Ultrasound diagnostic device and method for controlling the ultrasound diagnostic device

Abstract

To provide an ultrasonic diagnostic apparatus which can determine a medical examination category or a diagnosis category of a lesion part by referring to a plurality of ultrasonic images and correctly grasp a basis of the determination, and a control method of the ultrasonic diagnostic apparatus.SOLUTION: An ultrasonic diagnostic apparatus identifies properties of a lesion part with respect to a determination item for path selection in a plurality of branches of a determination procedure stored in a determination procedure memory on the basis of a plurality of ultrasonic images obtained by imaging the same lesion part, extracts at least one ultrasonic image that contributes to identification of the properties in the plurality of branches of the determination procedure from the plurality of ultrasonic images as a basis image, determines a medical examination category or a diagnosis category of the lesion part by performing path selection in the plurality of branches in the determination procedure by applying the identified properties to the determination item, and displays a path in the determination procedure when the medical examination category or the diagnosis category is determined and the extracted basis image on a monitor.SELECTED DRAWING: Figure 13

Description

[Technical Field]

[0001] The present invention relates to an ultrasonic diagnostic apparatus and a method for controlling the ultrasonic diagnostic apparatus, and more particularly to an ultrasonic diagnostic apparatus that determines the screening category or diagnostic category of a lesion according to a predetermined determination procedure having multiple branches. [Background technology]

[0002] In the medical field, ultrasound diagnostic devices that use ultrasound images have been put to practical use for some time. Generally, an ultrasound diagnostic device includes an ultrasound probe with a built-in transducer array and a device main body connected to the ultrasound probe. An ultrasound beam is transmitted from the ultrasound probe to a subject, and ultrasound echoes from the subject are received by the ultrasound probe. The received signals are then electrically processed to generate an ultrasound image.

[0003] Patent Document 1 discloses an apparatus that assists in examination of a subject by determining whether a lesion is benign or malignant based on an image, such as an ultrasound image, of the lesion in the subject. According to a predetermined examination procedure, decision options are presented in sequence, and decisions are made by referring to information on the lesion obtained by various tools, such as measurement tools. The history of each decision is displayed in bold lines on a diagram showing the entire examination procedure in a tree format. Furthermore, information such as measurement values ​​of the lesion obtained by the tools and serving as the basis for the decision is displayed corresponding to each decision. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-342028 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in order to determine whether a lesion is benign or malignant, multiple ultrasound images displayed as moving images are often referred to. In such cases, even if information such as measurement values ​​of the lesion is displayed along with the judgment history, there is a risk that the basis for the judgment cannot be accurately understood.

[0006] The present invention has been made to solve these conventional problems, and aims to provide an ultrasound diagnostic device and a control method for an ultrasound diagnostic device that can determine the screening category or diagnostic category of a lesion by referring to multiple ultrasound images and accurately grasp the basis for the determination. [Means for solving the problem]

[0007] The above object can be achieved by the following configuration. [1] An ultrasound diagnostic device that determines the screening category or diagnostic category of a lesion according to a predetermined determination procedure having multiple branches, a judgment procedure memory in which a judgment procedure is stored; an identification unit that identifies the characteristics of the lesion for a judgment item for selecting a path at a plurality of branches of a judgment procedure stored in a judgment procedure memory based on a plurality of ultrasound images of the same lesion; an extracting unit that extracts, as a basis image, at least one ultrasound image that contributes to the identification of characteristics at multiple branches of the determination procedure by the identifying unit from the multiple ultrasound images; a determination unit that determines the examination category or diagnosis category of the lesion by applying the characteristics identified by the identification unit to a determination item and selecting a path from a plurality of branches of a determination procedure; The monitor and a display control unit that displays on a monitor a path in a determination procedure when the determination unit determines a screening category or a diagnostic category and a basis image extracted by the extraction unit; An ultrasound diagnostic device comprising:

[0008] [2] The ultrasound diagnostic device according to [1], wherein the plurality of ultrasound images are images that constitute a video of a lesion. [3] The ultrasound diagnostic device according to [1] or [2], wherein each of the plurality of ultrasound images is an image of the entire or part of the lesion. [4] The ultrasound diagnostic device according to [2] or [3], wherein the plurality of ultrasound images are images thinned out from images constituting a video of the lesion, images interpolated, or images synthesized.

[0009] [5] The extraction unit forms an encircling line in the basis image that encloses a portion that contributes to the identification of the characteristics by the identification unit; The ultrasound diagnostic device according to any one of [1] to [4], wherein the display control unit displays an encircling line superimposed on the basis image. [6] The extraction unit forms a heat map based on the evidence image, in which the contribution rate of the portion that contributes to the identification of the property by the identification unit is represented by a shade of color or a difference in color; The ultrasonic diagnostic device according to any one of [1] to [5], wherein the display control unit displays the heat map on the monitor.

[0010] [7] An ultrasound diagnostic device according to any one of [1] to [6], wherein the display control unit, when multiple basis images are extracted for one branch by the extraction unit, displays the multiple basis images side by side on the monitor. [8] An input device for a user to perform input operations is provided, An ultrasound diagnostic apparatus according to any one of [1] to [7], wherein the display control unit sequentially displays the multiple basis images on the monitor based on the user's input operation via the input device when the extraction unit extracts multiple basis images for one branch. [9] The ultrasound diagnostic device according to [8], wherein the display control unit overlays a page number indicating which of a plurality of basis images the basis image is displayed on the monitor.

[0011]

[10] The identification unit measures the size of the lesion, The ultrasound diagnostic device according to any one of [1] to [9], wherein the display control unit displays the size measured by the identification unit on the monitor.

