Ultrasound diagnostic device and control method for ultrasound diagnostic device

Abstract

This ultrasonic diagnosis device is intended to be used for performing an ultrasonic test on the breast of a subject by an inspector, and is provided with: a voice acquisition sensor (3) for acquiring a voice during an ultrasonic test; a voice analysis unit (24) for analyzing the voice acquired by the voice acquisition sensor (3) to estimate the inspection position in the subject; and a body mark setting unit (25) for selecting one of left and right breast body marks on the basis of the inspection position in the subject which has been estimated by the voice analysis unit (24) and setting the selected breast body mark.

Description

[Technical Field]

[0001] The present invention relates to an ultrasonic diagnostic apparatus for examining the breast of a subject and a control method for an ultrasonic diagnostic apparatus. [Background Art]

[0002] Conventionally, examination of the breast of a subject has been performed by capturing an ultrasonic image using a so-called ultrasonic diagnostic apparatus. In the examination of the breast of a subject, in order to easily determine whether the captured ultrasonic image is of the left or right breast of the subject, a so-called body mark indicating the left breast or a body mark indicating the right breast is often set in association with the ultrasonic image. Moreover, such a body mark is often set manually by an examiner.

[0003] Generally, it is difficult to determine whether the ultrasonic image is captured from the left breast or the right breast of the subject only by checking the ultrasonic image. Therefore, for example, if an examiner mistakenly sets a body mark corresponding to the breast opposite to the actual breast of the subject, it is difficult to check the ultrasonic image and reset the body mark correctly after the examination. Accordingly, as disclosed in, for example, Patent Documents 1 to 3, techniques for automatically setting a body mark have been developed. Patent Document 1 discloses that position information of an ultrasonic probe is acquired using a magnetic sensor or the like, and a body mark indicating either the left or right breast is automatically set based on the acquired position information. Patent Document 2 discloses setting a body mark corresponding to the examination position of the subject based on an optical image of the subject. Patent Document 3 discloses that a body mark indicating either the left or right breast is set in association with an ultrasonic image based on information stored in a pre-captured X-ray image. [Prior Art Documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Unexamined Patent Publication No. 2021-166574 [Patent Document 2] Japanese Patent Publication No. 2015-226607 [Patent Document 3] Japanese Patent Publication No. 2012-135428 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] However, according to the technologies described in Patent Documents 1 to 3, it was sometimes difficult to easily introduce the equipment because it required expensive and complex devices.

[0006] This invention was made to solve the problems of the conventional methods, and aims to provide an ultrasound diagnostic device and a control method for the ultrasound diagnostic device that can accurately set body marks on the breast while being inexpensive and having a simple device configuration. [Means for solving the problem]

[0007] The above objective will be achieved through the following configuration. [1] An ultrasound diagnostic device for an examiner to perform an ultrasound examination on the breast of a subject, A sound acquisition sensor that acquires sound during ultrasound examination, A voice analysis unit estimates the examination location of the subject by analyzing the voice acquired by the voice acquisition sensor, The body mark setting unit selects and sets one of the left or right breast body marks based on the examination position of the subject estimated by the voice analysis unit. An ultrasound diagnostic device equipped with the following features. [2] The ultrasound diagnostic apparatus according to [1], wherein the sound analysis unit detects a series of motions of the ultrasound examination by analyzing the sound acquired by the sound acquisition sensor, and estimates the examination position based on the detected series of motions. [3] The ultrasound diagnostic apparatus according to [1] or [2], which is equipped with an input device that accepts input of either the left or right breast body mark by an operator prior to an ultrasound examination. [4] Equipped with a notification unit that notifies the inspector, The ultrasound diagnostic apparatus described in [3], wherein the notification unit notifies an error if the breast body mark selected by the body mark setting unit is different from the breast body mark input through the input device. [5] The ultrasound diagnostic apparatus according to [3], in which, if the breast body mark selected by the body mark setting unit is different from the breast body mark input through the input device, the body mark setting unit sets the breast body mark selected based on the examination position of the subject estimated by the voice analysis unit in place of the breast body mark input through the input device. [6] The ultrasound diagnostic apparatus according to any one of the items [1] to [5], wherein the voice analysis unit converts the voice acquired by the voice acquisition sensor into a string, extracts features related to the examination location from the converted string, calculates a first probability that the examination location is the left breast and a second probability that it is the right breast, and estimates the examination location based on the first and second probabilities. [7] The ultrasound diagnostic apparatus according to [6], wherein the voice analysis unit calculates a first probability and a second probability based on the respective prior probabilities corresponding to the specific examination sequence when there is a specific examination sequence for ultrasound examination of the left and right breasts. [8] The ultrasound diagnostic apparatus according to [6] or [7], wherein the voice analysis unit increases the weight of the calculation of the first and second probabilities based on the voice data when voice data including a conversation between the subject and the examiner in accordance with established guidelines is acquired by the voice acquisition sensor. [9] Ultrasound probe and, An image acquisition unit that acquires an ultrasound image of the subject's breast by transmitting and receiving an ultrasound beam using an ultrasound probe, A monitor that displays ultrasound images and An ultrasound diagnostic apparatus according to any one of items [1] to [8], comprising:

