Ultrasound image analysis apparatus and ultrasound image analysis program

Abstract

To appropriately calculate a GTC by using a breast ultrasound image formed by transmitting and receiving an ultrasound wave to and from a breast.SOLUTION: A mammary gland region identification unit 32 identifies a mammary gland region MR in a target breast ultrasound image TBUI formed by transmitting and receiving an ultrasound wave to and from a breast. A fat region identification unit 34 identifies a fat region FR in the target breast ultrasound image TBUI. A threshold value identification unit 36 identifies a brightness threshold value based on a brightness value of each pixel constituting the fat region FR. A GTC calculation unit 38 divides a pixel group constituting the mammary gland region MR into high-brightness pixels HP of which a brightness value is equal to or more than a brightness threshold value and low-brightness pixels LP of which a brightness value is less than the brightness threshold value. The GTC calculation unit 38 calculates a GTC that is a parameter indicating a ratio of the number of low-brightness pixels in the mammary gland region MR.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This specification discloses an improved ultrasound image analysis device and ultrasound image analysis program. [Background technology]

[0002] It has been known that breast density is a risk factor for breast cancer. Breast density can be measured using a mammography device. However, from the perspective of reducing pain to the subject, a technique for assessing breast cancer risk using breast ultrasound images formed by transmitting and receiving ultrasound waves to and from the breast has been proposed.

[0003] Specifically, it has been proposed to evaluate breast cancer risk by calculating a parameter called the Glandular Tissue Component (GTC), which is believed to be highly correlated with breast density using breast ultrasound images. Specifically, the glandular region (the region between the subcutaneous fat region and the retromammary fat region near the pectoralis major muscle, in the depth direction from the body surface) is identified in the breast ultrasound image, and the GTC is calculated based on the area ratio of the isoechoic region (composed of milk ducts, lobules, and surrounding stroma, and consisting of low-intensity stromal regions relative to high-intensity edematous stromal regions) in the glandular region. A larger GTC indicates higher breast density, which in turn indicates a higher risk of breast cancer.

[0004] For example, Patent Documents 1 and 2 disclose an ultrasound image analysis device that identifies the breast region, which is the region between the skin and the pectoralis major muscle, in a breast ultrasound image, identifies the mammary gland region, which is the region between the anterior boundary line and the posterior boundary line within the breast region, binarizes the mammary gland region using a predetermined brightness threshold, defines high-brightness regions as edematous stromal regions and low-brightness regions as GTC regions (isoechoic regions), and calculates the ratio of the GTC region to the mammary gland region. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2023-077810 [Patent Document 2] Japanese Patent Publication No. 2020-077820 Summary of the Invention [Problem to be solved by the invention]

[0006] To calculate GTC using breast ultrasound images, it is necessary to classify each pixel in the mammary gland region into high-intensity pixels (corresponding to edematous stromal regions) and low-intensity pixels (corresponding to isoechoic regions) based on their brightness values. The classification into high-intensity and low-intensity pixels is performed using a brightness threshold. This brightness threshold is an important parameter that directly affects the GTC value.

[0007] Ultrasound diagnostic devices or ultrasound image processing devices (e.g., computers such as servers) generally have a function for adjusting the brightness value of each pixel constituting a breast ultrasound image (hereinafter, sometimes simply referred to as the brightness value of a breast ultrasound image). Therefore, the brightness value of a breast ultrasound image may be set to various values ​​by a doctor or a facility (e.g., a hospital). For example, it may happen that one doctor sets the brightness values ​​of a breast ultrasound image higher overall, while another doctor sets the brightness values ​​of a breast ultrasound image lower overall.

[0008] If the brightness values ​​of a breast ultrasound image are adjusted globally, and the brightness threshold used to calculate the GTC is set to a predetermined value, the GTC may vary depending on the brightness values ​​of the adjusted breast ultrasound image, which may result in an inappropriate GTC being calculated.

[0009] The purpose of the ultrasound image analysis device disclosed in this specification is to appropriately calculate the GTC using a breast ultrasound image formed by transmitting and receiving ultrasound waves to and from the breast. [Means for solving the problem]

[0010] The ultrasound image analysis device disclosed in this specification is characterized by comprising: a mammary gland region identification unit that identifies a mammary gland region in a target breast ultrasound image to be processed, which is formed by transmitting and receiving ultrasound waves to and from the breast; a fat region identification unit that identifies a fat region in a breast ultrasound image formed by transmitting and receiving ultrasound waves to and from the breast; a threshold identification unit that identifies a brightness threshold based on the brightness value of each pixel that constitutes the fat region; a GTC calculation unit that divides a group of pixels that constitute the mammary gland region into high-brightness pixels whose brightness values ​​are equal to or greater than the brightness threshold and low-brightness pixels whose brightness values ​​are less than the brightness threshold, and calculates a GTC that indicates the proportion of the number of low-brightness pixels in the mammary gland region; and a provision processing unit that provides the GTC to a user.