[11] The identification unit calculates, for each judgment item, the proportion of the area in which the identified characteristic appears to the entire area of ​​the lesion; The ultrasound diagnostic device according to any one of [1] to

[10] , wherein the display control unit displays the ratio calculated by the identification unit on the monitor.

[0012]

[12] The determination unit includes a probability calculation unit that calculates the probability of a path selection at a plurality of branches of the determination procedure based on the characteristics of the lesion, The ultrasound diagnostic device according to any one of [1] to

[11] , wherein the display control unit displays the accuracy calculated by the accuracy calculation unit on the monitor.

[13] An ultrasound diagnostic device as described in

[12] , in which, when multiple screening categories or diagnostic categories correspond to any of multiple branches in the judgment procedure, the judgment unit judges the screening category or diagnostic category of the lesion by comparing the accuracy calculated by the accuracy calculation unit with a predetermined threshold value.

[14] An ultrasound diagnostic device according to any one of [1] to

[13] , comprising an ultrasound probe and an image generation unit that generates multiple ultrasound images of the same lesion by transmitting and receiving ultrasound beams to and from a subject using the ultrasound probe.

[0013]

[15] A control method for an ultrasound diagnostic apparatus that determines a screening category or a diagnostic category of a lesion according to a predetermined determination procedure having multiple branches, comprising: a step of identifying the characteristics of the lesion with respect to a judgment item for selecting a path at a plurality of branches of a judgment procedure based on a plurality of ultrasound images of the same lesion; extracting at least one ultrasound image that contributes to identifying the characteristics from the plurality of ultrasound images as a basis image; a step of determining the examination category or diagnostic category of the lesion by applying the identified characteristics to judgment items and selecting a route at a plurality of branches; The method includes a step of displaying on a monitor the path in the determination procedure when the examination category or the diagnostic category is determined and the extracted evidence image. A method for controlling an ultrasound diagnostic device. [Effects of the Invention]

[0014] According to the present invention, the identification unit identifies the characteristics of the lesion for the judgment items for route selection at multiple branches of the judgment procedure stored in the judgment procedure memory based on multiple ultrasound images of the same lesion, and the extraction unit extracts at least one ultrasound image from the multiple ultrasound images that contributes to the identification of the characteristics at multiple branches of the judgment procedure by the identification unit as a basis image, and the path in the judgment procedure when the screening category or diagnostic category is determined and the basis image extracted by the extraction unit are displayed on the monitor.Therefore, by referring to the multiple ultrasound images, it is possible to determine the screening category or diagnostic category of the lesion and accurately understand the basis for the determination. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to a first embodiment of the present invention. [Figure 2] 2 is a block diagram showing the internal configuration of a transmission / reception circuit according to the first embodiment. FIG. [Figure 3] FIG. 2 is a block diagram showing the internal configuration of an image generating unit according to the first embodiment. [Figure 4] FIG. 3 is a diagram showing a determination procedure used in the first embodiment. [Figure 5] FIG. 10 is a diagram showing the maximum diameter of a lesion measured by a measuring unit in one cross section. [Figure 6] FIG. 10 is a diagram showing the maximum diameter of the lesion measured by the measuring unit in another cross section. [Figure 7] FIG. 10 is a diagram showing the aspect ratio of a lesion measured by a measurement unit. [Figure 8] FIG. 1 is a diagram showing a schematic diagram of a lesion having an oval shape. [Figure 9] FIG. 1 is a diagram illustrating a polygonal lesion. [Figure 10] FIG. 1 is a schematic diagram of a lesion having a lobulated shape. [Figure 11]FIG. 1 is a diagram showing a schematic diagram of a lesion having an irregular shape. [Figure 12] 3 is a flowchart showing the operation of the first embodiment. [Figure 13] FIG. 10 is a diagram showing a determination procedure in which a route and a ground image are shown according to the first embodiment. [Figure 14] 10A and 10B are diagrams showing a part of a determination procedure in which a grounds image including an encircling line is displayed. [Figure 15] FIG. 10 is a diagram showing a part of a determination procedure in which a grounds image and a heat map are displayed side by side. [Figure 16] FIG. 10 is a diagram showing a part of a determination procedure in which a grounds image and a heat map are displayed in sequence. [Figure 17] FIG. 10 is a diagram showing a part of a determination procedure in which a plurality of basis images are displayed side by side. [Figure 18] 10A and 10B are diagrams showing a part of a determination procedure in which a plurality of basis images are displayed in sequence. [Figure 19] FIG. 10 is a diagram showing a part of the determination procedure in which the size of the lesion is displayed. [Figure 20] FIG. 10 is a diagram showing a part of the determination procedure in which the proportion of the area in which the characteristics of the identified lesion appear to the entire lesion area is displayed. [Figure 21] FIG. 10 is a diagram showing a part of the determination procedure in which the number of "necks" and "corners" is displayed. [Figure 22] 10 is a flowchart illustrating the operation of a modified example of the first embodiment. [Figure 23] FIG. 10 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to a second embodiment. [Figure 24] FIG. 10 is a diagram showing a part of a determination procedure in which the accuracy of route selection is displayed. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. The following description of the components will be given based on a representative embodiment of the present invention, but the present invention is not limited to such an embodiment. In this specification, a numerical range expressed using "to" means a range that includes the numerical values ​​before and after "to" as the lower and upper limits. In this specification, the terms "same" and "identical" include a margin of error generally accepted in the technical field.

[0017] [Embodiment 1] 1 shows the configuration of an ultrasonic diagnostic apparatus according to the first embodiment of the present invention. The ultrasonic diagnostic apparatus includes an ultrasonic probe 10 and an apparatus main body 20. The ultrasonic probe 10 and the apparatus main body 20 are wired to each other via a cable (not shown).

