Classifications

• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/08—Clinical applications
  • A61B8/0825—Clinical applications for diagnosis of the breast, e.g. mammography
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
  • A61B8/461—Displaying means of special interest
  • A61B8/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
  • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
  • G06T7/0002—Inspection of images, e.g. flaw detection
  • G06T7/0012—Biomedical image inspection
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
  • G06T7/60—Analysis of geometric attributes
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/08—Clinical applications
  • A61B8/0833—Clinical applications involving detecting or locating foreign bodies or organic structures
  • A61B8/085—Clinical applications involving detecting or locating foreign bodies or organic structures for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
  • A61B8/54—Control of the diagnostic device
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/10—Image acquisition modality
  • G06T2207/10132—Ultrasound image
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/30—Subject of image; Context of image processing
  • G06T2207/30004—Biomedical image processing
  • G06T2207/30068—Mammography; Breast
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/30—Subject of image; Context of image processing
  • G06T2207/30004—Biomedical image processing
  • G06T2207/30096—Tumor; Lesion

Definitions

• the present invention relates to an ultrasound diagnostic device used to examine the breasts of a subject, and a method for controlling the ultrasound diagnostic device.
• ultrasound diagnostic devices that capture ultrasound images of subjects have been put to practical use for some time.
• ultrasound diagnostic devices are equipped with an ultrasound probe that contains an array of transducers and a device main body that is connected to the ultrasound probe.
• An ultrasound beam is transmitted from the ultrasound probe to the subject, and ultrasound echoes from the subject are received by the ultrasound probe.
• An ultrasound image is generated by electrically processing the received signals.
• the composition of breast fat and glandular tissue varies from person to person, but the anatomical structure of the breast is the same: in the glandular tissue, the main duct branches into many extralobular ducts, which connect to many lobules.
• the stroma is present around the lobules, and the stroma and other tissues together make up the glandular tissue. It is known that there are two types of stroma around the lobules: surrounding stroma and edematous stroma.
• the surrounding stroma is present along the structure from the lobule to the milk duct, and contains a lot of collagen fibers.
• the edematous stroma fills the gaps between the surrounding stroma, and is rich in matrix, with collagen fibers and fat mixed in, and less collagen fibers than the surrounding stroma.
• Non-Patent Document 1 reports that even if the glandular area is almost the same, cancer is more likely to occur when the proportion of GTC (Glandular Tissue Component) areas, which include the milk ducts, lobules, and surrounding stroma, in the glandular area is high.
• GTC Global Tissue Component
• the proportion of the GTC area in the glandular area can be a risk factor. This means that the risk is high in patients whose lobules do not degenerate.
• Patent Document 1 an ultrasound diagnostic device is disclosed that extracts a region suspected of being a lesion within a mammary gland region, which is a region suspected of being a lesion.
• Patent Document 1 the ultrasound diagnostic device in Patent Document 1 is intended to detect areas suspected of having lesions in the mammary gland region, and is not interested in evaluating GTC regions. This poses the problem that it is not possible to consider in detail the risk of cancer in the mammary gland region.
• GTC regions and suspected lesion regions are depicted in ultrasound images as low-echo, i.e., low-brightness regions
• performing a GTC assessment based on an ultrasound image of a frame that includes a suspected lesion region may not produce accurate assessment results, and doctors and other users may not be able to accurately assess the risk of cancer in the mammary gland region.
• the present invention has been made to solve these conventional problems, and aims to provide an ultrasound diagnostic device that allows the user to accurately assess the risk of cancer in the subject's breast area, even when a suspected lesion area is present.
• the target frame generation unit generates a group of evaluation target frames from among a plurality of ultrasound images, ultrasound images of frames prior to a frame that is a predetermined number of frames before a frame in which a suspected lesion area is detected by the lesion detection unit, and ultrasound images of frames from a frame that is a predetermined number of frames after a frame in which a suspected lesion area is detected by the lesion detection unit.
• the ultrasound diagnostic device [9] The ultrasound diagnostic device according to [8], wherein the display control unit highlights the suspected lesion area on the monitor. [10] The ultrasound diagnostic device according to any one of [5] to [7], wherein the display control unit displays on the monitor ultrasound images of the respective frames for which the lesion detection unit has performed processing for detecting a suspected lesion region. [11] The ultrasound diagnostic device according to [10], wherein the display control unit displays a dialogue on the monitor to prompt the user to confirm whether or not to correct the detection result of the suspected lesion region by the lesion detection unit.
• An ultrasound diagnostic device according to any one of [5] to [11], wherein the evaluation unit classifies the mammary gland region of the ultrasound image of each frame of the frame group to be evaluated into a hypoechoic region and a hyperechoic region based on a determined brightness threshold, and displays on the monitor the glandular tissue composition ratio represented by the ratio of the number of pixels occupied by the hypoechoic region to the number of pixels occupied by the hyperechoic region as the result of the glandular tissue composition evaluation.
• the ultrasound diagnostic device according to any one of [1] to [14], wherein the lesion detection unit detects suspected lesion areas using a trained model that has been machine-learned based on multiple training data including ultrasound images of mammary gland areas each including a suspected lesion area.
• the lesion detection unit detects a suspected lesion region by performing image analysis on the ultrasound image.
• an ultrasound diagnostic device includes an image acquisition unit that continuously acquires multiple frames of ultrasound images of the subject's mammary gland region, a lesion detection unit that detects suspected lesion areas in the mammary gland region for each of the multiple frames of ultrasound images, a target frame generation unit that generates a group of frames to be evaluated using ultrasound images of frames other than those in which the suspected lesion areas have been detected by the lesion detection unit among the multiple frames of ultrasound images, and an evaluation unit that performs glandular tissue composition evaluation on the ultrasound images of each frame of the group of frames to be evaluated. This allows the user to accurately assess the risk of cancer in the subject's mammary gland region even when a suspected lesion area is present.
• FIG. 1 is a block diagram showing a configuration of an ultrasound diagnostic apparatus according to a first embodiment of the present invention
• 2 is a block diagram showing an internal configuration of a transmission/reception circuit according to the first embodiment
• 4 is a block diagram showing an internal configuration of an image generating unit in the first embodiment.
• FIG. 1 is a diagram showing an ultrasound image of a mammary gland region of a subject.
• FIG. 2 is a diagram showing an ultrasound image of a mammary gland region in which a GTC region is photographed.