[10] The breast body mark selected by the body mark setting unit is displayed on the monitor along with the ultrasound image. [9]

[11] A method for controlling an ultrasound diagnostic device for an examiner to perform an ultrasound examination on the breast of a subject, We acquire audio during ultrasound examinations. By analyzing the acquired audio, the subject's examination location is estimated. Based on the estimated examination location of the subject, select and set one of the left or right breast body markers. A method for controlling an ultrasound diagnostic device. [Effects of the Invention]

[0008] According to the present invention, the ultrasound diagnostic device is an ultrasound diagnostic device for which an examiner performs an ultrasound examination on the breast of a subject, and comprises a sound acquisition sensor that acquires sound during the ultrasound examination, a sound analysis unit that estimates the examination position of the subject by analyzing the sound acquired by the sound acquisition sensor, and a body mark setting unit that selects and sets one of the left or right breast body marks based on the examination position of the subject estimated by the sound analysis unit. Therefore, it is possible to accurately set the breast body marks while having an inexpensive and simple device configuration. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing the configuration of an ultrasound diagnostic device according to an embodiment of the present invention. [Figure 2] This is a block diagram showing the configuration of the transmitting and receiving circuit in an embodiment of the present invention. [Figure 3] This is a block diagram showing the configuration of the image generation unit in an embodiment of the present invention. [Figure 4] This figure shows an example of a breast body mark representing the left breast in an embodiment of the present invention. [Figure 5] This figure shows an example of a breast body mark representing the right breast in an embodiment of the present invention. [Figure 6] This flowchart shows the operation of an ultrasound diagnostic device according to an embodiment of the present invention. [Figure 7] This is a flowchart showing the operation of setting breast body marks in an embodiment of the present invention. [Figure 8]It is a flowchart showing the operation of speech analysis according to an embodiment of the present invention. [Figure 9] It is a flowchart showing the operation of an ultrasonic diagnostic apparatus according to a modification of the embodiment of the present invention. MODE FOR CARRYING OUT THE INVENTION

[0010] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. The following description of constituent features is made based on representative embodiments of the present invention, but the present invention is not limited to such embodiments. In the present specification, a numerical range expressed using "~" means a range that includes the numerical values described before and after "~" as the lower limit and the upper limit. In the present specification, the terms "identical" and "same" shall include error ranges generally accepted in the technical field.

[0011] Embodiment FIG. 1 shows the configuration of an ultrasonic diagnostic apparatus according to an embodiment of the present invention. The ultrasonic diagnostic apparatus includes an ultrasonic probe 1, an apparatus main body 2 connected to the ultrasonic probe 1, and a sound acquisition sensor 3 connected to the apparatus main body 2.

[0012] The ultrasonic probe 1 has a transducer array 11. A transmission / reception circuit 12 is connected to the transducer array 11.

[0013] The apparatus main body 2 has an image generation unit 21 connected to the transmission / reception circuit 12 of the ultrasonic probe 1. A display control unit 22 and a monitor 23 are sequentially connected to the image generation unit 21. The apparatus main body 2 also has a speech analysis unit 24 connected to the sound acquisition sensor 3. A body mark setting unit 25 is connected to the speech analysis unit 24. An image memory 26 and a notification unit 31 are connected to the image generation unit 21 and the body mark setting unit 25. A measurement unit 27 is connected to the image memory 26. A measurement result memory 28 and the display control unit 22 are connected to the measurement unit 27. The notification unit 31 is connected to the display control unit 22.

[0014] Furthermore, a control unit 29 is connected to the transmitting / receiving circuit 12, image generation unit 21, display control unit 22, sound analysis unit 24, body mark setting unit 25, image memory 26, measurement unit 27, measurement result memory 28, and notification unit 31. In addition, an input device 30 is connected to the body mark setting unit 25 and the control unit 29.