[0018] The ultrasonic probe 10 has a transducer array 11 and a transmission / reception circuit 12 connected to the transducer array 11 .

[0019] The device main body 20 has an image generation unit 21 connected to the transmission / reception circuit 12 of the ultrasound probe 10, and a display control unit 22 and a monitor 23 are connected to the image generation unit 21 in turn, and an image memory 24 is connected to the image generation unit 21. A recognition unit 25 and an extraction unit 26 are connected to the image memory 24, and the extraction unit 26 is connected to the recognition unit 25. A determination unit 27 is connected to the recognition unit 25, and the recognition unit 25, extraction unit 26, and determination unit 27 are each connected to the display control unit 22. A determination procedure memory 32 is connected to the recognition unit 25, extraction unit 26, and determination unit 27.

[0020] The image generating unit 21, the display control unit 22, the image memory 24, the identifying unit 25, the extracting unit 26, the determining unit 27, and the determining procedure memory 32 are connected to a main body control unit 28, and an input device 29 is connected to the main body control unit 28. The transmitting / receiving circuit 12 of the ultrasound probe 10 is also connected to the main body control unit 28. The image generating unit 21, the display control unit 22, the identifying unit 25, the extracting unit 26, the determining unit 27, the determining procedure memory 32, and the main body control unit 28 constitute a processor 30.

[0021] The transducer array 11 of the ultrasonic probe 10 has a plurality of ultrasonic transducers arranged one-dimensionally or two-dimensionally. Each of these transducers transmits ultrasonic waves in accordance with a drive signal supplied from the transmission / reception circuit 12, receives reflected waves from the subject, and outputs an analog reception signal. Each transducer is configured by forming electrodes on both ends of a piezoelectric element made of, for example, a piezoelectric ceramic typified by PZT (Lead Zirconate Titanate), a polymer piezoelectric element typified by PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal typified by PMN-PT (Lead Magnesium Niobate-Lead Titanate).

[0022] The transmission / reception circuit 12, under the control of the main body control unit 28, transmits ultrasonic waves from the transducer array 11 and generates sound ray signals based on reception signals acquired by the transducer array 11. As shown in Fig. 2, the transmission / reception circuit 12 has a pulser 13 connected to the transducer array 11, an amplifier 14, an AD (Analog-to-Digital) converter 15, and a beamformer 16, which are connected in series to the transducer array 11.

[0023] The pulser 13 includes, for example, a plurality of pulse generators, and adjusts the delay amount of each drive signal and supplies it to the plurality of transducers of the transducer array 11 so that the ultrasound waves transmitted from the plurality of transducers form an ultrasound beam based on a transmission delay pattern selected in response to a control signal from the main body control unit 28. In this way, when a pulsed or continuous wave voltage is applied to the electrodes of the transducers of the transducer array 11, the piezoelectric material expands and contracts, and each transducer generates a pulsed or continuous wave ultrasound wave, and an ultrasound beam is formed from the composite wave of these ultrasound waves.

[0024] 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 10. The ultrasonic echo propagating toward the transducer array 11 in this manner is received by each transducer constituting the transducer array 11. At this time, each transducer constituting the transducer array 11 expands and contracts upon receiving the propagating ultrasonic echo, generating a received signal which is an electrical signal, and outputs this received signal to the amplifier 14.

[0025] The amplifier 14 amplifies signals input from each transducer constituting 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 this reception data to the beamformer 16. The beamformer 16 performs so-called reception focusing processing by delaying and adding each piece of reception data converted by the AD converter 15 in accordance with the speed of sound or the distribution of sound speeds set based on the reception delay pattern selected in response to a control signal from the main body control unit 28. This reception focusing processing performs phasing and addition of each piece of reception data converted by the AD converter 15, and acquires a sound ray signal with a narrowed focus of the ultrasonic echo.

[0026] As shown in FIG. 3, the image generating section 21 of the device main body 20 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 10 in accordance with the depth of the ultrasonic reflection position, and then performs envelope detection processing to generate an ultrasonic image signal (B-mode image signal) that is tomographic image information on the tissue within the subject.

[0027] The DSC 42 converts (raster converts) the ultrasound image signal generated by the signal processing unit 41 into an image signal that conforms to the scanning method of 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 referred to as an ultrasound image.

[0028] 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 28. For example, 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 subject's breasts.

[0029] The image memory 24 may be a recording medium such as 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), or USB memory (Universal Serial Bus memory).

[0030] The judgment procedure memory 32 is a memory that stores a predetermined judgment procedure for determining which of a plurality of standardized examination categories a lesion falls into based on whether the lesion is benign or malignant. For example, a judgment procedure for determining the examination category of a mass formed in the mammary gland, as shown in Fig. 4, is stored in the judgment procedure memory 32. This judgment procedure is shown in the guidelines created by the Japanese Association of Breast and Thyroid Sonology (JABTS), and has multiple branches where the path splits off according to each judgment item. The determination procedure memory 32 may be, for example, a flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, USB memory, or the like.

[0031] JABTS defines screening categories 1-5 as follows: Screening Category 1: No abnormal findings Screening Category 2: Findings present but no further examination is required Screening Category 3: Benign but malignancy cannot be ruled out Screening Category 4: Suspected malignancy Screening Category 5: Malignant

[0032] For example, in the first branch B1, three judgment items are set regarding ultrasound echoes from inside the tumor in the ultrasound image: cystic pattern (unechoic), mixed pattern (having solid and liquid parts), and solid pattern. If a cystic pattern is selected based on the characteristics of the ultrasound echo, the tumor is determined to belong to screening category 2, and if a mixed pattern is selected, the tumor is determined to belong to screening category 3 or 4, but if the maximum diameter of the tumor is 5 mm or less, it is determined to belong to screening category 2.

