Ultrasonic image analysis apparatus, ultrasonic diagnostic apparatus, and control method for ultrasonic image analysis apparatus

Abstract

To provide an ultrasonic image analysis device, an ultrasonic diagnostic device, and a control method of an ultrasonic image analysis device capable of estimating a risk of cancer in a mammary gland region on the basis of an ultrasonic image as necessary on the basis of a result of a mammography examination.SOLUTION: Information on a structure of the breast of a subject acquired in a mammography examination is acquired by a breast structure information acquisition unit F. It is determined by an analysis determination unit 37 whether or not to execute analysis of a GTC (gland tissue composition) region including the lactiferous vessel and the lobule in a mammary gland region, and a peripheral interstitial tissue on the basis of the information on the structure of the breast of the subject. When the analysis is determined to be executed, the analysis of the GTC region is executed by a GTC region analysis unit 38 on the basis of an ultrasonic image of the breast of the subject.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an ultrasonic image analysis apparatus that analyzes ultrasonic images of a subject's breast being imaged. The present invention also relates to an ultrasonic diagnostic apparatus including the ultrasonic image analysis apparatus, and a control method for the ultrasonic image analysis apparatus.

Background Art

[0002] Conventionally, in the medical field, ultrasonic diagnostic apparatuses using ultrasonic images have been put into practical use. Generally, an ultrasonic diagnostic apparatus includes an ultrasonic probe incorporating a transducer array and an apparatus main body connected to the ultrasonic probe. The ultrasonic probe transmits an ultrasonic beam toward a subject, receives an ultrasonic echo from the subject with the ultrasonic probe, and generates an ultrasonic image by electrically processing the received signal.

[0003] Although the compositions of breast fat and mammary gland tissue vary among individuals, the anatomical structures of the breasts are common. In mammary gland tissue, it branches from the main duct to the extralobular duct and further connects to a large number of lobules. There is stroma around the lobules, and the mammary gland tissue is composed of the stroma as well. As stroma around the lobules, it is known that there are two types: peripheral stroma and edematous stroma. The peripheral stroma exists along the structure from the lobules to the ducts and contains a large amount of collagen fibers. On the other hand, the edematous stroma fills the space between the peripheral stroma, is rich in matrix, and collagen fibers, fat, etc. are mixed, and has fewer collagen fibers than the peripheral stroma.

[0004] In recent years, the concept of individual patient risk management has been spreading, and it is known that the ratio of the mammary gland area in the breast, particularly a high concentration of mammary gland, is a cancer risk factor. The ratio of the mammary gland area in the breast can be measured using a mammography apparatus. In Non-Patent Document 1, it is reported that even when the breast region is substantially the same, cancer is likely to occur when the ratio of the GTC (Glandular Tissue Component) region including ducts, lobules, and surrounding stroma within the breast region is high. That is, in addition to the ratio of the breast region within the breast, the ratio of the GTC region within the breast region can be a risk factor. This means that the risk is high in patients in whom lobular involution does not progress.

[0005] However, in a mammography device, it is impossible to distinguish between the surrounding stroma and the edematous stroma, and the entire breast tissue is observed in a white-like manner, so that the ratio of the GTC region in the breast region cannot be measured. Patent Document 1 discloses an ultrasonic diagnostic apparatus that extracts a breast region by detecting a boundary in the depth direction of an ultrasonic image and detects a lesion present in the breast region.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] However, the ultrasonic diagnostic apparatus of Patent Document 1 is aimed at detecting a lesion within the breast region and has no interest in further dividing the breast region into finer tissues. For this reason, there has been a problem that the risk of cancer in the breast region cannot be estimated. In addition, when the mammary gland regresses and the volume of the breast decreases, a fat area may be generated between the lobes in the mammary gland, etc., and the ratio of the mammary gland area to the breast area may decrease. In such a case, the cancer risk is low, and the necessity of measuring the ratio of the GTC area in the mammary gland area becomes low.

[0008] The present invention has been made to solve such conventional problems, and an ultrasonic image analysis apparatus capable of estimating the cancer risk in the mammary gland area based on an ultrasonic image as needed, based on the results of mammography examination, is provided. Another object of the present invention is to provide an ultrasonic diagnostic apparatus including such an ultrasonic image analysis apparatus and a control method for the ultrasonic image analysis apparatus.

Means for Solving the Problems

[0009] To achieve the above object, the ultrasonic image analysis apparatus according to the present invention includes a breast configuration information acquisition unit that acquires information regarding the breast configuration of a subject obtained by mammography examination, an analysis determination unit that determines whether or not to perform analysis of tissue composition regions within the mammary gland region based on the information regarding the breast configuration acquired by the breast configuration information acquisition unit, the gland and an adenoid tissue composition region analysis unit that analyzes the adenoid tissue composition region based on an ultrasonic image of the breast of the subject when it is determined by the analysis determination unit that analysis is to be performed. It is characterized by comprising 、 The mammary gland region includes mammary ducts, lobules, the surrounding stroma that exists along the structure from the lobules to the mammary ducts, and the edematous stroma that fills the space between the surrounding stroma. The surrounding stroma contains more collagen fibers than the edematous stroma. The glandular tissue composition region includes mammary ducts, lobules, and the surrounding stroma within the mammary gland region and does not include the edematous stroma. The glandular tissue composition region analysis unit detects the mammary gland region from the ultrasonic image, extracts the glandular tissue composition region by binarizing the detected mammary gland region using a luminance threshold value, and calculates the ratio of the glandular tissue composition region to the mammary gland region.

[0010] The breast composition information acquisition unit can acquire, as information regarding the breast composition, the breast category corresponding to the subject from among a plurality of types of breast categories classified according to breast density. In this case, it is preferable that the analysis determination unit determines to perform analysis of the glandular tissue composition region when the breast category corresponding to the subject belongs to at least one breast category determined in descending order of breast density among the plurality of types of breast categories classified.

[0011] The breast composition information acquisition unit may acquire, as information regarding the breast composition, the ratio of the breast region to the breast area of the subject. Further, the breast composition information acquisition unit can have a breast composition information calculation unit that calculates the ratio of the breast region to the breast area of the subject from a mammography image. It is preferable that the analysis determination unit determines to perform analysis of the glandular tissue composition region when the ratio of the breast region to the breast area is higher than a determined breast region threshold value. Furthermore, the breast composition information acquisition unit may acquire, as information regarding the breast composition, the ratio of the breast mass to the breast region of the subject. In this case, it is preferable that the analysis determination unit determines to perform analysis of the glandular tissue composition region when the ratio of the breast mass to the breast region is higher than a determined breast mass threshold value.

[0012] The glandular tissue composition region analysis unit can calculate the ratio of the glandular tissue composition region to the breast region. The glandular tissue composition region analysis unit includes a breast region detection unit that detects a breast region from an ultrasonic image, a glandular tissue composition region extraction unit that extracts the glandular tissue composition region within the breast region detected by the breast region detection unit, and a glandular tissue composition region ratio calculation unit that calculates the ratio of the glandular tissue composition region to the breast region and preferably includes the above.

[0013] The mammary gland region detection unit can detect the mammary gland region by performing image recognition on the ultrasound image. In this case, the device includes a breast region detection unit that detects the breast region located between the skin and the pectoral muscle from the ultrasound image, and the mammary gland region detection unit may recognize an anterior boundary line and a posterior boundary line within the breast region detected by the breast region detection unit, and detect the region between the anterior boundary line and the posterior boundary line as the mammary gland region. Alternatively, the mammary gland region detection unit can detect the mammary gland region from the ultrasound image using deep learning.