[0011] The target breast ultrasound image and the identified mammary gland area are presented to the user, the mammary gland area identification unit corrects the mammary gland area in accordance with instructions from the user, and the GTC calculation unit calculates a GTC indicating the proportion of low-brightness pixels in the corrected mammary gland area.

[0012] The breast ultrasound image is the target breast ultrasound image, and the ultrasound image analysis device further includes a brightness value adjustment unit that adjusts the brightness value of each pixel that constitutes the target breast ultrasound image, and the threshold determination unit determines the brightness threshold based on the adjusted brightness value of each pixel that constitutes the fatty region of the target breast ultrasound image, and the GTC calculation unit calculates a GTC that indicates the proportion of the number of low-brightness pixels in the mammary gland region of the target breast ultrasound image whose brightness values ​​have been adjusted.

[0013] The target breast ultrasound image and the identified fatty region are presented to the user, the fatty region identifying unit corrects the fatty region in response to an instruction from the user, and the threshold identifying unit identifies the brightness threshold based on the brightness value of each pixel constituting the corrected fatty region.

[0014] The provision processing unit may notify the user when the variation in luminance values ​​of the pixels constituting the fatty region is equal to or greater than a variation threshold.

[0015] The threshold determination unit determines a maximum brightness threshold within a brightness threshold range that the brightness threshold can take, and a minimum brightness threshold within the brightness threshold range, based on the variation in brightness values ​​of each pixel that constitutes the fat region; the GTC calculation unit calculates a maximum GTC, which is the GTC based on the maximum brightness threshold, and a minimum GTC, which is the GTC based on the minimum brightness threshold; and the provision processing unit provides the user with at least one of the maximum GTC and the minimum GTC, or the difference between the maximum GTC and the minimum GTC, or provides the user with the maximum GTC and the minimum GTC if the difference between the maximum GTC and the minimum GTC is greater than or equal to the GTC threshold.

[0016] In addition, the ultrasound image analysis program disclosed in this specification is characterized in that it causes a computer to function as a mammary gland region identification unit that identifies a mammary gland region in a target breast ultrasound image to be processed, which is formed by transmitting and receiving ultrasound waves to the breast; a fat region identification unit that identifies a fat region in a breast ultrasound image formed by transmitting and receiving ultrasound waves to the breast; a threshold identification unit that identifies a brightness threshold based on the brightness value of each pixel that constitutes the fat region; a GTC calculation unit that divides the group of pixels that constitute the mammary gland region into high-brightness pixels whose brightness values ​​are equal to or greater than the brightness threshold and low-brightness pixels whose brightness values ​​are less than the brightness threshold, and calculates a GTC that indicates the proportion of the number of low-brightness pixels in the mammary gland region; and a provision processing unit that provides the GTC to a user. [Effects of the Invention]

[0017] According to the ultrasound image analysis device disclosed in this specification, it is possible to appropriately calculate the GTC using a breast ultrasound image formed by transmitting and receiving ultrasound waves to and from the breast. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a schematic diagram illustrating the configuration of an ultrasound diagnostic apparatus according to the present embodiment. [Figure 2]1A and 1B are diagrams showing examples of target breast ultrasound images and mammary gland regions. [Figure 3] FIG. 10 is a diagram showing an example of a correction screen for a mammary gland region. [Figure 4] FIG. 10 is a diagram showing an example of a fat region in a target breast ultrasound image. [Figure 5] FIG. 10 is a diagram showing an example of a correction screen for a fat region. [Figure 6] FIG. 10 is a conceptual diagram showing high-luminance pixels and low-luminance pixels in a modified mammary gland region. [Figure 7] FIG. 10 is a diagram showing an example of a GTC display screen. [Figure 8] FIG. 10 is a diagram showing another example of the GTC display screen. [Figure 9] 4 is a flowchart showing the flow of processing performed by the ultrasound diagnostic apparatus according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0019] 1 is a schematic diagram showing the configuration of an ultrasound diagnostic apparatus 10 as an ultrasound image analysis apparatus according to this embodiment. The ultrasound diagnostic apparatus 10 is a medical device installed in a medical institution such as a hospital.

[0020] The ultrasound diagnostic device 10 is a device that scans an object with an ultrasound beam and generates an ultrasound image as a medical image based on the received signals obtained thereby. In particular, in this embodiment, the ultrasound diagnostic device 10 forms a breast ultrasound image based on the received signals obtained by transmitting and receiving ultrasound waves to and from the object's breast.

[0021] The transmitter / receiver 14, signal processor 16, image generator 18, brightness value adjuster 20, display controller 22, mammary gland region identifier 32, fatty region identifier 34, threshold identifier 36, and GTC calculator 38 included in the ultrasound diagnostic apparatus 10 are configured by a processor. The processor includes at least one of a general-purpose processor (e.g., a central processing unit (CPU)) and a dedicated processor (e.g., a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a programmable logic device). The processor may not be a single processor, but may be configured by the cooperation of multiple processors located at physically separate locations. Each of the above components may be realized by the cooperation of hardware, such as a processor, and software.