[0033] Furthermore, if a solid pattern is selected at branch B1, depending on the characteristics of the ultrasound echo, if it corresponds to "a maximum diameter of 2 cm or less, a sufficiently small aspect ratio, a smooth, clearly defined border all around," etc., it is determined to belong to screening category 2; if it does not, the process proceeds to the next branch B2. In branch B2, border hyperechoic image and mammary gland border disruption are set as criteria, and if at least one of these is true, the mass is determined to belong to screening category 4 or 5. If neither border hyperechoic image nor mammary gland border disruption is true, the screening category is determined according to whether there are multiple fine / punctate hyperechoic features, and according to the maximum diameter of the tumor and the aspect ratio of the mass. Furthermore, the screening category may be adjusted according to the shape of the mass.

[0034] Here, the diameter of the tumor is expressed as L1 × L2 × L3 [mm] by measuring the maximum length L1 of the tumor N and the maximum width L3 on a line perpendicular to the maximum length L1 in a cross section including the maximum dimension of the tumor N, as shown in Figure 5, and then measuring the maximum diameter L2 in a cross section perpendicular to the cross section including the maximum dimension of the tumor N, as shown in Figure 6. Note that the maximum length L1, maximum diameter L2, and maximum width L3 are measured including the dimensions of the boundary hyperechoic portion H. Furthermore, the aspect ratio of a tumor can be expressed as the value obtained by measuring the horizontal diameter W of the tumor M in a direction parallel to the subject's body surface (skin) and the vertical diameter D in a direction perpendicular to the horizontal diameter W, excluding the boundary hyperechoic portion, and dividing the vertical diameter D by the horizontal diameter W, as shown in Figure 7, for example.

[0035] Furthermore, the shape of the tumor is classified according to whether or not the shape, including the hyperechoic boundary portion, has "constrictions" and "corners," for example, into circular or elliptical shapes (no constrictions, no corners) as shown in Figure 8, polygonal shapes (no constrictions, corners) as shown in Figure 9, lobulated shapes (constrictions, no corners) as shown in Figure 10, and irregular shapes (constrictions, corners) as shown in Figure 11.

[0036] The discrimination unit 25 reads out a discrimination procedure from the discrimination procedure memory 32 and analyzes a plurality of ultrasound images generated by the image generation unit 21 and stored in the image memory 24, thereby discriminating the characteristics of the lesion for the judgment items for path selection at the plurality of branches of the discrimination procedure as shown in Fig. 4. The "cystic pattern," "mixed pattern," "solid pattern," "border hyperechoic image," "fracture of the mammary gland boundary line," "fine / punctate hyperechoic," "maximum diameter of the tumor," "aspect ratio of the tumor," "shape of the tumor," "waist," "corner," etc., exemplified in the above discrimination procedure, correspond to the characteristics of the lesion discriminated by the discrimination unit 25.

[0037] The classification of the characteristics of the lesion in the classification unit 25 can be performed using at least one of template matching, image analysis technology using feature quantities such as Adaboost (Adaptive Boosting), SVM (Support Vector Machine) or SIFT (Scale-Invariant Feature Transform), and a determination model trained using machine learning technology such as deep learning. Note that the determination model is, for example, a trained model trained using training ultrasound images of the breast including the lesion area. The boundary of the lesion is determined by the identification unit 25, and based on the boundary, the size of the lesion, such as the maximum diameter and aspect ratio, is also measured.

[0038] The multiple ultrasound images analyzed by the identification unit 25 may constitute a video of the same lesion in the subject, and each of the multiple ultrasound images is an image of all or part of the lesion. In addition, the identification unit 25 may directly analyze the multiple ultrasound images that make up the video of the lesion, or it may analyze images that have been thinned out from the multiple ultrasound images that make up the video, images that have been interpolated between the multiple ultrasound images that make up the video, or images that have been synthesized from the multiple ultrasound images that make up the video. The result of the classification of the nature of the lesion by the classification unit 25 is sent from the classification unit 25 to the extraction unit 26 and the determination unit 27 .

[0039] The extraction unit 26 receives the classification result of the characteristics of the lesion from the classification unit 25, and extracts at least one ultrasound image that contributes to classification at multiple branches of the judgment procedure by the classification unit 25 as a basis image from among the multiple ultrasound images generated by the image generation unit 21 and stored in the image memory 24. That is, when determining whether the characteristics of the lesion correspond to the judgment items at the multiple branches of the judgment procedure shown in Figure 4, the ultrasound image that best represents the judgment, the ultrasound image that is decisive for the judgment, is extracted. In this case, for example, the likelihood of determining each characteristic corresponding to the branch of the judgment procedure for multiple ultrasound images is scored and recorded, and the characteristic with the highest score, or the characteristic with the highest average, median, mode, etc. of the scores of the multiple ultrasound images, is selected as the branching path, and the ultrasound image with the highest score for the characteristic corresponding to the selected path is extracted as the basis image. The number of ultrasound images to be extracted is not limited to one, and the extracting unit 26 can also extract a plurality of ultrasound images as basis images.

[0040] The judgment unit 27 receives the identification result of the characteristics of the lesion from the identification unit 25, and in the multiple branches of the judgment procedure stored in the judgment procedure memory 32, applies the characteristics of the lesion identified by the identification unit 25 to the judgment items corresponding to each branch, and selects the path of the judgment procedure, thereby determining the examination category of the lesion.