[0015] The glandular tissue region proportion calculation unit can calculate the proportion of the glandular tissue region to the mammary gland region based on the number of pixels occupied by the mammary gland region and the number of pixels occupied by the glandular tissue region in the ultrasound image. The ultrasound image may be a three-dimensional ultrasound image, and the glandular tissue composition area ratio calculation unit may be configured to calculate the ratio of the glandular tissue composition area to the mammary gland area based on the volume of the mammary gland area detected by the mammary gland area detection unit and the volume of the glandular tissue composition area extracted by the glandular tissue composition area extraction unit.

[0016] The ultrasonic diagnostic apparatus according to the present invention comprises: a monitor for displaying an ultrasound image; The above-mentioned ultrasonic image analysis device and Equipped with The glandular tissue composition region analysis section is characterized by displaying the analysis results of the glandular tissue composition region on a monitor.

[0017] The glandular tissue composition region analysis unit preferably stores the analysis result of the glandular tissue composition region in a tag associated with the ultrasound image. It is preferable to include an ultrasonic probe and an image generating unit that generates an ultrasonic image of the subject's breast by transmitting and receiving an ultrasonic beam to and from the subject using the ultrasonic probe.

[0018] A method for controlling an ultrasonic image analysis device according to the present invention includes the steps of: Obtaining information regarding the subject's breast configuration obtained by mammography; Based on the obtained information about the breast structure,the gland Determine whether to perform an analysis of the tissue composition area, and when it is determined to perform the analysis, analyze the glandular tissue composition area based on the ultrasonic image of the subject's breast being imaged and The mammary gland region includes mammary ducts, lobules, the surrounding stroma that exists along the structure from the lobules to the mammary ducts, and the edematous stroma that fills the space between the surrounding stroma. The surrounding stroma contains more collagen fibers than the edematous stroma. The glandular tissue composition region includes mammary ducts, lobules, and the surrounding stroma within the mammary gland region and does not include the edematous stroma. The analysis of the glandular tissue composition region detects the mammary gland region from the ultrasonic image, extracts the glandular tissue composition region by binarizing the detected mammary gland region using a luminance threshold value, and calculates the ratio of the glandular tissue composition region to the mammary gland region. which is characterized by the above.

Effect of the Invention

[0019] According to the present invention, the breast composition information acquisition unit acquires information regarding the breast composition of the subject obtained by mammography, and the analysis determination unit determines whether to perform an analysis of the glandular tissue composition area including the milk ducts, lobules, and surrounding stroma in the mammary gland area based on the information regarding the breast composition. When it is determined to perform the analysis, the glandular tissue composition area analysis unit analyzes the glandular tissue composition area based on the ultrasonic image of the subject's breast being imaged. Therefore, it is possible to estimate the risk of cancer in the mammary gland area based on the ultrasonic image as necessary, taking into account the results of mammography.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0021] Hereinafter, embodiments of the present invention will be described based on the accompanying drawings. The description of the constituent elements described below is based on typical embodiments of the present invention, but the present invention is not limited to such embodiments. In this specification, a numerical range represented by "~" means a range including the numerical values described before and after "~" as the lower limit value and the upper limit value. In this specification, "identical" and "the same" shall include an error range generally acceptable in the technical field.

[0022] FIG. 1 shows the configuration of an ultrasonic diagnostic device 1 according to an embodiment of the present invention. The ultrasonic diagnostic device 1 includes an ultrasonic probe 2 and a diagnostic device main body 3. The ultrasonic probe 2 and the diagnostic device main body 3 are wired-connected to each other via a cable (not shown).

[0023] The ultrasonic probe 2 has a transducer array 21 and a transmission / reception circuit 22 connected to the transducer array 21.

[0024] The diagnostic device main body 3 has an image generation unit 31 connected to the transmission / reception circuit 22 of the ultrasonic probe 2. A display control unit 32 and a monitor 33 are sequentially connected to the image generation unit 31, and an image memory 34 is connected to the image generation unit 31. Also, the diagnostic device main body 3 has a main body side communication unit 35, a breast composition information calculation unit 36 is connected to the main body side communication unit 35, and an analysis determination unit 37 is connected to the main body side communication unit 35 and the breast composition information calculation unit 36. Furthermore, a GTC (Glandular Tissue Component) region analysis unit 38 is connected to the image memory 34 and the analysis determination unit 37, and an inspection result memory 39 and a display control unit 32 are connected to the GTC region analysis unit 38.

[0025] A main body control unit 40 is connected to the image generation unit 31, the display control unit 32, the image memory 34, the main body side communication unit 35, the breast composition information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the inspection result memory 39, and an input device 41 is connected to the main body control unit 40. Also, the transmission / reception circuit 22 of the ultrasonic probe 2 is connected to the main body control unit 40. A processor 42 is constituted by the image generation unit 31, the display control unit 32, the main body side communication unit 35, the breast composition information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the main body control unit 40.

[0026] Also, an ultrasonic image analysis device 4 is constituted by the main body side communication unit 35, the breast composition information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the main body control unit 40 within the processor 42. Furthermore, a mammography device 6 and a server 7 are connected to the main body side communication unit 35 via a network 5.

[0027] The transducer array 21 of the ultrasonic probe 2 has a plurality of ultrasonic transducers arranged in one or two dimensions. These transducers transmit ultrasonic waves according to drive signals supplied from the transmission / reception circuit 22, and receive reflected waves from the subject to output analog reception signals. Each transducer is configured, for example, by forming electrodes at both ends of a piezoelectric body composed of piezoelectric ceramics typified by PZT (Lead Zirconate Titanate), polymer piezoelectric elements typified by PVDF (Poly Vinylidene Di Fluoride), and piezoelectric single crystals typified by PMN-PT (Lead Magnesium Niobate-Lead Titanate solid solution).

[0028] Under the control of the main body control unit 40, the transmission / reception circuit 22 transmits ultrasonic waves from the transducer array 21 and generates a beam signal based on the reception signal acquired by the transducer array 21. As shown in FIG. 2, the transmission / reception circuit 22 has a pulsar 23 connected to the transducer array 21, and an amplification unit 24, an AD (Analog Digital) conversion unit 15, and a beamformer 26 that are sequentially connected in series to the transducer array 21.

[0029] The pulsar 23 includes, for example, a plurality of pulse generators, and supplies drive signals to the plurality of transducers of the transducer array 21 while adjusting the delay amount so that the ultrasonic waves transmitted from the plurality of transducers of the transducer array 21 form an ultrasonic beam based on the transmission delay pattern selected according to the control signal from the main body control unit 40. Thus, when a pulsed or continuous-wave voltage is applied to the electrodes of the transducers of the transducer array 21, the piezoelectric body expands and contracts, generating pulsed or continuous-wave ultrasonic waves from each transducer, and an ultrasonic beam is formed from the combined wave of these ultrasonic waves.

[0030] The transmitted ultrasonic beam is reflected, for example, by a target such as a part of a subject, and the ultrasonic echo propagates toward the transducer array 21 of the ultrasonic probe 2. The ultrasonic echo propagating toward the transducer array 21 in this way is received by each transducer constituting the transducer array 21. At this time, each transducer constituting the transducer array 21 expands and contracts by receiving the propagating ultrasonic echo, generates a received signal which is an electrical signal, and outputs these received signals to the amplifier unit 24.