[0022] The ultrasonic probe 12 is a device that transmits and receives ultrasonic waves to and from a subject. The ultrasonic probe 12 has a transducer array consisting of a plurality of transducer elements that transmit and receive ultrasonic waves to and from the subject. In particular, in this embodiment, the ultrasonic probe 12 is placed in contact with the subject's breast and transmits and receives ultrasonic waves to and from the breast.

[0023] The transmitter / receiver 14 transmits a transmission signal to the ultrasonic probe 12 (specifically, to each transducer element of the transducer element array) under the control of the controller 30 (described later). As a result, ultrasonic waves are transmitted from each transducer element toward the breast of the subject.

[0024] The transmitter / receiver 14 also receives reception signals from each transducer element that has received a reflected wave from the subject's breast. The transmitter / receiver 14 has an adder and a plurality of delays corresponding to each transducer element, and performs a delay-and-sum process in which the phases of the reception signals from each transducer element are aligned and added using the adder and the plurality of delays. This forms a reception beam signal in which information indicating the signal strength of the reflected wave from the subject is aligned in the depth direction of the subject.

[0025] The signal processing unit 16 performs various signal processing on the received beam signal from the transmitting / receiving unit 14, including filtering using a band-pass filter and detection processing.

[0026] The image forming unit 18 forms an ultrasound tomographic image (B-mode image) based on the received beam signals that have been signal-processed in the signal processing unit 16. In particular, in this embodiment, the image forming unit 18 forms a breast ultrasound image, which is a B-mode image. In this specification, the breast ultrasound image to be processed and used in the GTC calculation is referred to as a target breast ultrasound image. When simply referring to a breast ultrasound image, this means that it includes not only the target breast ultrasound image but also other breast ultrasound images. There may be multiple target breast ultrasound images. The multiple target breast ultrasound images may be of different cross sections. When there are multiple target breast ultrasound images, each unit described below processes each target breast ultrasound image.

[0027] The brightness value adjustment unit 20 adjusts the brightness value of each pixel constituting the breast ultrasound image formed by the image formation unit 18. The brightness value adjustment unit 20 may automatically adjust the brightness value of the breast ultrasound image based on a preset value previously set in the ultrasound diagnostic device 10. Alternatively, the brightness value adjustment unit 20 may adjust the brightness value of the breast ultrasound image in response to an instruction from a user such as a doctor. In this case, it is preferable that the user be able to specify the amount of brightness value adjustment for each depth.

[0028] The display control unit 22 controls the display of the target breast ultrasound tomographic image formed by the image forming unit 18 on the display 24. The display control unit 22 also controls the display 24 to display various information such as the calculation results of the GTC calculation unit 38 (described later). Details of the information displayed on the display 24 by the display control unit 22 will be described later.

[0029] The display 24 is a display device configured, for example, by a liquid crystal display or an organic EL (Electro Luminescence) display.

[0030] The memory 26 includes a hard disk drive (HDD), a solid state drive (SSD), an embedded multi-media card (eMMC), a read-only memory (ROM), or a random access memory (RAM). The memory 26 stores an ultrasound image analysis program for operating each unit of the ultrasound diagnostic device 10. The ultrasound image analysis program can also be stored in a computer-readable non-transitory storage medium such as a universal serial bus (USB) memory or a CD-ROM. The ultrasound diagnostic device 10 can read and execute the ultrasound image analysis program from such a storage medium.

[0031] The input interface 28 is configured by, for example, a button, a trackball, a touch panel, etc. The input interface 28 is used to input user commands to the ultrasound diagnostic apparatus 10.

[0032] The control unit 30 is configured to include at least one of a general-purpose processor (e.g., a CPU) and a dedicated processor (e.g., a GPU, an ASIC, an FPGA, or a programmable logic device). The control unit 30 may not be configured by a single processing device, but may be configured by the cooperation of multiple processing devices located in physically separate locations. The control unit 30 controls each unit of the ultrasound diagnostic device 10 in accordance with an ultrasound image analysis program stored in the memory 26.

[0033] The mammary gland region identifying unit 32 identifies a mammary gland region in the target breast ultrasound image. Fig. 2 is a diagram showing an example of the target breast ultrasound image TBUI and mammary gland region MR. The mammary gland region MR is the region between the subcutaneous fat region SF located directly below the body surface and the retromammary fat region RF located near the pectoral muscle in the depth direction. In Fig. 2, the mammary gland region MR is indicated by a dashed line.

[0034] The mammary gland region identifying unit 32 can identify the mammary gland region MR by analyzing the target breast ultrasound image TBUI. For example, the mammary gland region identifying unit 32 can identify the mammary gland region MR in the target breast ultrasound image TBUI by inputting the target breast ultrasound image TBUI to a learning model (e.g., a convolutional neural network) that is trained to identify the mammary gland region MR from a breast ultrasound image using the breast ultrasound image and a mammary gland region MR manually specified in the breast ultrasound image as learning data.