[0041] Under the control of the main body control unit 28, the display control unit 22 performs predetermined processing on the ultrasound image sent from the image generation unit 21, and displays the ultrasound image on the monitor 23. In addition, the display control unit 22 displays the judgment procedure stored in the identification unit 25 on the monitor 23, and superimposes on the judgment procedure the path in the judgment procedure when the examination category is determined by the judgment unit 27 and the basis image extracted by the extraction unit 26 on the monitor 23. The monitor 23 displays ultrasound images, determination procedures, 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).

[0042] The main body control unit 28 controls each part of the device main body 20 and the transmitting / receiving circuit 12 of the ultrasonic probe 10 based on a control program stored in advance. Although not shown, a main body side storage unit is connected to the main body control unit 28. The main body side storage unit stores control programs and the like. The main body side storage unit may be, for example, a flash memory, RAM, an SD card, or an SSD.

[0043] The input device 29 is used by the user to perform input operations, and is configured by devices such as a keyboard, a mouse, a trackball, a touchpad, and a touch sensor placed over the monitor 23, for example.

[0044] The processor 30 having the image generation unit 21, display control unit 22, identification unit 25, extraction unit 26, judgment unit 27 and main body control unit 28 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 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 composed of a combination of these.

[0045] In addition, the image generation unit 21, display control unit 22, identification unit 25, extraction unit 26, judgment unit 27 and main body control unit 28 of the processor 30 can be partially or entirely integrated into a single CPU or the like.

[0046] Next, the operation of the ultrasound diagnostic apparatus according to the first embodiment will be described with reference to the flowchart shown in FIG. First, in step S1, the identification unit 25 reads out a judgment procedure from the judgment procedure memory 32, analyzes multiple ultrasound images of the same lesion in the subject that have been photographed and stored in the image memory 24, and identifies the characteristics of the lesion for the judgment items set at each branch of the judgment procedure. For example, it is determined whether the lesion falls into one of the three judgment items set in the first branch B1 of the judgment procedure shown in Figure 4, namely, the cystic pattern, the mixed pattern, or the solid pattern.

[0047] Next, in step S2, the extraction unit 26 reads out the judgment procedure from the judgment procedure memory 32, and extracts at least one ultrasound image that contributes to identifying the characteristics of the lesion at the multiple branches of the judgment procedure performed in step S1 as a basis image. When determining whether the characteristics of the lesion correspond to the judgment items in step S1, the extraction unit 26 extracts, as a basis image, the ultrasound image that best represents the determination from the multiple ultrasound images analyzed by the identification unit 25. For example, for multiple ultrasound images, the likelihood of determining each characteristic corresponding to the branch of the judgment procedure is scored, and the characteristic with the highest score, or the characteristic with the highest average, median, mode, etc. of the scores of the multiple ultrasound images, is selected as the branching path, and the ultrasound image with the highest score for the characteristic corresponding to the selected path is extracted as the basis image. When there are multiple ultrasound images that most contribute to the classification by the classification unit 25, the basis image is not limited to one ultrasound image, but multiple ultrasound images are extracted as basis images.

[0048] Once the basis image has been extracted, the process proceeds to step S3, where it is determined whether or not the identification of the nature of the lesion in step S1 and the extraction of the basis image in step S2 have been completed for all of the multiple branches of the determination procedure. If there are any remaining branches for which the characteristics of the lesion have not yet been identified and the basis image has not yet been extracted, the process returns to step S1, and for the next branch in the judgment procedure, the identification unit 25 identifies the characteristics of the lesion, and then in step S2, the extraction unit 26 extracts the basis image. In this manner, steps S1 to S3 are repeated until identification of the nature of the lesion and extraction of the basis image are completed for all branches in step S3.

[0049] If it is determined in step S3 that the identification of the properties of the lesion and the extraction of the evidence images for all branches have been completed, the process proceeds to step S4, where the determination unit 27 reads out a determination procedure from the determination procedure memory 32 and determines the examination category of the lesion according to the determination procedure. At this time, the determination unit 27 can determine the examination category of the lesion by applying the properties of the lesion identified by the identification unit 25 to the judgment items corresponding to each branch in the multiple branches of the determination procedure and selecting the path of the determination procedure.

[0050] Once the examination category of the lesion has been determined in this manner, the process proceeds to step S5, where, as shown in Figure 13, the display control unit 22 displays on the monitor 23 the determination procedure used to determine the examination category, and further, the path taken by the determination unit 27 to determine the examination category and the basis image extracted by the extraction unit 26 are superimposed on the determination procedure. The boundary of the lesion determined by the discrimination unit 25 can be superimposed on the ground image. In FIG. 13, the path when the examination category is determined by the determining unit 27 is highlighted with a thick line, and it can be seen that the lesion of the subject has been determined to belong to examination categories 4 and 5. The judgment path is not limited to being displayed as a thick line, but can also be displayed as a highlighted line in a specific color.

[0051] Also, in the example shown in Figure 13, at the first branch B1, the lesion is judged to fall into the solid pattern out of three judgment items: cystic pattern, mixed pattern, and solid pattern. The ultrasound image that best represents this judgment is extracted by the extraction unit 26 and displayed near branch B1 in the judgment procedure as the basis image U1. Similarly, at branch B2, the lesion is judged to correspond to at least one of a boundary hyperechoic image and a mammary gland boundary line rupture, and the ultrasound image that best represents this judgment is extracted by extraction unit 26 and displayed near branch B2 in the judgment procedure as basis image U2.