• FIG. 10 is a diagram illustrating an example of an evaluation target frame group.
• FIG. 1 is a diagram showing a configuration of an ultrasound diagnostic apparatus according to a first embodiment of the present invention
• 2 is a block diagram showing an internal configuration of a transmission/reception circuit according to the first embodiment
• 4 is a block
• FIG. 13 is a diagram showing an example display of a group of evaluation target frames selected by a user.
• FIG. 13 is a diagram showing an example of how an exclusion frame confirmation button is displayed.
• FIG. 13 is a diagram showing a display example of an ultrasound image in which a suspected lesion region is detected.
• FIG. 11 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to a second embodiment of the present invention. 11 is a flowchart showing the operation of the second embodiment.
• FIG. 11 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to a third embodiment of the present invention. 13 is a flowchart showing the operation of the third embodiment.
• the ultrasonic diagnostic apparatus includes an ultrasonic probe 1 and an apparatus main body 2.
• the ultrasonic probe 1 and the apparatus main body 2 are wired to each other via a cable (not shown).
• the ultrasound probe 1 has a transducer array 11 and a transmission/reception circuit 12 connected to the transducer array 11.
• the device main body 2 has an image generation unit 21 connected to the transmission/reception circuit 12 of the ultrasound probe 1, to which a display control unit 22 and a monitor 23 are sequentially connected, and to which an image memory 24 is connected.
• a mammary gland region extraction unit 25 is also connected to the image memory 24.
• a lesion detection unit 26 is also connected to the mammary gland region extraction unit 25.
• a target frame generation unit 27 is also connected to the mammary gland region extraction unit 25 and the lesion detection unit 26.
• An evaluation unit 29 is connected to the target frame generation unit 27.
• a display control unit 22 and an evaluation result memory 30 are also connected to the evaluation unit 29.
• a main body control unit 31 is connected to the image generation unit 21, the display control unit 22, the image memory 24, the mammary gland region extraction unit 25, the target frame generation unit 27, the evaluation unit 29, and the evaluation result memory 30.
• An input device 32 is connected to the main body control unit 31.
• the transmission/reception circuit 12 and the image generation unit 21 form an image acquisition unit 33.
• the image generation unit 21, the display control unit 22, the mammary gland region extraction unit 25, the lesion detection unit 26, the target frame generation unit 27, the evaluation unit 29, and the main body control unit 31 form a processor 34 for the device main body 2.
• the transducer array 11 of the ultrasound probe 1 has multiple ultrasound transducers arranged one-dimensionally or two-dimensionally. Each of these transducers transmits ultrasound waves according to a drive signal supplied from the transmission/reception circuit 12, and also receives reflected waves from the subject and outputs an analog reception signal.
• Each transducer is constructed by forming electrodes on both ends of a piezoelectric body made of, for example, a piezoelectric ceramic such as PZT (Lead Zirconate Titanate), a polymer piezoelectric element such as PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal such as PMN-PT (Lead Magnesium Niobate-Lead Titanate).
• the transmission/reception circuit 12 transmits ultrasonic waves from the transducer array 11 and generates sound ray signals based on the reception signals acquired by the transducer array 11.
• the transmission/reception circuit 12 has a pulser 13 connected to the transducer array 11, an amplifier unit 14, an AD (Analog Digital) conversion unit 15, and a beamformer 16 connected in series to the transducer array 11.
• the transmitted ultrasonic beam is reflected by an object, such as a part of the subject, and an ultrasonic echo propagates toward the transducer array 11 of the ultrasonic probe 1.
• the ultrasonic echo propagating toward the transducer array 11 in this manner is received by each of the transducers that make up the transducer array 11.
• each of the transducers that make up the transducer array 11 expands and contracts upon receiving the propagating ultrasonic echo, generating a received signal, which is an electrical signal, and outputs these received signals to the amplifier unit 14.
• the amplifier 14 amplifies the signals input from each transducer that constitutes the transducer array 11 and transmits the amplified signals to the AD converter 15.
• the AD converter 15 converts the signals transmitted from the amplifier 14 into digital reception data and transmits these reception data to the beamformer 16.
• the beamformer 16 performs so-called reception focusing processing by adding each reception data converted by the AD converter 15 with a respective delay according to the sound speed or sound speed distribution set based on the reception delay pattern selected in response to a control signal from the main body control unit 31. This reception focusing processing causes the reception data converted by the AD converter 15 to be phased and added, and a sound ray signal with a narrowed focus of the ultrasonic echo is obtained.
• the image generating section 21 of the apparatus main body 2 has a configuration in which a signal processing section 41, a DSC (Digital Scan Converter) 42, and an image processing section 43 are connected in series.
• the signal processing unit 41 performs correction for attenuation due to distance on the sound ray signals sent from the transmission/reception circuit 12 of the ultrasonic probe 1 in accordance with the depth of the reflection position of the ultrasonic waves, and then performs envelope detection processing to generate an ultrasonic image signal (B-mode image signal) which is tomographic image information on the tissue in the subject.
• B-mode image signal ultrasonic image signal
• the DSC 42 converts (raster converts) the ultrasonic image signal generated by the signal processor 41 into an image signal conforming to a scanning method for a normal television signal.
• the image processing unit 43 performs various necessary image processing such as gradation processing on the ultrasound image signal input from the DSC 42, and then outputs a signal representing the ultrasound image to the display control unit 22 and the image memory 24.
• the signal representing the ultrasound image generated by the image generation unit 21 in this manner will be simply called an ultrasound image.
• the image generation unit 21 can also output the ultrasound image signal before processing by the DSC 42 or the ultrasound image signal immediately after processing by the DSC 42 to the image memory 24. In this case, the image generation unit 21 can generate an ultrasound image by reading these signals from the image memory 24 and processing them by the DSC 42 or the image processing unit 43.
• the image memory 24 is a memory that stores ultrasound images generated by the image generation unit 21 under the control of the main body control unit 31.
• the image memory 24 can hold multiple frames of ultrasound images generated by the image generation unit 21 in response to a diagnosis of the mammary gland region of the subject's breast.
• the image memory 24 may be, for example, a flash memory, HDD (Hard Disc Drive), SSD (Solid State Drive), FD (Flexible Disc), MO disk (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), or other recording media.
• HDD Hard Disc Drive
• SSD Solid State Drive
• FD Fexible Disc
• MO disk Magnetic-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
• the mammary gland region extraction unit 25 detects the subject's breast region from each of the multiple frames of ultrasound images read from the image memory 24, and extracts the mammary gland region from the detected breast region.
• FIG 4 shows an example of an ultrasound image U of a subject's breast.