[0035] Furthermore, the mammary gland region identifying unit 32 may identify the mammary gland region MR in the target breast ultrasound image TBUI in response to an instruction from the user. For example, the display control unit 22 may cause the target breast ultrasound image TBUI to be displayed on the display 24, and the user may input an instruction indicating the mammary gland region MR to the ultrasound diagnostic device 10 using the input interface 28, and the mammary gland region identifying unit 32 may identify the mammary gland region MR based on the input instruction.

[0036] The display control unit 22 may present the target breast ultrasound image TBUI and the mammary gland region MR identified by the mammary gland region identification unit 32 to the user by displaying them on the display 24. The user may then be able to modify the mammary gland region MR on this screen (a screen for modifying the mammary gland region MR).

[0037] FIG. 3 is a diagram showing an example of a correction screen for the mammary gland region MR. On the correction screen shown in FIG. 3, the user can input a correction instruction for the mammary gland region MR to the ultrasound diagnostic device 10 using a cursor Cu displayed on the screen or the like. The mammary gland region identification unit 32 corrects the mammary gland region MR in accordance with the correction instruction from the user. The user may be able to specify a removal region ER as one of the correction instructions for the mammary gland region MR. The removal region ER is a region to be excluded from the mammary gland region MR. In FIG. 3, the removal region ER is indicated by a dashed line. The mammary gland region identification unit 32 determines the portion of the mammary gland region MR excluding the removal region ER as the corrected mammary gland region MR.

[0038] The display control unit 22 may display the mammary gland region MR and the removal region ER in different modes on the correction screen. This allows the user to easily distinguish between the mammary gland region MR and the removal region ER. For example, the boundary line of the mammary gland region MR may be displayed in blue, and the boundary line of the removal region ER may be displayed in red. Alternatively, the entire mammary gland region MR may be displayed in blue, and the entire removal region ER may be displayed in red. In this case, the mammary gland region MR and the removal region ER may be colored semi-transparently so as not to reduce the visibility of the target breast ultrasound image TBUI itself. Alternatively, as shown in FIG. 3, the boundary line of the mammary gland region MR and the boundary line of the removal region ER may be different line types.

[0039] The fat region identifying unit 34 identifies fat regions in the breast ultrasound image. In this embodiment, the fat region identifying unit 34 identifies fat regions in the target breast ultrasound image, but as will be described later, the fat region identifying unit 34 may identify fat regions in breast ultrasound images other than the target breast ultrasound image under certain conditions.

[0040] 4 is a diagram showing an example of a fat region FR in a target breast ultrasound image TBUI. The fat region FR is a region within the subcutaneous fat region SF or the retromammary fat region RF. In FIG. 4, the fat region FR is indicated by a dashed line.

[0041] The fat region identifying unit 34 can identify the fat region FR by analyzing the target breast ultrasound image TBUI. For example, the fat region identifying unit 34 can identify the fat region FR in the target breast ultrasound image TBUI by inputting the target breast ultrasound image TBUI to a learning model (e.g., a convolutional neural network) that is trained to identify the fat region FR from the breast ultrasound image using the breast ultrasound image and the fat region FR manually specified in the breast ultrasound image as learning data.

[0042] Furthermore, the fatty region identifying unit 34 may identify the fatty region FR in the target breast ultrasound image TBUI in response to an instruction from the user. For example, the display control unit 22 may display the target breast ultrasound image TBUI on the display 24, and the user may input an instruction indicating the fatty region FR to the ultrasound diagnostic device 10 using the input interface 28, and the fatty region identifying unit 34 may identify the fatty region FR based on the input instruction.

[0043] The display control unit 22 may present the target breast ultrasound image TBUI and the fatty region FR identified by the fatty region identification unit 34 to the user by displaying them on the display 24. The user may then be able to modify the mammary gland region MR on this screen (a screen for modifying the fatty region FR).

[0044] Fig. 5 is a diagram showing an example of a correction screen for the mammary gland region MR. On the correction screen shown in Fig. 5, the user can use a cursor Cu displayed on the screen or the like to input a correction instruction for the fatty region FR to the ultrasound diagnostic apparatus 10. The fatty region specifying unit 34 corrects the fatty region FR in accordance with the correction instruction from the user.

[0045] As described below, the fat region FR is used to determine a brightness threshold for dividing the pixel group constituting the mammary gland region MR into high-brightness pixels and low-brightness pixels. Specifically, the brightness threshold is determined based on the brightness value of each pixel constituting the fat region FR. Therefore, the fat region identifying unit 34 may identify the fat region FR in a breast ultrasound image other than the target breast ultrasound image TBUI, as long as the fat region FR has a brightness value equivalent to that of the fat region FR in the target breast ultrasound image TBUI. For example, multiple breast ultrasound images acquired by the same doctor are often adjusted so that their brightness values ​​are similar to each other. Therefore, the fat region identifying unit 34 may identify the fat region FR in another breast ultrasound image (not necessarily of the same subject) acquired by the same doctor as the target breast ultrasound image TBUI.