[0031] The amplifier unit 24 amplifies the signals input from each transducer constituting the transducer array 21 and transmits the amplified signals to the AD conversion unit 25. The AD conversion unit 25 converts the signals transmitted from the amplifier unit 24 into digital received data and transmits these received data to the beamformer 26. The beamformer 26 gives respective delays to each of the received data converted by the AD conversion unit 25 according to the sound speed or the distribution of the sound speed set based on the reception delay pattern selected according to the control signal from the main body control unit 40, and adds them together, thereby performing so-called reception focusing processing. By this reception focusing processing, each of the received data converted by the AD conversion unit 25 is coherently added, and a beam signal in which the focus of the ultrasonic echo is narrowed is obtained.

[0032] As shown in FIG. 3, the image generation unit 31 of the diagnostic apparatus main body 3 has a configuration in which a signal processing unit 51, a DSC (Digital Scan Converter) 52, and an image processing unit 53 are sequentially connected in series. The signal processing unit 51 performs attenuation correction according to the distance according to the depth of the reflection position of the ultrasonic wave on the beam signal sent out from the transmission / reception circuit 22 of the ultrasonic probe 2, and then performs envelope detection processing, thereby generating an ultrasonic image signal (B-mode image signal) which is tomographic image information about the tissue in the subject.

[0033] The DSC 52 converts (raster-converts) the ultrasonic image signal generated by the signal processing unit 51 into an image signal conforming to the scanning method of a normal television signal. The image processing unit 53 performs various necessary image processes such as tone processing on the ultrasonic image signal input from the DSC 52, and then outputs a signal representing the ultrasonic image to the display control unit 32 and the image memory 34. The signal representing the ultrasonic image generated by the image generation unit 31 in this way will simply be referred to as the ultrasonic image.

[0034] The display control unit 32 performs predetermined processing on the ultrasonic image sent from the image generation unit 31 under the control of the main body control unit 40, and displays the ultrasonic image on the monitor 33. The monitor 33 displays the ultrasonic image under the control of the display control unit 32, and has a display device such as an LCD (Liquid Crystal Display), an organic EL display (Organic Electroluminescence Display), etc.

[0035] The image memory 34 is a memory that stores the ultrasonic image generated by the image generation unit 31 under the control of the main body control unit 40. For example, the image memory 34 can hold a plurality of frames of ultrasonic images generated by the image generation unit 31 corresponding to the diagnosis of the subject's breast.

[0036] As the image memory 34, recording media such as flash memory, HDD (Hard Disc Drive), SSD (Solid State Drive), FD (Flexible Disc), MO disc (Magneto - Optical disc), MT (Magnetic Tape), RAM (Random Access Memory), CD (Compact Disc), DVD (Digital Versatile Disc), SD card (Secure Digital card), USB memory (Universal Serial Bus memory), etc. can be used.

[0037] Under the control of the main body control unit 40, the main body side communication unit 35 receives breast composition information or mammography images regarding the breast composition of the subject transmitted from the mammography device 6 or the server 7 via the network 5. Note that as the breast composition information, the breast category Cm corresponding to the subject, the breast area ratio Rm1 which is the ratio of the breast area to the breast region of the subject, and the breast mass ratio Rm2 which is the ratio of the breast mass to the breast region of the subject obtained by mammography examination can be used.

[0038] In the 5th edition of BI-RADS (Breast Imaging Reporting and Data System 5th - edition), which is the comprehensive guideline for breast cancer image diagnosis by ACR (American College of Radiology), the breast composition is recommended to be classified into four types of breast categories C1 to C4, namely "fatty", "scattered breast tissue", "heterogeneously dense", and "extremely dense", from the lower breast density to the higher one. For example, the breast categories C4 of "extremely dense" and C3 of "heterogeneously dense" showing high breast density are regarded as risk factors for breast cancer, and in mammography examination, the breast category Cm corresponding to the subject is often shown as the examination result. Therefore, the main body side communication unit 35 receives the breast category Cm of the subject obtained by the mammography examination in the mammography device 6 as the breast composition information from the mammography device 6 or the server 7. Note that the breast category Cm of the subject can be automatically or manually assigned by the user in the mammography device 6, the server 7, or other workstations, etc., and the main body side communication unit 35 can also receive it from these mammography devices 6, the server 7, or other workstations, etc.

[0039] In addition, software for analyzing breast density from mammography images has been developed. By using this software, the mammography apparatus 6 or the server 7 can calculate the breast region ratio Rm1, which is the ratio of the breast region to the breast area of the subject in the mammography image. The main body side communication unit 35 can also receive the breast region ratio Rm1 as breast composition information from the mammography apparatus 6 or the server 7.

[0040] Furthermore, for example, in Japanese Patent Laid-Open No. 2019-177050, it is described that the breast mass ratio Rm2, which is the ratio of the breast mass to the breast region of the subject in the mammography image, that is, the breast tissue content ratio in the breast concentration region where the breast is concentrated is measured by the volume ratio. The main body side communication unit 35 may receive the breast mass ratio Rm2 as breast composition information from the mammography apparatus 6 or the server 7.

[0041] In this way, when the breast category Cm, the breast region ratio Rm1, or the breast mass ratio Rm2 is received as breast composition information from the mammography apparatus 6 or the server 7 by the main body side communication unit 35, the main body side communication unit 35 sends the received breast composition information to the analysis determination unit 37.

[0042] In addition, the main body side communication unit 35 can also receive a mammography image from the mammography apparatus 6 or the server 7 instead of breast composition information. In this case, the main body side communication unit 35 sends the received mammography image to the breast composition information calculation unit 36.

[0043] The breast composition information calculation unit 36 calculates the breast region ratio Rm1, which is the ratio of the breast region to the breast area of the subject in the mammography image. As shown in FIG. 4, it has a breast region detection unit 54 connected to the main body side communication unit 35, a breast region detection unit 55 connected to the breast region detection unit 54, and a breast region ratio calculation unit 56 connected to the breast region detection unit 54 and the breast region detection unit 55.

[0044] The breast region detection unit 54 analyzes the mammography image received by the main body side communication unit 35 to detect the breast region of the subject imaged in the mammography image, and the mammary gland region detection unit 55 detects the mammary gland region of the subject from within the breast region in the mammography image detected by the breast region detection unit 54. Based on the breast region detected by the breast region detection unit 54 and the mammary gland region detected by the mammary gland region detection unit 55, the mammary gland region ratio calculation unit 56 calculates the mammary gland region ratio Rm1 in the mammography image, and sends the calculated mammary gland region ratio Rm1 to the analysis and determination unit 37 as breast composition information. Note that the breast composition information calculation unit 36 can also detect the breast region and the mammary gland region from the mammography image using a determination model learned using machine learning techniques such as deep learning, and calculate the mammary gland region ratio Rm1, which is the ratio of the mammary gland region to the breast region of the subject.

[0045] Note that when the main body side communication unit 35 receives a mammography image composed of a three-dimensional image, the mammary gland region ratio calculation unit 56 can calculate the mammary gland region ratio Rm1 based on the ratio of the volume of the breast region detected by the breast region detection unit 54 to the volume of the mammary gland region detected by the mammary gland region detection unit 55. Also, when the main body side communication unit 35 receives a mammography image composed of a two-dimensional image, the mammary gland region ratio calculation unit 56 may calculate the mammary gland region ratio Rm1 based on the ratio of the area of the breast region detected by the breast region detection unit 54 to the area of the mammary gland region detected by the mammary gland region detection unit 55.