• This ultrasound image U is a cross-sectional image taken by contacting the tip of the ultrasound probe 1 with the subject's breast, with the subject's skin S appearing at the top of the ultrasound image U, which shows the shallowest part, and the pectoralis major muscle T appearing at the bottom of the ultrasound image U, which shows the deeper part.
• the mammary gland region extraction unit 25 can recognize the skin S and pectoralis major muscle T from the ultrasound image U, and detect the deep region between the skin S and pectoralis major muscle T as the breast region BR.
• the mammary gland region extraction unit 25 recognizes an anterior boundary line L1 located on the shallower side and a posterior boundary line L2 located on the deeper side within the detected breast region BR, and can extract the deep region between the anterior boundary line L1 and the posterior boundary line L2 as the mammary gland region M.
• the mammary gland region extraction unit 25 can perform image recognition using at least one of template matching, image analysis techniques using features such as Adaboost (Adaptive Boosting), SVM (Support Vector Machine) or SIFT (Scale-Invariant Feature Transform), and a judgment model trained using machine learning techniques such as deep learning.
• the judgment model is a trained model that has learned the breast region BR and the mammary gland region M (segmentation) within the breast region BR in a training ultrasound image of a breast.
• Lesion detection unit 26 detects suspected lesion area A based on ultrasound image U in which the subject's mammary gland area M has been captured.
• suspected lesion area A refers to an area in the mammary gland area M in which a lesion, including a so-called mass, is suspected.
• Lesion detection unit 26 can detect suspected lesion area A using at least one of template matching, image analysis technology using feature values such as Adaboost, SVM, or SIFT, and a judgment model trained using machine learning technology such as deep learning.
• the judgment model used here is a trained model that has learned a large number of lesion areas in ultrasound image U in which the mammary gland area M has been captured.
• the lesion detection unit 26 can assign a flag to the ultrasound image U of a frame in which a suspected lesion area A is detected to exclude it from the candidates for the group of frames to be evaluated, which will be described later.
• the target frame generating unit 27 generates an evaluation target frame group G using ultrasound images U of frames other than those in which a suspected lesion area A is detected by the lesion detection unit 26, among the multiple frames of ultrasound images U generated by the image generating unit 21.
• the target frame generating unit 27 can, for example, exclude ultrasound images U of frames to which a flag is assigned by the lesion detection unit 26 from among the multiple frames of ultrasound images U from among the multiple frames of ultrasound images U, and generate an evaluation target frame group G using ultrasound images U of frames to which no flag is assigned.
• FIG. 6 the target frame generating unit 27 generates an evaluation target frame group G using ultrasound images U of frames other than those in which a suspected lesion area A is detected by the lesion detection unit 26, among the multiple frames of ultrasound images U generated by the image generating unit 21.
• the target frame generating unit 27 can, for example, exclude ultrasound images U of frames to which a flag is assigned by the lesion detection unit 26 from among the multiple frames of ultrasound images U from among the multiple frames of ultrasound images U, and generate an evaluation
• N and K are natural numbers that satisfy N ⁇ K.
• the evaluation unit 29 performs GTC (Glandular Tissue Component) evaluation on the ultrasound images U of each frame of the evaluation target frame group G generated by the target frame generation unit 27.
• GTC Global Tissue Component
• the evaluation unit 29 When performing GTC evaluation, the evaluation unit 29 first extracts a GTC region R1 from the mammary gland region M extracted by the mammary gland region extraction unit 25, as shown in FIG. 5.
• the GTC region R1 is composed of the milk ducts, lobules, and surrounding stroma within the mammary gland region M, with edematous stroma R2 filling in the spaces between the surrounding stroma. Because the edematous stroma R2 is rich in matrix and contains adipocytes, when the mammary gland region M is observed using an ultrasound image U, the edematous stroma R2 appears with a relatively high echo level (hyperechoic) and high brightness. In contrast, the milk ducts, lobules, and surrounding stroma that make up the GTC region R1 have a relatively low echo level (hypoechoic) and are lower in brightness than the edematous stroma R2.
• the evaluation unit 29 can, for example, binarize the mammary gland region M of the ultrasound image U using a brightness threshold value Thb to classify it into a hypoechoic region and a hyperechoic region, and can distinguish between the GTC region R1 and the edematous stroma R2 within the mammary gland region M, and extract the GTC region R1.
• the evaluation unit 29 may also perform edge detection on the GTC region R1 in the ultrasound image U by image analysis, and automatically calculate the brightness threshold value Thb based on the change in brightness value in the detected edge portion, i.e., the change in brightness value of a plurality of pixels from the inside to the outside of the GTC region R1. In this way, it is possible to automatically set the brightness threshold value Thb suitable for the ultrasound image U to be subjected to image analysis, and it is possible to obtain a binarized image suitable for the ultrasound image U.
• the ultrasound diagnostic device can be configured to create a luminance histogram of the mammary gland region M detected from the ultrasound image U, and allow the user to input and set the luminance threshold value Thb from the input device 32 based on the histogram, a binarized image created using the initial value of the luminance threshold value Thb, and the ultrasound image U generated by the image generation unit 21.
• the evaluation unit 29 can also extract the GTC region R1 using a judgment model trained using machine learning techniques such as deep learning.
• a judgment model trained using machine learning techniques such as deep learning.
• a trained model that has trained the GTC region R1 (segmentation) within the mammary gland region M in a training ultrasound image of a breast is used as the judgment model.
• the evaluation unit 29 calculates the proportion of the GTC region R1 in the mammary gland region M, and performs GTC evaluation based on the calculated proportion of the GTC region R1.
• the evaluation unit 29 can calculate the proportion of the GTC region R1, for example, by the ratio of the sum of the number of pixels occupied by all of the hypoechoic regions in the mammary gland region M in the ultrasound image U to the number of pixels occupied by the hyperechoic regions in the mammary gland region M.
• the evaluation unit 29 can use, for example, any of the average, median, and maximum value of the percentage of a predetermined number of GTC regions R1 calculated in this manner from the ultrasound image U of a predetermined number of frames as the evaluation result of the final GTC evaluation.
• the evaluation unit 29 can also use any of the average, median, and maximum value of the remaining GTC regions R1 after removing outliers from the percentage of the predetermined number of GTC regions R1 as the evaluation result of the final GTC evaluation.
• an outlier is a value among multiple values whose difference between those values is greater than a predetermined difference threshold.
• the number of frames of the ultrasound image U used for GTC evaluation can be determined in advance, for example, by a user's input operation via the input device 32.
• the evaluation unit 29 can, for example, determine the category of the GTC region R1 based on the proportion of the GTC region R1 within the mammary gland region M, and use the category as the evaluation result of the GTC evaluation.