[0046] The threshold specifying unit 36 ​​specifies a brightness threshold based on the brightness values ​​of the pixels constituting the fat region FR specified by the fat region specifying unit 34. For example, the threshold specifying unit 36 ​​sets a representative value (e.g., average value) of the brightness values ​​of the pixels constituting the fat region FR as the brightness threshold. Alternatively, the threshold specifying unit 36 ​​may set a value obtained by adding or subtracting a predetermined bias value to or from the representative value of the brightness values ​​of the pixels constituting the fat region FR as the brightness threshold.

[0047] When the fat region FR has been corrected by the fat region specifying section 34, the threshold specifying section 36 may specify the brightness threshold based on the brightness value of each pixel that constitutes the corrected fat region FR.

[0048] In addition, when the brightness value of the target breast ultrasound image TBUI has been adjusted by the brightness value adjustment unit 20, the threshold determination unit 36 ​​may determine the brightness threshold based on the adjusted brightness value of each pixel that constitutes the fat region FR of the target breast ultrasound image TBUI.

[0049] The threshold value determination unit 36 ​​may calculate the variation in the luminance values ​​of each pixel that constitutes the fat region FR (or the modified fat region FR if modified). If the variation in the luminance values ​​of each pixel that constitutes the fat region FR is large, the luminance threshold may not be appropriate. Therefore, the display control unit 22 may notify the user when the variation in the luminance values ​​of each pixel that constitutes the fat region FR is equal to or greater than a predetermined variation threshold. This notification allows the user to modify or reselect the fat region FR.

[0050] In this embodiment, the threshold value specifying unit 36 ​​calculates the standard deviation s of the luminance values ​​of each pixel constituting the fat region FR as a parameter representing the variation in the luminance values ​​of each pixel constituting the fat region FR. Then, the display control unit 22 notifies the user when the standard deviation s of the luminance values ​​of each pixel constituting the fat region FR is equal to or greater than a predetermined standard deviation threshold.

[0051] Furthermore, the threshold specifying unit 36 ​​may specify a maximum brightness threshold within a possible brightness threshold range and a minimum brightness threshold within the brightness threshold range based on the variation in brightness values ​​of each pixel constituting the fat region FR. In this embodiment, the threshold specifying unit 36 ​​determines the maximum brightness threshold as m+s, which is obtained by adding the standard deviation s to a representative value (here, the average value m) of the brightness values ​​of the pixels constituting the fat region FR, and determines the minimum brightness threshold as ms, which is obtained by subtracting the standard deviation s from the average value m. How the maximum brightness threshold and the minimum brightness threshold are used will be described later. In this specification, the brightness threshold based on the representative value of the brightness values ​​of the pixels constituting the fat region FR may be referred to as a standard brightness threshold to distinguish it from the maximum brightness threshold and the minimum brightness threshold. When simply referred to as a brightness threshold, it means the standard brightness threshold.

[0052] The GTC calculation unit 38 calculates the GTC based on the target breast ultrasound image TBUI. Specifically, the GTC calculation unit 38 first divides the pixel group constituting the mammary gland region MR identified by the mammary gland region identification unit 32 into high-brightness pixels whose brightness values ​​are equal to or greater than the brightness threshold identified by the threshold identification unit 36, and low-brightness pixels whose brightness values ​​are less than the brightness threshold. In this embodiment, as shown in FIG. 6, the GTC calculation unit 38 forms a binarized image BI in the mammary gland region MR, in which the brightness values ​​of the high-brightness pixels HP are set to the maximum brightness and the brightness values ​​of the low-brightness pixels LP are set to the minimum brightness. Then, the GTC calculation unit 38 calculates the GTC, which is a parameter indicating the proportion of the number of low-brightness pixels LP in the mammary gland region MR.

[0053] In this embodiment, the GTC calculation unit 38 (Number of low-brightness pixels LP / Number of pixels in breast area MR) x 100 is calculated as GTC. However, the GTC may be calculated by other methods as long as it indicates the ratio of the number of low-luminance pixels LP in the mammary gland region MR. For example, since the number of pixels in the mammary gland region MR is the sum of the number of high-luminance pixels HP and the number of low-luminance pixels LP, the ratio of the number of high-luminance pixels HP to the number of low-luminance pixels LP may be calculated as the GTC.

[0054] When the mammary gland region MR has been corrected by the mammary gland region specifying section 32, the GTC calculation section 38 may calculate a GTC indicating the ratio of the number of low-luminance pixels LP in the corrected mammary gland region MR.