[0052] In this way, the identification unit 25 identifies the characteristics of the lesion for judgment items at multiple branches of the judgment procedure based on multiple ultrasound images of the same lesion in the subject, the extraction unit 26 extracts at least one ultrasound image from the multiple ultrasound images that contributes to the identification of the characteristics by the identification unit 25 as a basis image, and the display control unit 22 displays on the monitor 23 the path in the judgment procedure when the examination category is determined and the basis image extracted by the extraction unit 26, so that regardless of the user's level of skill, it becomes possible to determine the examination category of the lesion from multiple ultrasound images and accurately understand the basis for the determination.

[0053] The extraction unit 26 may form an encircling line surrounding a portion that contributes to the identification by the identification unit 25 in a basis image extracted from a plurality of ultrasound images based on the identification result of the characteristics of the lesion received from the identification unit 25, and may superimpose the encircling line E on the basis image U1 using the display control unit 22, as shown in Fig. 14. Instead of the encircling line E, the boundary line of the portion that contributes to the identification may be superimposed on the basis image U1. Furthermore, the extraction unit 26 may form a heat map based on the basis image U1 in which the contribution rate of the portion that contributes to the identification by the identification unit 25 is represented by a shade of color or a difference in color. As shown in Fig. 15, the display control unit 22 can display the heat map U1H on the monitor 23 alongside the basis image U1.

[0054] Instead of displaying the heat map U1H next to the basis image U1, the basis image U1 and the heat map U1H may be displayed alternately, as shown in Figure 16, based on the user's input operation via the input device 29. In this way, by superimposing the encircling line E on the grounds image U1 or displaying the heat map U1H, the user can intuitively grasp the parts that contribute to the classification by the classification unit 25.

[0055] Furthermore, in each branch of the judgment procedure, if the extraction unit 26 extracts multiple basis images that contribute to the classification in the classification unit 25, the corresponding multiple basis images U1a and U1b can be displayed side by side near the branch, as shown in, for example, Figure 17. Alternatively, a plurality of basis images extracted by the extraction unit 26 may be displayed sequentially on the monitor 23 based on an input operation by the user via the input device 29. In this case, for example, as shown in Fig. 18, a page number m / n indicating which of the n basis images extracted by the extraction unit 26 the currently displayed basis image U1m is, i.e., the page number m / n indicating the page number, may be overlaid on the basis image U1m. In this way, by displaying multiple basis images sequentially, multiple basis images can be displayed even if the monitor 23 does not have a large display space, and by overlaying the page numbers, it becomes easier for the user to understand the multiple basis images. Furthermore, a plurality of basis images may be automatically displayed in sequence at regular time intervals without relying on a user's input operation.

[0056] As in the judgment procedure shown in Figure 4, the size of the lesion may be set as a judgment item in multiple branches, so as shown in Figure 19, the size of the lesion measured by the identification unit 25, such as the maximum diameter of the tumor and the aspect ratio of the mass, can be superimposed on the judgment procedure and displayed on the monitor 23. Alternatively, the tumor area and mass area may be displayed on the image, the user may modify the displayed area via input device 29, and identification unit 25 may correct the measurement values ​​by re-measuring the maximum diameter of the tumor and the aspect ratio of the mass based on the modified area. For example, when the user modifies the outline of the displayed area, identification unit 25 corrects the measurement values ​​of the maximum diameter of the tumor and the aspect ratio of the mass based on the modified area, and determination unit 27 re-determines the screening category based on the corrected measurement values. The corrected maximum diameter of the tumor and the aspect ratio of the mass are displayed on monitor 23, superimposed on the determination procedure.

[0057] Furthermore, for each judgment item set in the evaluation procedure, the identification unit 25 can calculate the proportion of the area in which the characteristics of the identified lesion appear to the entire area of ​​the lesion. For example, the identification unit 25 creates a three-dimensional image based on multiple ultrasound images of the same lesion in the subject that are taken and analyzed, and calculates, for example, the proportion of the area recognized as "coarsely structured" at the boundary of the lesion to the entire area of ​​the lesion. The calculated proportion can be displayed on the monitor 23, superimposed on the evaluation procedure, as shown in Figure 20. Instead of creating a three-dimensional image, for example, in the first frame, the length of the coarsely structured portion is 2 cm and the rest is 8 cm, in the second frame, the coarsely structured portion is 1.5 cm and the rest is 7 cm, etc., the length of the coarsely structured portion and the rest can be calculated for each frame, and the ratio of the sum of the lengths of the coarsely structured portion to the sum of the lengths of the rest in all frames can be calculated and displayed on monitor 23.

[0058] As described above, the shape of a tumor is classified according to whether or not the shape, including the boundary hyperechoic portion, has "waists" and "corners." For example, the irregular shape shown in Fig. 11 has both "waists" and "corners." To identify an irregular shape, it is desirable to confirm the number of "waists" and "corners." Therefore, the identification unit 25 can calculate the number of "waists" and "corners" that the lesion has from multiple ultrasound images, and display the number of "waists" and "corners" on the monitor 23, superimposed on the determination procedure, as shown in Fig. 21.

[0059] In this way, by displaying on the monitor 23 the size of the lesion, the proportion of the area in which the identified characteristics of the lesion appear to the entire area of ​​the lesion, and the number of "constrictions" and "corners" based on the analysis by the identification unit 25, the user can understand in more detail the basis for route selection at multiple branches in the judgment procedure.