• the GTC region R1 category represents the degree of lobular shrinkage and can be used as a criterion for determining breast cancer risk.
• the evaluation unit 29 can also determine the category of the GTC region R1 using a trained model that is machine-learned based on multiple training data including, for example, an ultrasound image U in which a mammary gland region M is captured as shown in FIG. 4 or FIG. 5, and the category of the GTC region R1 in the ultrasound image U.
• the correspondence between the ultrasound image U in the training data and the category of the GTC region R1 can be performed by an expert such as a skilled doctor.
• the evaluation unit 29 can output, as the category of the GTC region R1, one of a number of predetermined categories, for example, one of two categories, Low and High, as the evaluation result. Low indicates that the lobule degeneration is less advanced than High.
• the evaluation unit 29 can also output, as the category of the GTC region R1, one of four categories, for example, Minimal, Mild, Moderate, and Marked. Mild indicates that the lobule degeneration is less advanced than Minimal, Moderate indicates that the lobule degeneration is less advanced than Mild, and Marked indicates that the lobule degeneration is less advanced than Moderate.
• the evaluation unit 29 determines the category of the GTC region R1 based on any one of the average, median, and maximum of the proportions of a predetermined number of GTC regions R1 obtained from an ultrasound image U of a predetermined number of frames, and the category determined in this manner can be used as the final evaluation result.
• the evaluation unit 29 can use the mode of the predetermined number of categories as the final evaluation result.
• both the GTC region R1 and the suspected lesion region A are depicted as hypoechoic regions in the ultrasound image U. Therefore, for example, when attempting to perform a GTC evaluation using an ultrasound image U of a frame in which the suspected lesion region A is detected, the GTC evaluation may be performed while the suspected lesion region A is regarded as the GTC region R1, and an accurate evaluation result may not be obtained.
• the evaluation unit 29 performs a GTC evaluation based on the evaluation target frame group G generated by the target frame generation unit 27 and in which the suspected lesion region A is not detected, thereby improving the accuracy of the evaluation.
• the display control unit 22 Under the control of the main body control unit 31, the display control unit 22 performs a predetermined process on the ultrasound image U sent from the image generation unit 21, and displays the ultrasound image U on the monitor 23.
• the display control unit 22 can also display the evaluation result ER of the GTC evaluation output by the evaluation unit 29 together with the representative ultrasound image U used in the GTC evaluation, as shown in FIG. 7, for example.
• the ratio of the GTC region R1 in the mammary gland region M is displayed as a numerical value as the evaluation result ER of the GTC evaluation.
• the representative ultrasound image U used in the GTC evaluation for example, the latest ultrasound image U, the oldest ultrasound image U, or an ultrasound image U specified by the user via the input device 32, among the ultrasound images U of a predetermined number of frames used in the GTC evaluation, can be displayed.
• the user can accurately assess the risk of cancer in the breast area M of the subject, even if a suspected lesion area A is present in the breast area M.
• the monitor 23 displays the ultrasound image U etc. under the control of the display control unit 22, and has a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).
• a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).
• the evaluation result memory 30 stores the evaluation result ER of the GTC evaluation for each partial region by the evaluation unit 29. For example, after examining the subject, the user can read out the evaluation result ER via the input device 32 and consider the risk of cancer in the subject's breast based on the evaluation result ER.
• a recording medium such as a flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, USB memory, etc. can be used.
• the main body control unit 31 controls each part of the device main body 2 and the transmission/reception circuit 12 of the ultrasonic probe 1 based on a control program stored in advance.
• the input device 32 is used by the user to perform input operations, and is composed of devices such as a keyboard, a mouse, a trackball, a touch pad, and a touch sensor disposed over the monitor 23, for example.
• the processor 34 having the image generation unit 21, display control unit 22, mammary gland area extraction unit 25, lesion detection unit 26, target frame generation unit 27, evaluation unit 29 and main body control unit 31 is composed of a CPU (Central Processing Unit) and a control program for causing the CPU to perform various processes, but may also be composed of 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 a combination of these.
• CPU Central Processing Unit
• FPGA Field Programmable Gate Array
• DSP Digital Signal Processor
• ASIC Application Specific Integrated Circuit
• GPU Graphics Processing Unit
• other ICs Integrated Circuits
• image generating unit 21, display control unit 22, mammary gland region extracting unit 25, lesion detecting unit 26, target frame generating unit 27, evaluation unit 29 and main body control unit 31 of the processor 34 can be partially or entirely integrated into a single CPU or the like.
• step S2 the ultrasound image U generated by the image generating unit 21 is displayed on the monitor 23 via the display control unit 22, and is also stored in the image memory 24.
• the transmission intensity of the ultrasound and the depth range of the ultrasound image U displayed on the monitor 23 are adjusted under the control of the main body control unit 31 so that the entire subject's breast, i.e., for example, the subject's breast area BR shown in Figure 4 or Figure 5, fits within the screen.
• the mammary gland region extraction unit 25 detects the breast region BR of the subject from the ultrasound image U acquired in step S1, and extracts the mammary gland region M from the detected breast region BR.
• the mammary gland region extraction unit 25 can perform image recognition using at least one of template matching, image analysis technology using feature amounts such as Adaboost, SVM, or SIFT, and a judgment model trained using machine learning technology such as deep learning.
• step S4 the lesion detection unit 26 performs processing to detect a suspected lesion area A in the mammary gland area M extracted in step S3 based on the ultrasound image U acquired in step S1, and the target frame generation unit 27 determines whether or not the suspected lesion area A has been detected by the lesion detection unit 26.
• Lesion detection unit 26 performs processing to detect suspected lesion area A using at least one of, for example, template matching, image analysis technology using features such as Adaboost, SVM, or SIFT, and a judgment model trained using machine learning technology such as deep learning. In addition, lesion detection unit 26 assigns a flag to ultrasound image U of a frame in which suspected lesion area A is detected. Target frame generation unit 27 can determine that suspected lesion area A has been detected if a flag has been assigned to ultrasound image U, and can determine that suspected lesion area A has not been detected if a flag has not been assigned to ultrasound image U.
• step S5 If the target frame generator 27 determines that a suspected lesion area A has been detected, the process proceeds to step S5.
• step S5 the target frame generation unit 27 excludes the ultrasound image U in which the suspected lesion area A was detected in step S4 from the candidates for the evaluation target frame group G.
• step S4 If it is determined in step S4 that no suspected lesion area A has been detected, the target frame generation unit 27 leaves the ultrasound image U acquired in step S1 as a candidate for the evaluation target frame group G.