[0055] In addition, when the brightness value of the target breast ultrasound image TBUI is adjusted by the brightness value adjustment unit 20, the GTC calculation unit 38 may calculate a GTC indicating the proportion of low-brightness pixels LP in the mammary gland region MR of the target breast ultrasound image TBUI whose brightness value has been adjusted.

[0056] When there are multiple target breast ultrasound images TBUI, the GTC calculation unit 38 calculates a GTC for each target breast ultrasound image TBUI. Then, based on the multiple calculated GTCs, a representative GTC is calculated. In this embodiment, the GTC calculation unit 38 calculates an average GTC, which is the average value of the multiple GTCs, as the representative GTC.

[0057] If the threshold value specifying unit 36 ​​specifies a maximum brightness threshold and a minimum brightness threshold in addition to the standard brightness threshold, the GTC calculation unit 38 may calculate a maximum GTC, which is a GTC based on the maximum brightness threshold, and a minimum GTC, which is a GTC based on the minimum brightness threshold. That is, the GTC calculation unit 38 calculates, as the maximum GTC, a parameter indicating the proportion of the number of low-brightness pixels LP in the mammary gland region MR when the group of pixels constituting the mammary gland region MR is divided into high-brightness pixels HP whose brightness values ​​are equal to or greater than the maximum brightness threshold and low-brightness pixels LP whose brightness values ​​are less than the maximum brightness threshold. Also, the GTC calculation unit 38 calculates, as the minimum GTC, a parameter indicating the proportion of the number of low-brightness pixels LP in the mammary gland region MR when the group of pixels constituting the mammary gland region MR is divided into high-brightness pixels HP whose brightness values ​​are equal to or greater than the minimum brightness threshold and low-brightness pixels LP whose brightness values ​​are less than the minimum brightness threshold.

[0058] When there are multiple target breast ultrasound images TBUI, the GTC calculation unit 38 can determine a representative maximum GTC by taking a representative value (e.g., average value) of multiple maximum GTCs for each target breast ultrasound image TBUI, and can determine a representative minimum GTC by taking a representative value (e.g., average value) of multiple minimum GTCs for each target breast ultrasound image TBUI.

[0059] The display control unit 22, which serves as a provision processing unit, provides the GTC calculated by the GTC calculation unit 38 to the user by displaying it on the display 24. FIG. 7 is a diagram showing an example of a GTC display screen. The display control unit 22 displays the GTC calculated by the GTC calculation unit 38 as a numerical value P on the display 24. The display control unit 22 may also display the target breast ultrasound image TBUI and the binarized image BI on the display 24 in addition to the GTC numerical value P. When there are multiple target breast ultrasound images TBUI, the display control unit 22 displays a representative GTC on the GTC display screen.

[0060] The user may be able to modify the mammary gland region MR and the fatty region FR on the GTC display screen. For example, the user may use a cursor Cu or the like on the GTC display screen to input a modification instruction for the mammary gland region MR to the ultrasound diagnostic device 10. The user may be able to specify a removal region ER on the GTC display screen. The mammary gland region identification unit 32 modifies the mammary gland region MR in response to the modification instruction from the user. Furthermore, the user may use a cursor Cu or the like on the GTC display screen to input a modification instruction for the fatty region FR to the ultrasound diagnostic device 10. The fatty region identification unit 34 modifies the fatty region FR in response to the modification instruction from the user.

[0061] When the mammary gland region MR or the fatty region FR is modified on the GTC display screen, the GTC may fluctuate. Therefore, when the mammary gland region MR or the fatty region FR is modified on the GTC display screen, the threshold specification unit 36 ​​respecifies the brightness threshold based on the modified fatty region FR, and the GTC calculation unit 38 recalculates the GTC based on the modified mammary gland region MR and the respecified brightness threshold. The display control unit 22 then displays the recalculated GTC on the GTC display screen as a numerical value P. In this way, by modifying the mammary gland region MR or the fatty region FR on the GTC display screen, the user can easily grasp the fluctuation in the GTC due to the modification.

[0062] The user may also be able to adjust the brightness value of each pixel constituting the target breast ultrasound image TBUI on the GTC display screen. In this embodiment, the display control unit 22 displays a brightness adjustment controller C on the GTC display screen for adjusting the brightness value of each pixel constituting the target breast ultrasound image TBUI. The user can input an instruction to adjust the brightness value of each pixel constituting the target breast ultrasound image TBUI to the ultrasound diagnostic device 10 by operating the brightness adjustment controller C with the cursor Cu. The brightness value adjustment unit 20 adjusts the brightness value of each pixel constituting the target breast ultrasound image TBUI in accordance with the adjustment instruction from the user.