[0046] The breast composition information acquisition unit F for acquiring the breast composition information obtained in the mammography examination is configured by the main body side communication unit 35 and the breast composition information calculation unit 36, and the breast composition information consisting of the breast category Cm, the mammary gland region ratio Rm1, and the mammary gland volume ratio Rm2 received by the main body side communication unit 35, or the breast composition information consisting of the mammary gland region ratio Rm1 calculated by the breast composition information calculation unit 36 based on the mammography image is sent from the breast composition information acquisition unit F to the analysis and determination unit 37. In addition, the breast composition information calculation unit 36 can calculate not only the breast tissue area ratio Rm1, but also at least one of the breast category Cm and the breast tissue volume ratio Rm2. In this case, the breast composition information consisting of the breast category Cm, the breast tissue area ratio Rm1, and the breast tissue volume ratio Rm2 may be sent from the breast composition information calculation unit 36 to the analysis and determination unit 37.

[0047] The analysis and determination unit 37 determines whether to analyze the GTC region including the lactiferous ducts, lobules, and surrounding stroma within the breast tissue area based on the breast composition information acquired by the breast composition information acquisition unit F.

[0048] It has been reported in the above-mentioned Non-Patent Document 1 that the ratio of the GTC region in the breast tissue area can be a cancer risk factor, and analyzing the GTC region within the breast tissue area has great significance in estimating the cancer risk. However, when the ratio of the breast tissue area to the breast area decreases due to breast involution and a decrease in breast volume, etc., the cancer risk becomes lower, and thus the necessity of analyzing the GTC region within the breast tissue area becomes less. In addition, in the mammography image obtained by the mammography apparatus, the surrounding stroma and the edematous stroma cannot be distinguished, so it is necessary to use an ultrasonic image to analyze the GTC region.

[0049] Therefore, the analysis and determination unit 37 determines whether to analyze the GTC region based on the breast composition information of the subject obtained by the mammography examination. That is, when it is determined that it is desirable to estimate the cancer risk in the breast tissue area in more detail based on the breast composition information of the subject acquired by the breast composition information acquisition unit F, the analysis of the GTC region is determined to be performed. On the other hand, when it is determined that the cancer risk is low based on the breast composition information, it is determined not to perform the analysis of the GTC region using the ultrasonic image. Thereby, it becomes possible to perform an effective cancer risk estimation according to the subject.

[0050] Specifically, when the breast category Cm of the subject is input from the main body side communication unit 35, the analysis determination unit 37 determines whether the input breast category Cm is the breast category C4 of "extremely high concentration" or the breast category C3 of "heterogeneous high concentration", which are determined in descending order of breast density among the four classified breast categories C1 to C4. When it belongs to the breast categories C4 and C3 indicating these high breast densities, the analysis of the GTC region is determined to be carried out. On the other hand, when the input breast category Cm is the breast category C2 of "scattered breast" or the breast category C1 of "fatty", which indicates a relatively low breast density, the analysis determination unit 37 determines that the cancer risk is low and decides not to perform the analysis of the GTC region.

[0051] Note that it is not limited to determining to perform the GTC region analysis only when the breast category Cm of the subject belongs to the two breast categories C4 and C3 determined in descending order of breast density among the four classified breast categories C1 to C4. For example, when the breast category Cm of the subject is any one of the breast category C4 of "extremely high concentration", the breast category C3 of "heterogeneous high concentration", and the breast category C2 of "scattered breast", which are determined in descending order of breast density, the GTC region analysis may be determined to be carried out. Furthermore, the GTC region analysis may be determined to be carried out only in the case of the breast category C4 of "extremely high concentration" with the highest breast density.

[0052] Also, in the above-mentioned BI-RADS version 5, the classification of four types of breast categories is recommended, but not limited to this. When the breast category Cm of the subject belongs to at least one breast category determined in descending order of breast density among multiple classified breast categories, the GTC region analysis can be determined to be carried out.

[0053] Further, when the analysis determination unit 37 receives the breast region ratio Rm1 of the subject from the main body side communication unit 35, it compares the input breast region ratio Rm1 with the defined breast region threshold Th1. When the breast region ratio Rm1 is higher than the breast region threshold Th1, it determines to perform the analysis of the GTC region. When the breast region ratio Rm1 is less than or equal to the breast region threshold Th1, it determines that the cancer risk is low and decides not to perform the analysis of the GTC region.

[0054] Similarly, when the analysis determination unit 37 receives the breast region ratio Rm1 calculated by the breast composition information calculation unit 36 from the breast composition information calculation unit 36, it also compares the input breast region ratio Rm1 with the defined breast region threshold Th1. When the breast region ratio Rm1 is higher than the breast region threshold Th1, it determines to perform the analysis of the GTC region. When the breast region ratio Rm1 is less than or equal to the breast region threshold Th1, it determines not to perform the analysis of the GTC region.

[0055] Furthermore, when the analysis determination unit 37 receives the breast mass ratio Rm2 of the subject from the main body side communication unit 35 or from the breast composition information calculation unit 36, it compares the input breast mass ratio Rm2 with the defined breast mass threshold Th2. When the breast mass ratio Rm2 is higher than the breast mass threshold Th2, it determines to perform the analysis of the GTC region. When the breast mass ratio Rm2 is less than or equal to the breast mass threshold Th2, it determines that the cancer risk is low and decides not to perform the analysis of the GTC region.

[0056] When it is determined by the analysis determination unit 37 to perform the analysis of the GTC region, the GTC region analysis unit 38 analyzes the GTC region based on the ultrasonic image of the subject's breast that has been imaged. As shown in FIG. 5, it includes a breast region detection unit 57 connected to the analysis determination unit 37 and the image memory 34, a breast region detection unit 58 connected to the breast region detection unit 57, a GTC region extraction unit 59 connected to the breast region detection unit 58, and a GTC region ratio calculation unit 60 connected to the breast region detection unit 58 and the GTC region extraction unit 59. The GTC region extraction unit 59 and the GTC region ratio calculation unit 60 are connected to the display control unit 32.

[0057] The breast region detection unit 57 detects the breast region of the subject from the ultrasonic image generated by the image generation unit 31. FIG. 6 shows an example of an ultrasonic image of the subject's breast. This ultrasonic image is a tomographic image taken by bringing the tip of the ultrasonic probe 2 into contact with the subject's breast. The skin S of the subject is reflected in the upper end of the ultrasonic image showing the shallowest part, and the pectoralis major muscle T is reflected in the lower part of the ultrasonic image showing the deeper part. The breast region detection unit 57 can recognize the skin S and the pectoralis major muscle T from the ultrasonic image and detect the deep region between the skin S and the pectoralis major muscle T as the breast region BR.

[0058] The mammary gland region detection unit 58 detects the mammary gland region of the subject from the ultrasonic image generated by the image generation unit 31. As shown in FIG. 6, the mammary gland region detection unit 58 recognizes the front boundary line L1 located on the shallower side and the rear boundary line L2 located on the deeper side within the breast region BR detected by the breast region detection unit 57, and can detect the deep region between the front boundary line L1 and the rear boundary line L2 as the mammary gland region M.