• step S6 the main body control unit 31 determines whether or not to end the capture of the ultrasound image U. For example, the main body control unit 31 can determine to end the capture of the ultrasound image U when an instruction to end the capture is input by the user via the input device 32, and can determine to continue the capture of the ultrasound image U when no instruction to end the capture is specifically input by the user via the input device 32.
• step S6 If it is determined in step S6 that capturing ultrasound images U should continue, the process returns to step S1, where a new ultrasound image U is acquired, and then steps S2 to S6 are performed in sequence. In this manner, as long as it is determined in step S6 that capturing ultrasound images U should continue, the process of steps S1 to S6 is repeated, and multiple frames of ultrasound images U are left as candidates for the frame group G to be evaluated.
• step S7 the target frame generator 27 generates an evaluation target frame group G using multiple frames of ultrasound images U in which it has been determined that no suspected lesion area A has been detected during the repetition of steps S1 to S6.
• step S8 the evaluation unit 29 extracts the GTC region R1 from the mammary gland region M extracted in step S3 for each ultrasound image U of the evaluation target frame group G generated in step S7, calculates the proportion of the GTC region R1 in the mammary gland region M, and performs a GTC evaluation based on the calculated proportion of the GTC region R1.
• the evaluation unit 29 can, for example, binarize the mammary gland region M of the ultrasound image U using a brightness threshold value Thb, thereby distinguishing between the GTC region R1 and the edematous stroma R2 in the mammary gland region M and extracting the GTC region R1.
• the evaluation unit 29 can also extract the GTC region R1 using a trained model that has trained the GTC region R1 (segmentation) in the mammary gland region M in a training ultrasound image of the breast.
• the evaluation unit 29 can calculate the proportion of the GTC region R1, for example, by the ratio of the sum of the number of pixels occupied by all hypoechoic regions in the mammary gland region M in the ultrasound image U to the number of pixels occupied by hyperechoic regions in the mammary gland region M.
• the evaluation unit 29 can output, for example, the average, median or maximum value of the proportion of the GTC region R1 in the mammary gland region M calculated in this way for multiple frames of ultrasound image U, as the final evaluation result ER.
• the evaluation unit 29 can also determine the category of the GTC region R1 based on, for example, the average, median, or maximum value of the proportion of the GTC region R1 in the mammary gland region M calculated for multiple frames of ultrasound images U, and output the category as the evaluation result ER. At this time, the evaluation unit 29 can output, as the category of the GTC region R1, any of a number of predetermined categories, for example, the two categories of Low and High, or any of the four categories of Minimal, Mild, Moderate, and Marked.
• the evaluation unit 29 can also input multiple frames of ultrasound images U into a machine learning trained model, outputting the category of the GTC region R1 for each of the multiple frames of ultrasound images U, and outputting the most frequent value as the final evaluation result ER of the GTC evaluation.
• both the GTC region R1 and the suspected lesion region A are depicted as hypoechoic regions in the ultrasound image U, and if a GTC evaluation is performed when the suspected lesion region A is regarded as the GTC region R1, an accurate evaluation result ER may not be obtained.
• the evaluation unit 29 performs a GTC evaluation based on the evaluation target frame group G in which the suspected lesion region A is not detected, and therefore can output a highly accurate evaluation result ER.
• step S9 the display control unit 22 displays the evaluation result ER of the GTC evaluation output in step S7 on the monitor 23, as shown in FIG. 7, for example.
• the user can accurately grasp the evaluation result ER, so even if a suspected lesion area A exists in the mammary gland area M, it is possible to accurately consider the risk of cancer in the subject's breast.
• step S9 When the processing of step S9 is completed in this manner, the operation of the ultrasound diagnostic device according to the flowchart in Figure 8 is completed.
• the lesion detection unit 26 detects a suspected lesion area A in the mammary gland region M for each of the multiple frames of ultrasound images U
• the target frame generation unit 27 generates an evaluation target frame group G using ultrasound images U of frames other than those in which the suspected lesion area A was detected by the lesion detection unit 26 among the multiple frames of ultrasound images U
• the evaluation unit 29 performs GTC evaluation on the ultrasound images U of each frame of the evaluation target frame group G. Therefore, even if a suspected lesion area A is present, the user can accurately consider the risk of cancer in the subject's mammary gland region M.
• the transmitting/receiving circuit 12 is described as being provided in the ultrasonic probe 1 , the transmitting/receiving circuit 12 may be provided in the device main body 2 . Further, although the image generating unit 21 is described as being provided in the device main body 2, the image generating unit 21 may be provided in the ultrasound probe 1.
• the device main body 2 may be a so-called stationary type, a portable type that is easy to carry, or a so-called handheld type that is configured, for example, by a smartphone or tablet computer. In this way, the type of device that configures the device main body 2 is not particularly limited.
• the ultrasonic probe 1 and the device body 2 are connected to each other by wire, the ultrasonic probe 1 and the device body 2 may be connected to each other wirelessly.
• the target frame generation unit 27 can also generate a group of evaluation target frames G from ultrasound images U of multiple frames, including ultrasound images U of frames that are a predetermined number of frames before the frame in which the lesion detection unit 26 detected the suspected lesion area A, and ultrasound images U of frames that are a predetermined number of frames after the frame in which the lesion detection unit 26 detected the suspected lesion area A.
• the target frame generation unit 27 when a suspected lesion area A is detected in the Nth ultrasound image U of multiple ultrasound images U, the target frame generation unit 27 generates an evaluation target frame group G from ultrasound images U of frames prior to the N-Xth frame and ultrasound images U of frames after the N+Xth frame, where X is a set number of frames, and can exclude ultrasound images U of frames N-X+1 to N+X-1 from the evaluation target frame group G.
• X is an integer equal to or greater than 0
• N is a natural number equal to or greater than 2
• X ⁇ N is satisfied.
• the ultrasound images U of several frames before and after the frame in which the suspected lesion area A is detected may actually contain the suspected lesion area A for some reason, such as the ultrasound images U being unclear. Therefore, by generating the evaluation target frame group G from the ultrasound images U of frames preceding the frame a predetermined number of frames before the frame in which the suspected lesion area A is detected, and the ultrasound images U of frames following the frame a predetermined number of frames after the frame in which the lesion detection unit 26 detects the suspected lesion area A, the ultrasound images U including the suspected lesion area A can be more reliably excluded from the evaluation target frame group G, allowing the evaluation unit 29 to accurately perform the GTC evaluation.
• the display control unit 22 can also display on the monitor 23, for example, an ultrasound image U of each frame of the evaluation target frame group G generated by the target frame generation unit 27, by using a display screen of the monitor 23 as shown in FIG. 9.
