may be determined that a lesion is detected. If an end condition is satisfied in S10, this process ends.

[0066] If it is determined that a lesion has been detected, in S12, a smoothing number (number of reference data) is determined based on the rate of change. In S14, it is determined whether a temporal continuity condition (first condition) is satisfied. In S15, it is determined whether a spatial continuity condition (second condition) is satisfied. If both the first condition and the second condition are satisfied, S16 is executed, and if either condition is not satisfied, S18 is executed.

[0067] In S16, a mark is generated based on the result of the smoothing process, i.e., based on the smoothed position data string and size data string. In S20, the generated mark is displayed. In S18, the display of the mark is restricted. Specifically, the mark is hidden. The above-mentioned processes are repeatedly executed.

[0068] A second operation example of the mark generating unit is shown in Fig. 10. In Fig. 10, the same steps as those shown in Fig. 9 are given the same step numbers, and the description thereof will be omitted.

[0069] In the second operation example, if either the first or second condition is not satisfied, smoothing is restricted and a mark is generated in S21. That is, a mark is generated based on unsmoothed position data and size data, and the mark is displayed in S20.

[0070] In both the first and second operation examples, when a certain condition is satisfied, a smoothed mark is displayed according to a smoothing degree based on a rate of change. In a situation where the content of a tomographic image hardly changes, it is possible to effectively prevent or reduce the occurrence of an event where the mark is displayed flickering. In a situation where the content of a tomographic image changes significantly, it is possible to reliably notify a lesion that is suddenly detected by the mark. [Explanation of symbols]

[0071] 10 probe, 26 image forming section, 28 image analysis section, 30 mark generating section, 33 rate of change calculation section, 34 smoothing section.

Claims

1. an analysis unit that identifies the location of a lesion for each frame of data based on a frame data sequence acquired by repeatedly scanning an ultrasonic beam, and outputs a location data sequence; a smoothing unit which smooths the location data string while dynamically changing a smoothing degree according to a rate of change indicating a degree of temporal change of the frame data content, and outputs the smoothed location data string, the smoothing unit decreasing the smoothing degree as the rate of change increases; a generating unit that generates a mark notifying the lesion area according to the smoothed location data sequence; Including, the mark is displayed on an ultrasound image formed based on the frame data sequence; 1. An ultrasonic diagnostic apparatus comprising:

2. 2. The ultrasonic diagnostic apparatus according to claim 1, the analysis unit identifies a position and a size of the lesion as the location of the lesion, and outputs a position data string and a size data string as the location data string; the smoothing unit includes a first smoothing unit that smoothes the position data string and a second smoothing unit that smoothes the size data string; the generating unit generates the mark in accordance with the smoothed position data sequence and the smoothed size data sequence.

1. An ultrasonic diagnostic apparatus comprising:

3. 3. The ultrasonic diagnostic apparatus according to claim 2, each of the position data indicates a center position of a region including the lesion; Each of the size data indicates a corner position of the area.

1. An ultrasonic diagnostic apparatus comprising:

4. 2. The ultrasonic diagnostic apparatus according to claim 1, the smoothing unit calculates the rate of change by calculating a difference or a correlation value between frame data based on the frame data sequence.

1. An ultrasonic diagnostic apparatus comprising:

5. 2. The ultrasonic diagnostic apparatus according to claim 1, the smoothing unit increases or decreases the number of frame data used in the smoothing when increasing or decreasing the degree of smoothing; 1. An ultrasonic diagnostic apparatus comprising:

6. 2. The ultrasonic diagnostic apparatus according to claim 1, The generation unit is determining a temporal discontinuity for the lesion based on an output of the analysis unit; and limiting the generation of the mark when the temporal discontinuity is determined.

1. An ultrasonic diagnostic apparatus comprising:

7. 2. The ultrasonic diagnostic apparatus according to claim 1, The generation unit is determining a spatial discontinuity for the lesion based on the output of the analyzer; limiting the generation of the mark when the spatial discontinuity is determined.

1. An ultrasonic diagnostic apparatus comprising:

8. a step of identifying the location of a lesion for each frame of data based on a frame of data sequence acquired by repeatedly scanning the ultrasound beam, thereby generating a location data sequence; smoothing the location data string while dynamically varying a degree of smoothing according to a rate of change indicating a degree of temporal change in the content of the frame data, thereby generating a smoothed location data string, the degree of smoothing decreasing as the rate of change increases; generating a mark indicating the lesion area according to the smoothed location data sequence; Including, the mark is displayed on an ultrasound image formed based on the frame data sequence; A diagnostic support method comprising:

9. A program for executing a diagnostic support method in an information processing device, A function of identifying the location of a lesion for each frame of data based on a frame of data sequence acquired by repeatedly scanning an ultrasonic beam, thereby generating a location data sequence; a function for smoothing the location data string while dynamically varying the degree of smoothing according to a rate of change indicating the degree of temporal change of the frame data content, thereby generating a smoothed location data string, the function decreasing the degree of smoothing as the rate of change increases; a function of generating a mark notifying the lesion area according to the smoothed location data sequence; Including, the mark is displayed on an ultrasound image formed based on the frame data sequence; A program characterized by:

Citation Information

Patent Citations

  • Ultrasonic diagnostic apparatus and program

    JP2013188236A

  • Ultrasonic diagnostic device and ultrasonic image processing method

    JP2020018694A

  • Diagnostic device and diagnostic method

    JP2020081742A

  • Ultrasonic diagnostic device and analyzer

    JP2020178989A

  • Computer-aided diagnosis (CAD) apparatus and method using consecutive medical images

    US20160117818A1