[0015] Furthermore, the image acquisition unit 41 is composed of the transmitting and receiving circuit 12 of the ultrasonic probe 1 and the image generation unit 21 of the device body 2. In addition, the processor 43 for the device body 2 is composed of the image generation unit 21, display control unit 22, sound analysis unit 24, body mark setting unit 25, measurement unit 27, control unit 29, and notification unit 31 of the device body 2.

[0016] The transducer array 11 of the ultrasonic probe 1 has a plurality of ultrasonic transducers arranged in one or two dimensions. Each of these ultrasonic transducers transmits ultrasound according to a drive signal supplied from the transmitting / receiving circuit 12, and also receives ultrasonic echoes from the subject and outputs a signal based on the ultrasonic echoes. Each ultrasonic transducer is constructed by forming electrodes at both ends of a piezoelectric body made of, for example, a piezoelectric ceramic represented by PZT (Lead Zirconate Titanate), a polymer piezoelectric element represented by PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal represented by PMN-PT (Lead Magnesium Niobate-Lead Titanate).

[0017] The transmitting / receiving circuit 12 transmits ultrasonic waves from the transducer array 11 and generates a sound line signal based on the received signal acquired by the transducer array 11, under the control of the control unit 29. As shown in Figure 2, the transmitting / receiving circuit 12 includes a pulser 51 connected to the transducer array 11, and an amplifier 52, an AD (Analog to Digital) converter 53, and a beamformer 54 connected sequentially in series from the transducer array 11.

[0018] The pulser 51 includes, for example, multiple pulse generators, and based on a transmission delay pattern selected according to a control signal from the control unit 29, it supplies each drive signal to the multiple ultrasonic transducers of the transducer array 11, adjusting the delay amount, so that the ultrasonic waves transmitted from the transducers form an ultrasonic beam. In this way, when a pulsed or continuous wave voltage is applied to the electrodes of the ultrasonic transducers of the transducer array 11, the piezoelectric material expands and contracts, generating pulsed or continuous wave ultrasonic waves from each ultrasonic transducer, and an ultrasonic beam is formed from the combined wave of these ultrasonic waves.

[0019] The transmitted ultrasonic beam is reflected from a target, such as a part of the subject, and propagates toward the transducer array 11 of the ultrasonic probe 1. The ultrasonic echo propagating toward the transducer array 11 is received by each ultrasonic transducer that makes up the transducer array 11. At this time, each ultrasonic transducer that makes 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 amplification unit 52.

[0020] The amplification unit 52 amplifies the signals input from each ultrasonic transducer constituting the transducer array 11 and transmits the amplified signals to the AD conversion unit 53. The AD conversion unit 53 converts the signals transmitted from the amplification unit 52 into digital received data. The beamformer 54 performs so-called receive focus processing by adding each received data received from the AD conversion unit 53 with a corresponding delay. Through this receive focus processing, each received data converted by the AD conversion unit 53 is added in phase and a sound ray signal with a focused ultrasonic echo is obtained.

[0021] As shown in Figure 3, the image generation unit 21 has a configuration in which a signal processing unit 55, a DSC (Digital Scan Converter) 56, and an image processing unit 57 are connected in series in sequence.

[0022] The signal processing unit 55 receives the sound line signal from the transmitting / receiving circuit 12, applies a sound velocity value set by the control unit 29 to correct for attenuation due to distance according to the depth of the ultrasonic reflection position, and then performs envelope detection processing to generate a B-mode image signal, which is tomographic image information about the tissue within the subject.

[0023] The DSC56 converts the B-mode image signal generated by the signal processing unit 55 into an image signal that follows the scanning method of a normal television signal (raster conversion). The image processing unit 57 performs various necessary image processing, such as gradation processing, on the B-mode image signal input from the DSC 56, and then sends the B-mode image signal to the display control unit 22 and the image memory 26. Hereafter, the B-mode image signal processed by the image processing unit 57 will be referred to as the ultrasound image.

[0024] The display control unit 22, under the control of the control unit 29, performs predetermined processing on the ultrasound image etc. generated by the image generation unit 21 and displays it on the monitor 23. The monitor 23 displays various information under the control of the display control unit 22. The monitor 23 may include, for example, a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).

[0025] The voice acquisition sensor 3 includes a microphone and acquires sound during ultrasound examination as an electrical signal. The sound during ultrasound examination refers to the sound including the conversation between the examiner and the subject during the ultrasound examination. The voice acquisition sensor 3 sends the acquired sound information to the voice analysis unit 24.