• a first arrow button B1 pointing to the left, a second arrow button B2 pointing to the right, an ultrasound image U, and an image selection button B3 are displayed on the display screen of the monitor 23.
• the ultrasound images U of each frame of the evaluation target frame group G are displayed on the monitor 23 one frame at a time.
• the user can specify the ultrasound image U currently being displayed on the monitor 23, for example by selecting the image selection button B3 via the input device 32.
• the evaluation unit 29 can perform a GTC evaluation on the ultrasound image U of the frame thus specified by the user among the group of frames G to be evaluated. This allows the user to check not only the evaluation result ER of the GTC evaluation based on ultrasound images U of multiple frames, but also the evaluation result ER of the GTC evaluation for the ultrasound image U of a specific frame desired by the user, thereby enabling a more detailed consideration of the risk of cancer in the mammary gland region M.
• the display control unit 22 can also display on the monitor 23, among the ultrasound images U of multiple frames, an ultrasound image U of a frame in which a suspected lesion area A has been detected by the lesion detection unit 26.
• the display control unit 22 can first perform a display as shown in FIG. 10 on the monitor 23.
• the evaluation result ER of the GTC evaluation, a representative ultrasound image U in the evaluation target frame group G, and an excluded frame confirmation button B4 are displayed on the monitor 23.
• the display control unit 22 can, for example, produce a display as shown in FIG. 11 on the monitor 23 when the user selects the excluded frame confirmation button B4 via the input device 32.
• a first arrow button B1, a second arrow button B2, and an ultrasound image U showing a suspected lesion area A are displayed on the display screen of the monitor 23.
• the ultrasound images U of the frames of the evaluation target frame group G are displayed one by one on the monitor 23.
• the display control unit 22 can highlight the suspected lesion area A, for example, by superimposing a frame line E1 surrounding the suspected lesion area A on the ultrasound image U so that the user can easily confirm the suspected lesion area A.
• the method of highlighting the suspected lesion area A is not particularly limited, and any other method of displaying the frame line E1 can be used, for example, by giving the suspected lesion area A a color different from the surrounding area, by making the suspected lesion area A blink, by highlighting the outline of the suspected lesion area A, or the like.
• the display control unit 22 can display on the monitor 23 the ultrasound image U of each frame in which the lesion detection unit 26 has performed the detection process for the suspected lesion area A, and a dialogue for confirming with the user whether or not to correct the detection result of the suspected lesion area A by the lesion detection unit 26. After confirming the dialogue, the user can, for example, correct the detection result of the suspected lesion area A by performing an input operation via the input device 32.
• the device main body 2 may also be provided with a transmission circuit (not shown) that transmits the evaluation result ER of the GTC evaluation output by the evaluation unit 29, for example, via a network, to an external server device (not shown), such as a test information management system such as an electronic medical record, a report system that creates reports using medical images, and a PACS (Picture Archiving and Communication System).
• an external server device such as a test information management system such as an electronic medical record, a report system that creates reports using medical images, and a PACS (Picture Archiving and Communication System).
• protocols such as HTTP (Hypertext Transfer Protocol), HTTPS (Hypertext Transfer Protocol Secure), FTP (File Transfer Protocol), HL7 (Health Level Seven), DICOM (Digital Imaging and Communications in Medicine), etc. may be used.
• the size calculation unit 51 is connected to the lesion detection unit 26.
• the size calculation unit 51 is connected to the target frame generation unit 27 and the main body control unit 31A.
• the image generation unit 21, the display control unit 22, the mammary gland region extraction unit 25, the lesion detection unit 26, the target frame generation unit 27, the evaluation unit 29, the main body control unit 31A and the size calculation unit 51 constitute the processor 34A for the device main body 2A.
• the size calculation unit 51 calculates the size of the suspected lesion area A detected by the lesion detection unit 26.
• the size calculation unit 51 can calculate, for example, the maximum dimension of the suspected lesion area A or the number of pixels that the suspected lesion area A occupies in the mammary gland area M as the size of the suspected lesion area A.
• the target frame generation unit 27 can include, for example, an ultrasound image U of a frame in which the size of the suspected lesion area A calculated by the size calculation unit 51 is smaller than a predetermined size threshold value in the group of frames G to be evaluated.
• Step S15 has been added.
• Steps S11 to S14 correspond to steps S1 to S4 shown in Figure 8
• steps S16 to S20 correspond to steps S5 to S9 shown in Figure 8. Therefore, detailed descriptions of steps S11 to S14 and steps S16 to S20 will be omitted.
• step S11 an ultrasound image U is acquired, in step S12, the ultrasound image U is displayed on the monitor 23, and in step S13, the mammary gland region M is extracted from the ultrasound image U, and the process proceeds to step S14.
• step S14 the lesion detection unit 26 performs a process of detecting a suspected lesion area A from the ultrasound image U, and the target frame generation unit 27 determines whether or not the suspected lesion area A has been detected by this process. If it is determined that the suspected lesion area A has been detected, the process proceeds to step S15.
• step S15 the size calculation unit 51 calculates the size of the suspected-lesion area A detected in step S14, and the target frame generation unit 27 determines whether the calculated size of the suspected-lesion area A is smaller than a predetermined size threshold.
• the size calculation unit 51 can calculate, for example, the maximum dimension of the suspected-lesion area A or the number of pixels that the suspected-lesion area A occupies in the mammary gland area M as the size of the suspected-lesion area A.
• step S15 If it is determined in step S15 that the size of the suspected lesion area A is equal to or larger than the predetermined size threshold, the process proceeds to step S16.
• step S16 the target frame generator 27 excludes the ultrasound image U acquired in step S11 from the candidates for the evaluation target frame group G.
• step S15 If it is determined in step S15 that the size of the suspected lesion area A is smaller than the determined size threshold, the target frame generation unit 27 leaves the ultrasound image U acquired in step S11 as a candidate for the evaluation target frame group G.
• step S14 If it is determined in step S14 that the suspected lesion area A has not been detected, if it is determined in step S15 that the size of the suspected lesion area A is smaller than a predetermined size threshold, or if the processing of step S16 is completed, the process proceeds to step S17.
• step S17 the main body control unit 31A determines whether or not to end the capture of the ultrasound image U.
• steps S11 to S17 are repeated as long as it is determined in step S17 that capturing ultrasound images U should continue. If it is determined in step S17 that capturing ultrasound images U should end, the process proceeds to step S18, in which a group of frames G to be evaluated is generated by the target frame generator 27.
• the group of frames G to be evaluated that is generated includes ultrasound images U that show a suspected lesion area A that is smaller than a set size threshold, but because this suspected lesion area A is very small, it has almost no adverse effect on the GTC evaluation.