[0059] In order to perform the detection of the above-described breast region BR and the detection of the mammary gland region M, image recognition can be performed using at least one of template matching, image analysis techniques using feature quantities such as Adaboost (Adaptive Boosting), SVM (Support Vector Machine), or SIFT (Scale-Invariant Feature Transform), and a determination model learned using machine learning techniques such as deep learning. Note that the determination model is a learned model obtained by learning the breast region BR and the mammary gland region M (segmentation) within the breast region BR in the learning ultrasonic image of the breast.

[0060] The GTC region extraction unit 59 extracts the GTC region from the breast region M of the subject detected by the breast region detection unit 58. The GTC region is composed of mammary ducts, lobules, and surrounding stroma within the breast region M, and the edematous stroma fills the space between the surrounding stroma. Since the edematous stroma is rich in matrix and contains mixed adipocytes, when observing the breast region M with an ultrasonic image, the edematous stroma has a high echo level and appears as high brightness. In contrast, the mammary ducts, lobules, and surrounding stroma that make up the GTC region have a relatively low echo level and lower brightness than the edematous stroma.

[0061] Therefore, the GTC region extraction unit 59 can distinguish the GTC region and the edematous stroma within the breast region M from each other and extract the GTC region, for example, by binarizing the breast region M of the ultrasonic image using a luminance threshold Thb. For example, as in the ultrasonic image shown in FIG. 7, when the GTC region R1 and the edematous region R2 filled with the edematous stroma are mixed within the breast region M, by binarizing the breast region M using an appropriate luminance threshold Thb, a binarized image as shown in FIG. 8 can be obtained.

[0062] In the binarized image of FIG. 8, pixels having a luminance value less than the luminance threshold Thb are represented in black (the hatched part in FIG. 8) to form a black portion P1, and pixels having a luminance value greater than or equal to the luminance threshold Thb are represented in white to form a white portion P2. The black portion P1 corresponds to the GTC region R1, and the white portion P2 corresponds to the edematous region R2. That is, by binarizing the breast region M, the GTC region R1 can be extracted as the black portion P1. The binarized image created by the GTC region extraction unit 59 is displayed on the monitor 33 via the display control unit 32.

[0063] Note that as the luminance threshold Thb, a predetermined constant value can be used. In addition, the GTC region extraction unit 59 may perform edge detection on the GTC region R1 in the ultrasonic image through image analysis, and automatically calculate the luminance threshold Thb based on the change in luminance value at the detected edge portion, that is, the change in luminance values of a plurality of pixels from the inside to the outside of the GTC region R1. In this way, the luminance threshold Thb suitable for the ultrasonic image to be subjected to image analysis can be automatically set, and a binarized image adapted to the ultrasonic image can be obtained.

[0064] Furthermore, a histogram of the luminance of the breast region M detected from the ultrasonic image may be created, and based on the histogram, the binarized image created using the initial value of the luminance threshold Thb, and the ultrasonic image generated by the image generation unit 31, the user may be configured to input and set the luminance threshold Thb from the input device 41.

[0065] In addition, the GTC region extraction unit 59 may also extract the GTC region R1 using a determination model learned by utilizing machine learning techniques such as deep learning. In this case, a learned model obtained by learning the GTC region R1 (segmentation) within the breast region M in the learning ultrasonic image in which the breast was photographed is used as the determination model.

[0066] The GTC region ratio calculation unit 60 calculates the ratio of the GTC region R1 to the breast region M and sends it to the display control unit 32. Specifically, the GTC region ratio calculation unit 60 inputs the breast region M detected by the breast region detection unit 58 and the GTC region R1 extracted by the GTC region extraction unit 59, and calculates the GTC region ratio of the GTC region R1 to the breast region M. In addition, the GTC region ratio calculation unit 60 stores the calculated GTC region ratio in the inspection result memory 39 as an inspection result.

[0067] Although the GTC area ratio cannot be measured by a mammography device, in the ultrasonic diagnostic apparatus according to this embodiment, it can be calculated, for example, based on the number of occupied pixels of the breast area M and the number of occupied pixels of the GTC area R1 in an ultrasonic image. Specifically, the GTC area ratio is represented by the ratio of the sum of the number of occupied pixels of all GTC areas R1 existing in the breast area M to the total number of occupied pixels of the breast area M. The GTC area ratio calculation unit 60 may display the calculated GTC area ratio numerically on the monitor 33, or may also display it on the monitor 33 in the form of a pie chart, bar graph, or the like.

[0068] The inspection result memory 39 is a memory that stores, under the control of the main body control unit 40, the GTC area ratio calculated by the GTC area ratio calculation unit 60 of the GTC area analysis unit 38 as an inspection result. As the inspection result memory 39, similar to the image memory 34, recording media such as a flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, and USB memory can be used. Note that the inspection result memory 39 may be either a memory integrated with the image memory 34 or a memory separate from the image memory 34.

[0069] Also, the ultrasonic image generated by the image generation unit 31 may be represented, for example, as image data in a so-called DICOM (Digital Imaging and Communications in Medicine) format with patient identification information attached, having tags for storing additional information, and the GTC area ratio calculated by the GTC area ratio calculation unit 60 of the GTC area analysis unit 38 may be stored in the tags attached to the ultrasonic image.

[0070] The main body control unit 40 controls each part of the diagnostic apparatus main body 3 and the transmission / reception circuit 22 of the ultrasonic probe 2 based on a pre-stored control program and the like. Also, although not shown, a main body storage unit is connected to the main body control unit 40. The main body storage unit stores a control program and the like. Further, as the main body storage unit, for example, a flash memory, a RAM, an SD card, an SSD, or the like can be used.

[0071] The input device 41 is for the user to perform an input operation, and is composed of, for example, a keyboard, a mouse, a trackball, a touch pad, and a touch sensor disposed on top of the monitor 33 and other devices.

[0072] The processor 42 having the image generation unit 31, the display control unit 32, the main body side communication unit 35, the breast configuration information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the main body control unit 40 is composed of a CPU (Central Processing Unit) and a control program for causing the CPU to perform various processes. However, it may be configured using an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a GPU (Graphics Processing Unit), or other ICs (Integrated Circuits), or may be configured by combining them.

[0073] Also, the image generation unit 31, the display control unit 32, the main body side communication unit 35, the breast configuration information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the main body control unit 40 of the processor 42 can be configured by being partially or entirely integrated into one CPU or the like. The ultrasonic image analysis apparatus 4, which consists of the main body side communication unit 35, the breast composition information calculation unit 36, the analysis determination unit 37, the GTC region analysis unit 38, and the main body control unit 40 within the processor 42, may be configured by an FPGA, DSP, ASIC, GPU, or other IC, independent of the image generation unit 31 and the display control unit 32.

[0074] The mammography apparatus 6 connected to the diagnostic apparatus main body 3 via the network 5 includes an X-ray source 61 and an X-ray detector 62, as shown in FIG. 9. For example, with respect to the breast of a subject in a compressed state by a compression plate (not shown), X-rays are irradiated from the X-ray source 61 while changing the X-ray incident angle, and the X-rays transmitted through the breast are detected by the X-ray detector 62, thereby acquiring a mammography image.