[0063] When the brightness value of each pixel constituting the target breast ultrasound image TBUI is adjusted on the GTC display screen, the GTC may fluctuate. Therefore, when the brightness value of each pixel constituting the target breast ultrasound image TBUI is adjusted on the GTC display screen, the threshold determination unit 36 ​​re-determines the brightness threshold based on the adjusted brightness value of each pixel constituting the fatty region FR of the target breast ultrasound image TBUI, and the GTC calculation unit 38 calculates the GTC indicating the proportion of low-brightness pixels LP in the glandular region MR of the target breast ultrasound image TBUI whose brightness value has been adjusted. The display control unit 22 then displays the recalculated GTC as a numerical value P on the GTC display screen. In this way, by adjusting the brightness value of each pixel constituting the target breast ultrasound image TBUI on the GTC display screen, the user can easily grasp the fluctuation of the GTC due to the adjustment of the brightness value.

[0064] Furthermore, the display control unit 22 may display a histogram H of the brightness values ​​of each pixel constituting the mammary gland region MR on the GTC display screen. Furthermore, the histogram H may indicate the brightness threshold value identified by the threshold value identification unit 36. In the example of FIG. 7, the frequency of pixels having brightness lower than the brightness threshold value (i.e., low-brightness pixels LP) is indicated by shading, and the frequency of pixels having brightness higher than the brightness threshold value (i.e., high-brightness pixels HP) is indicated by white. This allows the user to intuitively grasp graphically the ratio of low-brightness pixels LP to high-brightness pixels HP among the pixels constituting the mammary gland region MR.

[0065] When the GTC calculation unit 38 calculates the maximum GTC and the minimum GTC, the display control unit 22 may provide the maximum GTC and the minimum GTC to the user. For example, as shown in Fig. 8, the display control unit 22 may display the maximum GTC value Pmax and the minimum GTC value Pmin on the GTC display screen. When there are multiple target breast ultrasound images TBUI, the display control unit 22 may display the representative maximum GTC value and the representative minimum GTC value on the GTC display screen.

[0066] The display control unit 22 may also provide the user with the difference between the maximum GTC and the minimum GTC (or the difference between the representative maximum GTC and the representative minimum GTC). For example, the display control unit 22 may display a numerical value indicating the difference between the maximum GTC and the minimum GTC on the GTC display screen, instead of or in addition to the maximum GTC numerical value Pmax and the minimum GTC numerical value Pmin.

[0067] Furthermore, the display control unit 22 may notify the user when the difference between the maximum GTC and the minimum GTC (or the difference between the representative maximum GTC and the representative minimum GTC) is equal to or greater than a predetermined GTC threshold. For example, the display control unit 22 may display a predetermined message on the GTC display screen when the difference between the maximum GTC and the minimum GTC is equal to or greater than the GTC threshold.

[0068] The outline of the configuration of the ultrasound diagnostic apparatus 10 according to this embodiment has been described above. The flow of processing by the ultrasound diagnostic apparatus 10 will be described below with reference to the flowchart shown in FIG.

[0069] In step S10, one target breast ultrasound image TBUI is selected as a processing object from among a plurality of target breast ultrasound images TBUI, which are B-mode images formed by the image forming unit 18.

[0070] In step S12, the brightness value adjuster 20 adjusts the brightness value of each pixel constituting the target breast ultrasound image TBUI selected in step S10.

[0071] In step S14, the mammary gland region specifying unit 32 specifies the mammary gland region MR in the target breast ultrasound image TBUI.

[0072] In step S16, a fatty region FR is identified in the target breast ultrasound image TBUI.

[0073] In step S18, the threshold specifying unit 36 ​​specifies a brightness threshold based on the brightness value of each pixel that constitutes the fat region FR specified by the fat region specifying unit 34.

[0074] In step S20, the GTC calculation unit 38 divides the group of pixels constituting the mammary gland region MR identified in step S14 into high-brightness pixels HP whose brightness values ​​are equal to or greater than the brightness threshold identified in step S18 and low-brightness pixels LP whose brightness values ​​are less than the brightness threshold. Then, the GTC calculation unit 38 calculates the GTC, which is a parameter indicating the proportion of low-brightness pixels LP in the mammary gland region MR.

[0075] In step S22, the GTC calculation unit 38 determines whether or not GTCs have been calculated for all target breast ultrasound images TBUI to be processed. If there are any target breast ultrasound images TBUI for which GTCs have not been calculated, the process returns to step S10, and from step S10 onwards, processing is performed for the other target breast ultrasound images TBUI (calculating GTCs). If GTCs have been calculated for all target breast ultrasound images TBUI, the process proceeds to step S24.

[0076] In step S24, the GTC calculation unit 38 calculates an average GTC, which is a representative GTC of the multiple GTCs calculated for each target breast ultrasound image TBUI.

[0077] In step S26, the display control unit 22 causes the display 24 to display a GTC display screen including the average GTC value calculated in step S24.

[0078] The above describes the ultrasound image analysis device according to the present disclosure, but the ultrasound image analysis device according to the present disclosure is not limited to the above embodiment, and various modifications are possible as long as they do not deviate from the spirit of the device.