• step S19 the evaluation unit 29 performs a GTC evaluation using the group of evaluation target frames G generated in step S18.
• the display control unit 22 displays the evaluation result ER of the GTC evaluation output in step S19 on the monitor 23, for example as shown in FIG. 7.
• step S20 When the processing of step S20 is completed in this manner, the operation of the ultrasound diagnostic device according to the flowchart in Figure 13 is completed.
• the size calculation unit 51 calculates the size of the suspected lesion area A detected by the lesion detection unit 26, and the target frame generation unit 27 includes in the evaluation target frame group G the ultrasound image U of a frame in which the size of the suspected lesion area A calculated by the size calculation unit 51 is smaller than a predetermined size threshold.
• an accurate evaluation result ER of the GTC evaluation is obtained, so that even if a suspected lesion area A is present, the user can accurately consider the risk of cancer in the subject's mammary gland area M.
• the target frame generation unit 27 can also determine the ultrasound images U to be included in the evaluation target frame group G by taking into account the degree of malignancy of the suspected lesion area A detected by the lesion detection unit 26 .
• FIG. 14 shows the configuration of an ultrasound diagnostic device according to embodiment 3.
• the ultrasound diagnostic device according to embodiment 3 includes a device body 2B instead of the device body 2 in the ultrasound diagnostic device according to embodiment 1 shown in FIG. 1.
• Device body 2B includes a new malignancy calculation unit 52 in device body 2 in embodiment 1, and includes a body control unit 31B instead of the body control unit 31.
• the malignancy calculation unit 52 is connected to the lesion detection unit 26.
• the malignancy calculation unit 52 is connected to the target frame generation unit 27 and the main body control unit 31B.
• the image generation unit 21, the display control unit 22, the mammary gland region extraction unit 25, the lesion detection unit 26, the target frame generation unit 27, the evaluation unit 29, the main body control unit 31B, and the malignancy calculation unit 52 constitute the processor 34B for the device main body 2B.
• the malignancy calculation unit 52 calculates the malignancy of the suspected lesion area A detected by the lesion detection unit 2, for example, by performing image analysis.
• the malignancy calculated by the malignancy calculation unit 52 refers to the probability that the tissue within the set suspected lesion area A is malignant. For example, the higher the malignancy of a pixel, the higher the probability that the pixel represents tissue within a malignant lesion, and the lower the malignancy of a pixel, the higher the probability that the pixel represents tissue within a benign lesion.
• the malignancy calculation unit 52 can calculate the malignancy of the suspected lesion area A by recognizing the shape of the tissue using, for example, an image recognition method including pattern matching and extraction of so-called features, or a deep learning method.
• the malignancy calculation unit 52 can calculate the malignancy by learning in advance multiple ultrasound images including malignant masses and multiple ultrasound images including benign masses as so-called teacher data, and comparing the relationship between the brightness of a specific pixel in the suspected lesion area A and the brightness of its surrounding pixels with the learned data.
• the target frame generation unit 27 can include in the evaluation target frame group G ultrasound images U of frames in which the malignancy of the suspected lesion area A calculated by the malignancy calculation unit 52 is smaller than a determined malignancy threshold value.
• step S21 an ultrasound image U is acquired, in step S22, the ultrasound image U is displayed on the monitor 23, and in step S23, the mammary gland region M is extracted from the ultrasound image U, and the process proceeds to step S24.
• step S24 the lesion detection unit 26 performs a process of detecting a suspected lesion area A from the ultrasound image U, and the target frame generation unit 27 determines whether or not the suspected lesion area A has been detected by this process. If it is determined that the suspected lesion area A has been detected, the process proceeds to step S25.
• step S25 the malignancy calculation unit 52 calculates the malignancy of the suspected lesion area A detected in step S24, and the target frame generation unit 27 determines whether the calculated malignancy of the suspected lesion area A is smaller than a determined malignancy threshold.
• the malignancy calculation unit 52 can calculate the malignancy of the suspected lesion area A by recognizing the shape of the tissue using, for example, an image recognition method including pattern matching and extraction of so-called features, or a deep learning method.
• step S25 If it is determined in step S25 that the malignancy of the suspected lesion area A is equal to or greater than the determined malignancy threshold, the process proceeds to step S26.
• step S26 the target frame generator 27 excludes the ultrasound image U acquired in step S21 from the candidates for the evaluation target frame group G.
• the target frame generation unit 27 leaves the ultrasound image U acquired in step S21 as a candidate for the evaluation target frame group G.
• step S24 If it is determined in step S24 that the suspected lesion area A has not been detected, if it is determined in step S25 that the malignancy of the suspected lesion area A is less than the determined malignancy threshold, or if the processing of step S26 is completed, the process proceeds to step S27.
• step S27 the main body control unit 31B determines whether or not to end the capture of the ultrasound image U.
• step S27 determines whether the capturing of ultrasound images U should continue. If it is determined in step S27 that the capturing of ultrasound images U should end, the process proceeds to step S28, in which a group of frames G to be evaluated is generated by the target frame generator 27.
• the group of frames G to be evaluated that is generated does not include ultrasound images U that show a suspected lesion area A with a malignancy level greater than a determined malignancy level threshold, i.e., a suspected lesion area A that can be judged to be sufficiently malignant.
• step S29 the evaluation unit 29 performs GTC evaluation using the group of evaluation frames G generated in step S28. Since the group of evaluation frames G does not include a suspicious lesion area A that can be sufficiently determined to be malignant, the evaluation unit 29 can perform GTC evaluation accurately.
• the display control unit 22 displays the evaluation result ER of the GTC evaluation output in step S29 on the monitor 23, for example as shown in FIG. 7.
• step S30 When the processing of step S30 is completed in this manner, the operation of the ultrasound diagnostic device according to the flowchart in Figure 15 is completed.
• the malignancy calculation unit 52 calculates the malignancy of the suspected lesion area A detected by the lesion detection unit 26, and the target frame generation unit 27 includes in the evaluation target frame group G the ultrasound image U of a frame in which the size of the suspected lesion area A calculated by the malignancy calculation unit 52 is smaller than a predetermined malignancy threshold value, so that the evaluation unit 29 can accurately perform GTC evaluation, and even if a suspected lesion area A is present, the user can accurately consider the risk of cancer in the subject's mammary gland area M.
• the ultrasound diagnostic device of embodiment 3 has a configuration in which a malignancy calculation unit 52 is added to the ultrasound diagnostic device of embodiment 1, but it can also have a configuration in which a malignancy calculation unit 52 is added to the ultrasound diagnostic device of embodiment 2.