[0060] In the above-described embodiment 1, as shown in FIG. 12, in step S1, the identification unit 25 identifies the characteristics of the lesion in a plurality of ultrasound images, and in step S2, the basis image that contributes to the identification of the characteristics is extracted, but this is not limited to this. For example, as shown in the flowchart of Figure 22, first, in step S6, a determination is made of all characteristic items pre-stored in the identification unit 25 for all of the multiple ultrasound images, and following this determination, in the subsequent step S7, at least one ultrasound image that best represents each individual characteristic item may be extracted as a basis image.

[0061] Once all characteristic items have been determined and the basis image extracted in this manner, the process proceeds to step S4, as in embodiment 1, where the determination unit 27 determines the examination category of the lesion area according to the determination procedure, and then in step S5, the display control unit 22 displays the determination procedure on the monitor 23, and the path taken when determining the examination category and the basis image are superimposed on the determination procedure.

[0062] [Embodiment 2] 23 shows the configuration of an ultrasonic diagnostic apparatus according to embodiment 2. This ultrasonic diagnostic apparatus has an apparatus main body 20A connected to an ultrasonic probe 10. In apparatus main body 20A, determination unit 27A and main body control unit 28A are used instead of determination unit 27 and main body control unit 28 in apparatus main body 20 of the ultrasonic diagnostic apparatus according to embodiment 1 shown in FIG. 1, and the other configuration is the same as that of apparatus main body 20 in embodiment 1.

[0063] The determination unit 27A includes an accuracy calculation unit 31 therein, and the accuracy calculation unit 31 is connected to the display control unit 22. A main body control unit 28A is connected to the image generation unit 21, the display control unit 22, the image memory 24, the identification unit 25, the extraction unit 26, and the determination unit 27A, and an input device 29 is connected to the main body control unit 28A. In addition, the transmission / reception circuit 12 of the ultrasound probe 10 is connected to the main body control unit 28A. The image generating unit 21, the display control unit 22, the identifying unit 25, the extracting unit 26, the determining unit 27A, and the main body control unit 28A constitute a processor 30A.

[0064] The accuracy calculation unit 31 applies the characteristics of the lesion identified by the identification unit 25 to the judgment items corresponding to each branch, and calculates the accuracy of route selection for each branch when selecting a route for the assessment procedure. The accuracy calculation in the accuracy calculation unit 31 can be performed using a determination model trained using a machine learning technique such as deep learning. The determination model is, for example, a trained model that has trained mammary gland regions (segmentation) in training ultrasound images of breasts.

[0065] For example, in the first branch B1 of the determination procedure shown in Fig. 13, the probability that the lesion corresponds to each of the three judgment items, the cystic pattern, the mixed pattern, and the solid pattern, is calculated by the probability calculation unit 31. Then, as shown in Fig. 24, the display control unit 22 displays on the monitor 23 the probability X% that the lesion corresponds to the cystic pattern, the probability Y% that the lesion corresponds to the mixed pattern, and the probability Z% that the lesion corresponds to the solid pattern, superimposed on the determination procedure. This allows the user to understand in more detail the basis for route selection at each branch in the determination procedure.

[0066] 13, if the lesion corresponds to at least one of a boundary hyperechoic image and a mammary gland boundary line rupture, it is determined to belong to screening categories 4 and 5. In this way, when multiple screening categories correspond to one branch, it is also possible to determine which of the corresponding multiple screening categories the lesion belongs to by comparing the accuracy of route selection calculated by the accuracy calculation unit 31 with a predetermined threshold value. For example, at branch B2, if the probability of at least one of a hyperechoic image of the boundary and a rupture of the mammary gland boundary line is below a predetermined threshold, it can be determined that it belongs to screening category 4, and if it is greater than the predetermined threshold, it can be determined that it belongs to screening category 5.

[0067] In the above-described first and second embodiments, the ultrasonic probe 10 has the transmitting / receiving circuit 12, but the device main body 20, 20A may also be configured to have the transmitting / receiving circuit 12. Furthermore, the device main body 20, 20A has the image generating unit 21, but the ultrasonic probe 10 may have the image generating unit 21. Furthermore, of the signal processing unit 41, DSC 42, and image processing unit 43 that make up the image generating unit 21 shown in FIG. 3, the ultrasonic probe 10 may have only the signal processing unit 41, and the device main body 20, 20A may have the DSC 42 and image processing unit 43. Furthermore, as the device main bodies 20 and 20A in the first and second embodiments, a stationary device main body can be used, or a compact device main body of a portable or handheld type can also be used.

[0068] In the above-mentioned embodiments 1 and 2, the examination category of the lesion in the breast is determined according to the judgment procedure stored in the judgment procedure memory 32, but this is not limited to this. By storing a judgment procedure for determining the examination category related to the thyroid gland in the judgment procedure memory 32, the examination category of the lesion in the thyroid gland can be determined in the same way according to a predetermined judgment procedure having multiple branches. Furthermore, by storing a determination procedure for determining not only the medical examination category but also the diagnostic category in the determination procedure memory 32, the present invention can be similarly applied to the determination of the diagnostic category.

[0069] JABTS defines diagnostic category IV as follows: Diagnostic Category I: Normal Diagnostic Category II: Normal or Inflammatory Cells Diagnostic category IIIa: Benign cells, but malignancy cannot be ruled out Diagnostic category IIIb: High probability of malignancy but benignity cannot be ruled out Diagnostic Category IV: Suspected malignancy Diagnostic Category V: Malignant

[0070] By using the ultrasound diagnostic device of the present invention, it becomes possible to determine the diagnostic category of a lesion in the mammary gland or thyroid gland from multiple ultrasound images and accurately understand the basis for the determination, regardless of the user's level of experience, just as with the screening category. [Explanation of symbols]

[0071] 10 ultrasound probe, 11 transducer array, 12 transmitting / receiving circuit, 13 pulser, 14 amplifier, 15 AD conversion unit, 16 beamformer, 20 device main body, 21 image generation unit, 22 display control unit, 23 monitor, 24 image memory, 25 identification unit, 26 extraction unit, 27, 27A judgment unit, 28, 28A main body control unit, 29 input device, 30, 30A processor, 31 accuracy calculation unit, 32 judgment procedure memory, 41 signal processing unit, 42 DSC, 43 image processing unit, B1, B2 bifurcation, M mass, N tumor, H boundary hyperechoic area, L1, L2 maximum length, L3 maximum width, W horizontal diameter, D vertical diameter, U1, U1a, U1b, U1m, U2 basis image, E encirclement, U1H heat map.