[0026] The voice analysis unit 24 estimates the examination position of the subject by the examiner by analyzing the voice acquired by the voice acquisition sensor 3. The examination position refers to the position where the ultrasound probe 1 is in contact with the subject's body surface during an ultrasound examination. In this process, the voice analysis unit 24, for example, converts the voice acquired by the voice acquisition sensor 3 into a string of characters, extracts features related to the examination position from the converted string of characters, calculates a first probability that the examination position is the subject's left breast and a second probability that it is the right breast, and estimates the examination position based on the calculated first and second probabilities.

[0027] The speech analysis unit 24 can perform noise removal and speech distortion correction on the information representing the speech by performing so-called cepstrum analysis, etc., before converting the speech into a string.

[0028] As a method for converting speech to text by the speech analysis unit 24, for example, the method described in U.S. Patent Application Publication No. 2002 / 0059069, or known statistical methods such as those described in "Frederick Jelinek (1998), "Statistical Methods for Speech Recognition", MIT Press, ISBN 0-262-10066-5", can be used. When using such statistical methods, for example, the so-called Bayes' theorem can be used to calculate the probabilities of multiple candidate text strings contained in the speech acquired by the speech acquisition sensor 3, and by taking into account the plausibility of the text strings based on a language model, the text string with the highest probability can be selected from among the candidate text strings, thereby converting the speech to text.

[0029] The speech analysis unit 24, when calculating candidate strings from speech, analyzes, for example, the frequency components and temporal changes of sound waves in the speech, extracts feature quantities one by one from the speech waveform, and identifies phonemes corresponding to the feature quantities by performing so-called pattern matching on the extracted feature quantities. For the pattern matching method, known algorithms such as Gaussian Mixture Model-Hidden Markov Model and Deep Neural Network-Hidden Markov Model can be used.

[0030] Furthermore, the speech analysis unit 24 can, for example, pre-store dictionary data containing multiple words, and construct words from phonemes by performing pattern matching between identified phonemes and multiple words included in the dictionary data. In this process, the speech analysis unit 24 can construct words using language models such as N-grams or recurrent neural networks.

[0031] Furthermore, the voice analysis unit 24 pre-stores multiple strings related to the examination of the right breast and multiple strings related to the examination of the left breast. By comparing these pre-stored strings with the strings obtained by converting the voice using pattern matching or the like, it extracts features related to the examination location consisting of strings related to the examination of either the left or right breast. Examples of strings related to the examination of the left breast include "left," "left breast," and "left arm." Examples of strings related to the examination of the right breast include "right," "right breast," and "right arm."

[0032] Furthermore, the voice analysis unit 24 has an initial value for the first probability that the examination location is the left breast (prior probability for the first probability) and an initial value for the second probability that it is the right breast (prior probability for the second probability), and weights the first and second probabilities based on the number of strings representing features related to the examination location that are extracted. If the prior probabilities for the first probability and the prior probabilities for the second probability are both 50%, and a certain number of strings related to the left breast are extracted more than the strings related to the right breast, the voice analysis unit 24 can add a certain probability value to the prior probability for the first probability and subtract a certain probability value from the prior probability for the second probability. As a result, the voice analysis unit 24 can calculate the first probability as 65% and the second probability as 35%, for example.

[0033] The voice analysis unit 24 has a predetermined probability threshold, and can identify the left breast as the examination location when the first probability is equal to or greater than the probability threshold, and can identify the right breast as the examination location when the second probability is equal to or greater than the probability threshold.

[0034] Furthermore, the voice analysis unit 24 can detect a series of actions during an ultrasound examination by analyzing the audio, and estimate the examination position based on the detected sequence of actions. In this process, the voice analysis unit 24 can pre-store multiple examination contents, such as "examination start," "examination of left breast," "examination of right breast," "switching from examination of left breast to right breast," "switching from examination of right breast to left breast," and "examination end," and calculate the probability that those examination contents are currently being performed based on specific strings of characters contained in the text identified from the audio, thereby calculating a first probability and a second probability.

[0035] In this process, the voice analysis unit 24, for example as shown in Table 1, identifies phrases such as "We will begin the examination," "We will start with the left breast," "We will now begin the examination of the right breast," "Please raise your right hand," and "We will end the examination" from the voice, and then extracts specific strings such as "examination," "breast," "left," "right," "start," "raise hand," and "end" from these phrases. Here, in Table 1, "1" indicates that the string was extracted from the identified phrase, and "0" indicates that the string was not extracted from the identified phrase.