Landscapes

• Health & Medical Sciences (AREA)
• Engineering & Computer Science (AREA)
• Life Sciences & Earth Sciences (AREA)
• Medical Informatics (AREA)
• Physics & Mathematics (AREA)
• Public Health (AREA)
• Biomedical Technology (AREA)
• General Health & Medical Sciences (AREA)
• Pathology (AREA)
• Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
• Radiology & Medical Imaging (AREA)
• Molecular Biology (AREA)
• Biophysics (AREA)
• Heart & Thoracic Surgery (AREA)
• Veterinary Medicine (AREA)
• Surgery (AREA)
• Animal Behavior & Ethology (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Theoretical Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Geometry (AREA)
• Quality & Reliability (AREA)
• Data Mining & Analysis (AREA)
• Databases & Information Systems (AREA)
• Epidemiology (AREA)
• Primary Health Care (AREA)
• Physiology (AREA)
• Ultra Sonic Daignosis Equipment (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Related Child Applications (1)

Publications (1)

Family

ID=92755211

Family Applications (1)

Country Status (4)

Citations (6)

• 2024
  • 2024-02-09 WO PCT/JP2024/004572 patent/WO2024190217A1/ja not_active Ceased
  • 2024-02-09 JP JP2025506594A patent/JPWO2024190217A1/ja active Pending
  • 2024-02-09 EP EP24770335.8A patent/EP4681653A1/en active Pending
• 2025
  • 2025-09-08 US US19/322,020 patent/US20260000382A1/en active Pending

Patent Citations (6)

Non-Patent Citations (3)

Also Published As

Similar Documents

Legal Events