[0075] The mammography apparatus 6 also has a computer (not shown), and the computer can calculate the breast region ratio Rm1, which is the ratio of the breast region to the mammary gland region in the breast region of the subject, or the breast mass ratio Rm2, which is the ratio of the breast mass to the mammary gland region, from the mammography image. Furthermore, the mammography apparatus 6 can calculate the breast category Cm of the subject based on the breast region ratio Rm1 or the breast mass ratio Rm2.

[0076] The server 7 connected to the diagnostic apparatus main body 3 via the network 5 stores various image data generated by the ultrasonic diagnostic apparatus 1 and the mammography apparatus 6. Specifically, the ultrasonic image generated by the diagnostic apparatus main body 3 and the mammography image generated by the mammography apparatus 6 can be stored in the server 7. The server 7 can be used as a server in a so-called PACS (Picture Archiving and Communication System: medical image management system) or a workstation.

[0077] In addition, a computer built into the server 7 can also calculate a breast region ratio Rm1, which is the ratio of the breast gland region to the breast region of the subject in the mammography image, or a breast gland mass ratio Rm2, which is the ratio of the breast gland mass to the breast gland region. Furthermore, the server 7 can also store the breast gland category Cm of the subject obtained by the mammography examination in the mammography apparatus 6.

[0078] Next, with reference to the flowchart shown in FIG. 10, the operation of the ultrasonic diagnostic apparatus 1 according to the embodiment will be described. First, in step S1, breast structure information, which is information regarding the breast structure of the subject obtained by mammography examination, is acquired by the breast structure information acquisition unit F of the diagnostic apparatus main body 3.

[0079] Specifically, as the breast structure information, the breast gland category Cm, the breast region ratio Rm1, or the breast gland mass ratio Rm2 of the subject, which is transmitted from the mammography apparatus 6 or the server 7 to the main body side communication unit 35 via the network 5, is acquired. Further, based on the mammography image transmitted from the mammography apparatus 6 or the server 7 to the main body side communication unit 35 via the network 5, the breast structure information calculation unit 36 calculates the breast region ratio Rm1 of the subject, and the calculated breast region ratio Rm1 may be acquired as the breast structure information. Furthermore, the breast gland category Cm and the breast gland mass ratio Rm2 calculated by the breast structure information calculation unit 36 may be acquired as the breast structure information.

[0080] Next, in step S2, an analysis determination process is performed by the analysis determination unit 37 to determine whether or not to perform an analysis of the GTC region based on the breast structure information acquired in step S1.

[0081] The operation of the analysis determination process in the analysis determination unit 37 is shown in the flowchart of FIG. 11. In step S11, it is determined whether the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is the breast category Cm of the subject. In step S11, if it is determined that the breast category is Cm of the subject, the process proceeds to step S12, and it is determined whether the breast category Cm of the subject belongs to the breast category C4 of "extremely high density" and the breast category C3 of "heterogeneous high density", which are determined in descending order of breast density among the four classified breast categories C1 to C4.

[0082] In step S12, if it is determined that the breast category Cm of the subject is the breast category C4 of "extremely high density" or the breast category C3 of "heterogeneous high density", it is determined that the estimation of the cancer risk by analyzing the GTC region is necessary, and the process proceeds to step S13, and it is determined to perform the analysis of the GTC region. On the other hand, in step S12, if it is determined that the breast category Cm of the subject is neither the breast category C4 of "extremely high density" nor the breast category C3 of "heterogeneous high density", it is determined that the cancer risk is low, and the process proceeds to step S14, and it is determined not to perform the analysis of the GTC region.

[0083] In step S11, if it is determined that the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is not the breast category Cm of the subject, in step S15, it is determined whether the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is the breast region ratio Rm1.

[0084] In step S15, when it is determined that the breast region ratio Rm1 of the subject has been input, the process proceeds to step S16, where the input breast region ratio Rm1 is compared with a defined breast region threshold Th1. If it is determined that the breast region ratio Rm1 is higher than the breast region threshold Th1, it is judged that it is necessary to estimate the cancer risk by analyzing the GTC region, and the process proceeds to step S13, where it is determined to perform the analysis of the GTC region. On the other hand, in step S16, if it is determined that the breast region ratio Rm1 of the subject is equal to or less than the defined breast region threshold Th1, it is judged that the cancer risk is low, and the process proceeds to step S17, where it is determined not to perform the analysis of the GTC region.

[0085] Also, in step S15, when it is determined that the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is not the breast region ratio Rm1, in step S18, it is determined whether the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is the breast mass ratio Rm2.

[0086] In step S18, when it is determined that the breast mass ratio Rm2 of the subject has been input, the process proceeds to step S19, where the input breast mass ratio Rm2 is compared with a defined breast mass threshold Th2. If it is determined that the breast mass ratio Rm2 is higher than the breast mass threshold Th2, it is judged that it is necessary to estimate the cancer risk by analyzing the GTC region, and the process proceeds to step S13, where it is determined to perform the analysis of the GTC region. On the other hand, in step S19, if it is determined that the breast mass ratio Rm2 of the subject is equal to or less than the defined breast mass threshold Th2, it is judged that the cancer risk is low, and the process proceeds to step S20, where it is determined not to perform the analysis of the GTC region.

[0087] Also, in step S18, when it is determined that the breast composition information input from the breast composition information acquisition unit F to the analysis determination unit 37 is not the breast mass ratio Rm2, it is judged that no useful breast composition information for determining whether to perform the analysis of the GTC region has been obtained, and the process proceeds to step S20, where it is determined not to perform the analysis of the GTC region.

[0088] In this way, in step S2 of FIG. 10, the analysis determination unit 37 determines whether to perform the analysis of the GTC region. In step S2, if it is determined to perform the analysis of the GTC region, the process proceeds to step S3, and the GTC region analysis unit 38 performs GTC region analysis processing based on the ultrasonic image of the subject's breast that has been imaged.

[0089] The operation of the GTC region analysis processing in the GTC region analysis unit 38 is shown in the flowchart of FIG. 12. First, in step S31, the subject's breast is photographed using the ultrasonic probe 2, and an ultrasonic image is acquired. At this time, under the control of the main body control unit 40, the transmission and reception of ultrasonic waves are started from a plurality of vibrators of the vibrator array 21 according to the drive signal from the pulsar 23 of the transmission and reception circuit 22 of the ultrasonic probe 2. The ultrasonic echoes from inside the subject's breast are received by a plurality of vibrators of the vibrator array 21, and the received signal, which is an analog signal, is output to the amplifier 24 and amplified, and then AD-converted by the AD conversion unit 25 to obtain received data.

[0090] The received data is subjected to reception focusing processing by the beamformer 26, and the resulting beam signal is sent to the image generation unit 31 of the diagnostic apparatus main body 3. The image generation unit 31 generates an ultrasonic image representing the tomographic image information of the subject's breast. At this time, the signal processing unit 51 of the image generation unit 31 performs attenuation correction and envelope detection processing on the beam signal according to the depth of the reflection position of the ultrasonic wave, and the DSC 52 converts it into an image signal according to the scanning method of a normal television signal. The image processing unit 53 performs various necessary image processing such as tone processing.

[0091] In the subsequent step S32, the ultrasonic image generated by the image generation unit 31 is displayed on the monitor 33 via the display control unit 32 and is also stored in the image memory 34. Note that when acquiring the ultrasonic image, under the control of the main body control unit 40, the transmission intensity of the ultrasonic waves and the depth range of the ultrasonic image displayed on the monitor 33 are adjusted so that the entire breast of the subject, that is, the depth portion between the skin S and the pectoralis major muscle T of the subject shown in FIG. 6 for example, fits within the screen.