[0079] For example, in the above embodiment, the ultrasound image analysis device is the ultrasound diagnostic device 10, but the ultrasound image analysis device is not limited to the ultrasound diagnostic device 10. For example, the ultrasound image analysis device may be a personal computer (PC (Personal Computer)) or a server having a processor, memory, a communication interface, an input interface, and a display. In this case, the processor of the PC or server serving as the ultrasound image analysis device performs the functions of the brightness value adjustment unit 20, the display control unit 22, the mammary gland region identification unit 32, the fat region identification unit 34, the threshold identification unit 36, and the GTC calculation unit 38, acquires a target breast ultrasound image TBUI from the ultrasound diagnostic device or the like, and performs GTC calculation processing on the acquired target breast ultrasound image TBUI. [Explanation of symbols]

[0080] 10 Ultrasound diagnostic device, 12 Ultrasound probe, 14 Transmitter / receiver unit, 16 Signal processing unit, 18 Image formation unit, 20 Brightness value adjustment unit, 22 Display control unit, 24 Display, 26 Memory, 28 Input interface, 30 Control unit, 32 Mammary gland region identification unit, 34 Fat region identification unit, 36 Threshold identification unit, 38 GTC calculation unit.

Claims

1. a mammary gland region identifying unit that identifies a mammary gland region in a target breast ultrasound image that is a processing target and is formed by transmitting and receiving ultrasound waves to and from the breast; a fat region identifying unit that identifies a fat region in a breast ultrasound image formed by transmitting and receiving ultrasound waves to and from the breast; a threshold value specifying unit that specifies a brightness threshold value based on the brightness value of each pixel that constitutes the fat region; a GTC calculation unit that divides a group of pixels constituting the mammary gland region into high-luminance pixels whose luminance values ​​are equal to or greater than the luminance threshold and low-luminance pixels whose luminance values ​​are less than the luminance threshold, and calculates a GTC that indicates the ratio of the number of low-luminance pixels in the mammary gland region; a providing processing unit that provides the GTC to a user; An ultrasound image analysis device comprising:

2. the target breast ultrasound image and the identified mammary gland region are presented to the user; the mammary gland region specifying unit corrects the mammary gland region in response to an instruction from the user; The GTC calculation unit calculates a GTC indicating a ratio of the number of low-luminance pixels in the mammary gland region after correction.

2. The ultrasonic image analysis device according to claim 1.

3. the breast ultrasound image is the target breast ultrasound image; The ultrasound image analyzer includes: a brightness value adjusting unit that adjusts the brightness value of each pixel that constitutes the target breast ultrasound image; Furthermore, the threshold specifying unit specifies the brightness threshold based on the adjusted brightness value of each pixel constituting the fat region of the target breast ultrasound image; The GTC calculation unit calculates a GTC indicating a ratio of the number of low-brightness pixels in the mammary gland region of the target breast ultrasound image whose brightness values ​​have been adjusted.

2. The ultrasonic image analysis device according to claim 1.

4. the target breast ultrasound image and the identified fat region are presented to the user; the fat region specifying unit corrects the fat region in response to an instruction from the user; the threshold specifying unit specifies the brightness threshold based on a brightness value of each pixel constituting the modified fat region.

2. The ultrasonic image analysis device according to claim 1.

5. The providing processing unit notifies the user when a variation in luminance values ​​of the pixels constituting the fat region is equal to or greater than a variation threshold.

2. The ultrasonic image analysis device according to claim 1.

6. the threshold specifying unit specifies a maximum luminance threshold value and a minimum luminance threshold value in a luminance threshold range that the luminance threshold value can take, based on a variation in luminance values ​​of the pixels that constitute the fat region; the GTC calculation unit calculates a maximum GTC, which is the GTC based on the maximum brightness threshold, and a minimum GTC, which is the GTC based on the minimum brightness threshold; The providing processing unit provides at least one of the maximum GTC and the minimum GTC, or the difference between the maximum GTC and the minimum GTC to the user, or provides the difference between the maximum GTC and the minimum GTC to the user when the difference is equal to or greater than a GTC threshold.

2. The ultrasonic image analysis device according to claim 1.

7. Computer, a mammary gland region identifying unit that identifies a mammary gland region in a target breast ultrasound image that is a processing target and is formed by transmitting and receiving ultrasound waves to and from the breast; a fat region identifying unit that identifies a fat region in a breast ultrasound image formed by transmitting and receiving ultrasound waves to and from the breast; a threshold value specifying unit that specifies a brightness threshold value based on the brightness value of each pixel that constitutes the fat region; a GTC calculation unit that divides a group of pixels constituting the mammary gland region into high-luminance pixels whose luminance values ​​are equal to or greater than the luminance threshold and low-luminance pixels whose luminance values ​​are less than the luminance threshold, and calculates a GTC that indicates the ratio of the number of low-luminance pixels in the mammary gland region; a providing processing unit that provides the GTC to a user; An ultrasound image analysis program characterized by functioning as follows.

Images