Claims

1. An ultrasound diagnostic device that determines a screening category or a diagnostic category of a lesion according to a predetermined determination procedure having multiple branches, a judgment procedure memory in which the judgment procedure is stored; an identification unit that identifies the characteristics of the lesion for the judgment items for route selection at the plurality of branches of the judgment procedure stored in the judgment procedure memory based on a plurality of ultrasound images of the same lesion; an extracting unit that extracts, as a basis image, at least one ultrasound image that contributes to the identification of the characteristics in the plurality of branches of the determination procedure by the identifying unit from the plurality of ultrasound images; a determination unit that determines the screening category or the diagnostic category of the lesion by applying the characteristics identified by the identification unit to the judgment items and selecting a path in the plurality of branches of the judgment procedure; The monitor and a display control unit that displays, on the monitor, a path in the determination procedure when the determination unit determines the examination category or the diagnostic category and the evidence image extracted by the extraction unit; Equipped with the display control unit displays the determination procedure on the monitor, and displays the basis image extracted by the extraction unit in each of the plurality of branches of the determination procedure on the monitor, positioned near the corresponding branch of the determination procedure; An ultrasound diagnostic apparatus in which the basis images extracted by the extraction unit in at least two branches out of the plurality of branches are different from each other.

2. The ultrasound diagnostic apparatus according to claim 1 , wherein the plurality of ultrasound images are images constituting a moving image of the lesion area.

3. 3. The ultrasonic diagnostic apparatus according to claim 1, wherein each of the plurality of ultrasonic images is an image of the entire or part of the lesion.

4. The ultrasound diagnostic apparatus according to claim 2 , wherein the plurality of ultrasound images are images thinned out from images constituting a moving image of the lesion, images interpolated, or images synthesized.

5. the extraction unit forms an encircling line in the basis image that encloses a portion that contributes to the identification of the property by the identification unit; The ultrasound diagnostic apparatus according to claim 1 , wherein the display control unit displays the encircling line superimposed on the basis image.

6. The ultrasound diagnostic apparatus according to claim 1 or 2, wherein when the extraction unit extracts a plurality of basis images for one branch, the display control unit displays the plurality of basis images side by side on the monitor.

7. an input device for a user to perform an input operation; The ultrasound diagnostic apparatus of claim 1 or 2, wherein when the extraction unit extracts multiple basis images for one branch, the display control unit sequentially displays the multiple basis images on the monitor based on input operations by the user via the input device.

8. The ultrasound diagnostic apparatus according to claim 7 , wherein the display control unit overlays a page number indicating which of the plurality of basis images the basis image corresponds to on the basis image displayed on the monitor.

9. the identification unit measures the size of the lesion; The ultrasound diagnostic apparatus according to claim 1 , wherein the display control unit displays the size measured by the identification unit on the monitor.

10. the identification unit calculates, for each of the judgment items, a ratio of an area in which the identified characteristic appears to an entire area of ​​the lesion; The ultrasound diagnostic apparatus according to claim 1 , wherein the display control unit displays the ratio calculated by the identification unit on the monitor.

11. the determination unit includes a probability calculation unit that calculates a probability of route selection at the plurality of branches of the determination procedure based on the characteristics of the lesion; The ultrasound diagnostic apparatus according to claim 1 , wherein the display control unit displays the accuracy calculated by the accuracy calculation unit on the monitor.

12. 12. The ultrasound diagnostic device of claim 11, wherein when a plurality of the screening categories or the diagnostic categories correspond to any of the plurality of branches of the judgment procedure, the judgment unit judges the screening category or the diagnostic category of the lesion by comparing the accuracy calculated by the accuracy calculation unit with a predetermined threshold value.

13. 3. The ultrasound diagnostic device according to claim 1, further comprising: an ultrasound probe; and an image generating unit configured to generate the plurality of ultrasound images of the same lesion by transmitting and receiving ultrasound beams to and from the subject using the ultrasound probe.

14. A method for controlling an ultrasound diagnostic apparatus that determines a screening category or a diagnostic category of a lesion according to a predetermined determination procedure having multiple branches, comprising: a step of identifying the characteristics of the lesion with respect to a judgment item for route selection at the plurality of branches of the judgment procedure based on a plurality of ultrasound images of the same lesion; extracting at least one ultrasound image that contributes to identifying the characteristic from the plurality of ultrasound images as a basis image; determining the screening category or the diagnostic category of the lesion by selecting a path at the plurality of branches by applying the identified characteristics to the judgment items; a step of displaying on a monitor a path in the determination procedure when the screening category or the diagnostic category is determined and the extracted evidence image; the displaying step includes displaying the judgment procedure on the monitor, and displaying the basis image extracted in each of the plurality of branches of the judgment procedure on the monitor in a position adjacent to the corresponding branch of the judgment procedure; A method for controlling an ultrasound diagnostic apparatus, wherein the basis images extracted in at least two of the plurality of branches are different from each other.

Images