[0092] When the ultrasonic image is thus stored in the image memory 34, in step S33, the ultrasonic image is input to the GTC region analysis unit 38, and the breast region BR of the subject is detected from the ultrasonic image by the breast region detection unit 57 shown in FIG. 5. For example, as shown in FIG. 6, the deep region between the skin S of the subject shown in the shallowest part of the ultrasonic image and the pectoralis major muscle T shown in a deeper part is detected as the breast region BR. Furthermore, the ultrasonic image is input to the mammary gland region detection unit 58 via the breast region detection unit 57, and the front boundary line L1 and the rear boundary line L2 are recognized within the breast region BR detected by the breast region detection unit 57 by the mammary gland region detection unit 58, and the deep region between the front boundary line L1 and the rear boundary line L2 is detected as the mammary gland region M.

[0093] Next, in step S34, the GTC region R1 is extracted from the mammary gland region M detected by the mammary gland region detection unit 58 by the GTC region extraction unit 59 of the GTC region analysis unit 38 shown in FIG. 5. At this time, the GTC region extraction unit 59 obtains a binarized image as shown in FIG. 8 by binarizing, for example, the mammary gland region M of the ultrasonic image shown in FIG. 7 using a luminance threshold Thb consisting of a predetermined constant value. In the binarized image of FIG. 8, the black portion P1 corresponds to the extracted GTC region R1, and the white portion P2 corresponds to the edematous region R2 filled with the edematous stroma. The binarized image created by the GTC region extraction unit 59 is displayed on the monitor 33 via the display control unit 32.

[0094] In the subsequent step S35, the GTC region ratio calculation unit 60 of the GTC region analysis unit 38 calculates the GTC region ratio of the GTC region R1 with respect to the breast region M, and it is displayed on the monitor 33 via the display control unit 32. At this time, the GTC region ratio calculation unit 60 can calculate the GTC region ratio based on the ratio of the occupied pixel number of all the GTC regions R1 existing within the breast region M to the total occupied pixel number of the breast region M in the ultrasonic image. The calculated GTC region ratio is displayed on the monitor 33 in the form of a numerical value, a pie chart, a bar graph, etc., and is also stored in the inspection result memory 39 as an inspection result. Also, the calculated GTC region ratio can be stored in a DICOM format tag associated with the ultrasonic image, or can be directly transmitted from the ultrasonic diagnostic apparatus 1 to an external server 7, a diagnostic report system, etc. via a network.

[0095] In this way, the GTC region ratio that cannot be measured by a mammography apparatus is displayed on the monitor 33. By checking the GTC region ratio displayed on the monitor 33, it becomes possible to estimate the cancer risk in the breast region of the subject.

[0096] In addition, when the breast composition information acquisition unit F acquires a plurality of pieces of breast composition information including the breast category Cm, the breast region ratio Rm1, or the breast volume ratio Rm2, the analysis determination unit 37 makes a determination on whether to perform the analysis of the GTC region based on each of the acquired plurality of pieces of breast composition information. When a determination result that the analysis of the GTC region is to be performed is obtained for at least one piece of breast composition information among the plurality of pieces of breast composition information, the execution of the analysis of the GTC region can also be determined. Alternatively, when a determination result that the analysis of the GTC region is to be performed is obtained for all of the plurality of pieces of breast composition information acquired by the breast composition information acquisition unit F, it may be configured to determine the execution of the analysis of the GTC region.

[0097] In the above-described embodiment, the ultrasonic image generated by the image generation unit 31 is a two-dimensional ultrasonic image. However, the image generation unit 31 can also be configured to generate a three-dimensional ultrasonic image of the breast of the subject. After acquiring a plurality of two-dimensional ultrasonic images on a plurality of different tomographic planes by scanning the ultrasonic probe 2 in a planar manner, a three-dimensional ultrasonic image may be generated based on these plurality of two-dimensional ultrasonic images. Alternatively, instead of the ultrasonic probe 2, a three-dimensional probe may be used to generate a three-dimensional ultrasonic image while the three-dimensional probe remains stationary.

[0098] In this case, the breast region detection unit 58 of the GTC region analysis unit 38 detects the breast region M from the three-dimensional ultrasonic image, and the GTC region extraction unit 59 extracts the GTC region R1 from the breast region M of the three-dimensional ultrasonic image. The GTC region ratio calculation unit 60 can calculate the GTC region ratio of the GTC region R1 to the breast region M based on the volume of the breast region M detected by the breast region detection unit 58 and the volume of the GTC region R1 extracted by the GTC region extraction unit 59. The calculated GTC region ratio is displayed on the monitor 33 and also stored in the examination result memory 39. In this way, by calculating the GTC region ratio based on the three-dimensional ultrasonic image, the accuracy of cancer risk estimation in the breast region M of the subject is improved, and a more reliable diagnosis can be performed.

[0099] In the above-described embodiment, the breast structure information calculation unit 36 of the breast structure information acquisition unit F calculates the breast region ratio Rm1, which is the ratio of the breast region to the breast region of the subject, as the breast structure information from the mammography image. However, the present invention is not limited to this. The breast structure information calculation unit 36 can also be configured to calculate the breast mass ratio Rm2, which is the ratio of the breast mass to the breast region of the subject, and the breast category Cm as the breast structure information from the mammography image.

[0100] In the above-described embodiment, the ultrasonic image analysis device 4 is arranged inside the ultrasonic diagnostic device 1, but it is not limited to this. The ultrasonic image analysis device 4 can also be separated from the ultrasonic diagnostic device 1 and used. For example, the ultrasonic image analysis device 4 is arranged inside a server 7 connected to a general-purpose ultrasonic imaging device via a network 5 shown in FIG. 1, and an ultrasonic image of a subject's breast taken by the general-purpose ultrasonic imaging device is transmitted to the server 7, and the ultrasonic image analysis device 4 may calculate the GTC region ratio. Further, for example, as described in Japanese Patent Application Laid-Open No. 2008-161283, Japanese Patent Application Laid-Open No. 2019-69319, etc., the ultrasonic image analysis device 4 can be built into a mammography device having an ultrasonic measurement function, and the GTC region ratio can be calculated inside the mammography device.

[0101] The connection method between the ultrasonic probe 2 and the diagnostic device main body 3 in the above-described embodiment is not particularly limited, and may be a wired connection or a wireless connection. In the above-described embodiment, the ultrasonic probe 2 has the transmission / reception circuit 22, but it can also be configured such that the diagnostic device main body 3 has the transmission / reception circuit 22. Further, although the diagnostic device main body 3 has the image generation unit 31, the ultrasonic probe 2 may have the image generation unit 31. Furthermore, among the signal processing unit 51, DSC 52, and image processing unit 53 that constitute the image generation unit 31 shown in FIG. 3, only the signal processing unit 51 may be provided in the ultrasonic probe 2, and the diagnostic device main body 3 may be configured to have the DSC 52 and the image processing unit 53. In addition, as the diagnostic device main body 3 in the embodiment, a portable or hand-held compact diagnostic device main body can also be used, or a stationary diagnostic device main body can also be used.

Explanation of Reference Numerals

[0102] 1 Ultrasonic diagnostic apparatus, 2 ultrasonic probe, 3 diagnostic apparatus main body, 4 ultrasonic image analyzer, 5 network, 6 mammography apparatus, 7 server, 21 transducer array, 22 transmission / reception circuit, 23 pulsar, 24 amplifier section, 25 AD conversion section, 26 beam former, 31 image generation section, 32 display control section, 33 monitor, 34 image memory, 35 main body side communication section, 36 breast constitution information calculation section, 37 analysis determination section, 38 GTC region analysis section, 39 examination result memory, 40 main body control section, 41 input device, 42 processor, 51 signal processing section, 52 DSC, 53 image processing section, 54, 57 breast region detection section, 55, 58 mammary gland region detection section, 56 mammary gland region ratio calculation section, 59 GTC region extraction section, 60 GTC region ratio calculation section, 61 X-ray source, 62 X-ray detector, S skin, BR breast region, M mammary gland region, L1 front boundary line, L2 rear boundary line, T pectoralis major muscle, R1 GTC region, R2 edematous region, P1 black part, P2 white part.

Claims

1. A breast composition information acquisition unit that acquires information regarding the breast composition of a subject obtained by mammography, An analysis determination unit that determines whether to perform an analysis of the glandular tissue composition region within the mammary gland region based on the information regarding the breast composition acquired by the breast composition information acquisition unit, A glandular tissue composition region analysis unit that analyzes the glandular tissue composition region based on an ultrasonic image in which the breast of the subject is imaged when it is determined by the analysis determination unit that the analysis is to be performed, Comprising, The mammary gland region includes a milk duct, a lobule, a surrounding stroma existing along a structure extending from the lobule to the milk duct, and an edematous stroma filling between the surrounding stroma, The surrounding stroma contains more collagen fibers than the edematous stroma, The glandular tissue composition region includes the milk duct, the lobule, and the surrounding stroma within the mammary gland region and does not include the edematous stroma, The glandular tissue composition region analysis unit is an ultrasonic image analysis apparatus that detects the mammary gland region from the ultrasonic image, extracts the glandular tissue composition region by binarizing the detected mammary gland region using a luminance threshold value, and calculates a ratio of the glandular tissue composition region to the mammary gland region.

2. The ultrasonic image analysis apparatus according to claim 1, wherein the breast composition information acquisition unit acquires, as the information regarding the breast composition, a breast category corresponding to the subject among a plurality of types of breast categories classified according to breast density.

3. The ultrasonic image analysis apparatus according to claim 2, wherein the analysis determination unit determines to perform the analysis of the glandular tissue composition region when the breast category corresponding to the subject belongs to at least one breast category determined in descending order of the breast density among the plurality of types of breast categories classified.

4. The ultrasonic image analysis apparatus according to claim 1, wherein the breast composition information acquisition unit acquires, as the information regarding the breast composition, a ratio of the mammary gland region to the breast region of the subject.

5. The ultrasonic image analysis apparatus according to claim 4, wherein the breast composition information acquisition unit includes a breast composition information calculation unit that calculates a ratio of the mammary gland region to the breast region of the subject from a mammography image.

6. The ultrasonic image analysis apparatus according to claim 4 or 5, wherein the analysis determination unit determines to perform the analysis of the glandular tissue composition region when the ratio of the mammary gland region to the breast region is higher than a determined mammary gland region threshold value.

7. The ultrasonic image analysis apparatus according to claim 1, wherein the breast composition information acquisition unit acquires, as information regarding the breast composition, a ratio of the amount of mammary gland in the mammary gland region of the subject.

8. The ultrasonic image analysis apparatus according to claim 7, wherein the analysis determination unit determines to perform analysis of the glandular tissue composition region when the ratio of the amount of mammary gland to the mammary gland region is higher than a determined mammary gland amount threshold value.

9. The ultrasonic image analysis apparatus according to any one of claims 1 to 8, wherein the glandular tissue composition region analysis unit calculates a ratio of the glandular tissue composition region to the mammary gland region.

10. The glandular tissue composition region analysis unit includes a mammary gland region detection unit that detects the mammary gland region from the ultrasonic image, a glandular tissue composition region extraction unit that extracts the glandular tissue composition region within the mammary gland region detected by the mammary gland region detection unit, and a glandular tissue composition region ratio calculation unit that calculates a ratio of the glandular tissue composition region to the mammary gland region. The ultrasonic image analysis apparatus according to claim 9.

11. The ultrasonic image analysis apparatus according to claim 10, wherein the mammary gland region detection unit detects the mammary gland region by performing image recognition on the ultrasonic image.

12. The apparatus includes a breast region detection unit that detects a breast region located between the skin and the pectoralis major muscle from the ultrasonic image, and the mammary gland region detection unit recognizes a front boundary line and a rear boundary line within the breast region detected by the breast region detection unit, and detects a region between the front boundary line and the rear boundary line as the mammary gland region. The ultrasonic image analysis apparatus according to claim 11.

13. The ultrasonic image analysis apparatus according to claim 10, wherein the mammary gland region detection unit detects the mammary gland region from the ultrasonic image using deep learning.

14. The glandular tissue composition region ratio calculation unit according to any one of claims 10 to 13 calculates a ratio of the glandular tissue composition region to the mammary gland region based on the number of occupied pixels of the mammary gland region and the number of occupied pixels of the glandular tissue composition region in the ultrasonic image.

15. The ultrasonic image is a three-dimensional ultrasonic image, and the glandular tissue composition region ratio calculation unit according to any one of claims 10 to 14 calculates a ratio of the glandular tissue composition region to the mammary gland region based on the volume of the mammary gland region detected by the mammary gland region detection unit and the volume of the glandular tissue composition region extracted by the glandular tissue composition region extraction unit.

16. A monitor for displaying the ultrasonic image, The ultrasonic image analysis apparatus according to any one of claims 1 to 15 and comprising The glandular tissue composition region analysis unit is an ultrasonic diagnostic apparatus that displays the analysis result of the glandular tissue composition region on the monitor.

17. The ultrasonic diagnostic apparatus according to claim 16, wherein the glandular tissue composition region analysis unit stores the analysis result of the glandular tissue composition region in a tag attached to the ultrasonic image.

18. The ultrasonic diagnostic apparatus according to claim 16 or 17, comprising an ultrasonic probe and an image generation unit that generates the ultrasonic image obtained by transmitting and receiving an ultrasonic beam to and from the subject using the ultrasonic probe.

19. Obtain information regarding the breast composition of the subject obtained by mammography, Determine whether to perform an analysis of the glandular tissue composition region within the mammary gland region based on the obtained information regarding the breast composition, When it is determined to perform the analysis, analyze the glandular tissue composition region based on the ultrasonic image of the breast of the subject that has been imaged, The mammary gland region includes a lactiferous duct, a lobule, a surrounding stroma existing along a structure from the lobule to the lactiferous duct, and an edematous stroma filling between the surrounding stroma, The surrounding stroma contains more collagen fibers than the edematous stroma, The glandular tissue composition region includes the lactiferous duct, the lobule, and the surrounding stroma within the mammary gland region and does not include the edematous stroma, The analysis of the glandular tissue composition region is a control method of an ultrasonic image analysis apparatus that detects the mammary gland region from the ultrasonic image, extracts the glandular tissue composition region by binarizing the detected mammary gland region using a luminance threshold value, and calculates the ratio of the glandular tissue composition region to the mammary gland region.

Images