[0036] [Table 1]

[0037] In this process, the speech analysis unit 24 can select sentences related to the breast examination of the subject from among multiple sentences identified from the speech by using a so-called topic model, such as Probabilistic Latent Semantic Analysis (PLSA), as a trained model for so-called machine learning or deep learning. The speech analysis unit 24 can also select sentences related to the breast examination of the subject using a language model such as a recurrent neural network.

[0038] The voice analysis unit 24 calculates the probability that the following examination procedures are currently being performed, based on the extracted specific strings, for example as shown in Table 2: "Start of examination," "Examination of left breast," "Examination of right breast," "Switching from examination of left breast to right breast," "Switching from examination of right breast to left breast," and "End of examination." The voice analysis unit 24 can calculate the probability of each examination procedure in such a way that, for example, the probability of an examination procedure with more associated strings is higher.

[0039] [Table 2]

[0040] For example, if the phrase "We will begin with the left breast" is identified from the audio, the strings "breast" and "left" are extracted, resulting in a relatively high probability of 90% that the examination is "examining the left breast." Similarly, if the phrase "We will now begin the examination of the right breast" is identified from the audio, the strings "examination," "breast," "right," and "start" are extracted, resulting in a relatively high probability of 80% that the examination is "examining the right breast" and "switching from the left breast to the right breast," which are related to these strings.

[0041] The voice analysis unit 24 can, for example, identify the left breast as the examination location if the examination content "examining the left breast" is above a probability threshold, and can also identify the right breast as the examination location if the examination content "examining the right breast" is above a probability threshold.

[0042] Furthermore, ultrasound examinations are generally performed in accordance with guidelines established by academic societies and hospitals. The voice analysis unit 24 can, for example, pre-store multiple strings of characters that conform to established guidelines for ultrasound examinations of a subject's breast, and when voice data including dialogue between the subject and the examiner that conforms to the guidelines is acquired by the voice acquisition sensor 3, it can increase the weight given to the calculation of the first and second probabilities based on that voice data.

[0043] For example, if the guideline "For large breasts, have the patient raise their upper arm above their head" is stored, and the phrase "Please raise your right hand" is identified from the voice, the voice analysis unit 24 can increase the weight of the calculation of the second probability, such as setting the second probability that the examination location is the right breast to 90%. This allows for a more accurate calculation of the first and second probabilities in breast ultrasound examinations performed in accordance with guidelines.

[0044] Furthermore, hospitals and other medical facilities often have a specific order for ultrasound examinations of the left and right breasts. The voice analysis unit 24 can, for example, pre-store a specific order for ultrasound examinations of the left and right breasts, set prior probabilities for a first probability and a second probability based on the stored order, and calculate the first and second probabilities based on their respective prior probabilities. For example, if an examination order of performing an examination of the right breast after the left breast is stored, and neither breast has been examined yet, the voice analysis unit 24 sets the prior probability for the first probability that the examination location is the left breast to be higher than the prior probability for the second probability. Also, for example, if an examination order of performing an examination of the right breast after the left breast is stored, and only the left breast has been examined, the voice analysis unit 24 sets the prior probability for the second probability that the examination location is the right breast to be higher than the prior probability for the first probability. This allows for more accurate calculation of the first and second probabilities in breast ultrasound examinations performed according to a specific examination sequence.

[0045] The body mark setting unit 25 selects and sets one of the left or right breast body marks based on the subject's examination position estimated by the voice analysis unit 24. The body mark setting unit 25 can also set a breast body mark specified by the examiner via the input device 30. Generally, breast body marks known include the breast body mark 71L that mimics the subject's left breast, as shown in Figure 4, and the breast body mark 71R that mimics the subject's right breast, as shown in Figure 5.

[0046] The breast body mark 71L schematically represents the left breast as seen from the front, and has a circular breast region BR and a roughly triangular axillary region 73 representing the armpit and extending diagonally upward from the breast region BR. The breast region BR is divided into four regions: the inner upper region A, the inner lower region B, the outer upper region C, and the outer lower region D, and the axillary region 73 is connected to the upper left of the outer upper region C.

[0047] Breast body mark 71R schematically represents the right breast as seen from the front, and is a horizontally inverted version of breast body mark 71L, which represents the left breast.

[0048] The breast body marks 71L and 71R set by the body mark setting unit 25 are sent to the image memory 26 and the notification unit 31.

[0049] The image memory 26 stores the ultrasound images generated by the image generation unit 21 and the breast body marks 71L and 71R set by the body mark setting unit 25, linked together under the control of the control unit 29.

[0050] For example, the image memory 26 can be a recording medium such as flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), FD (Flexible Disk), MO disk (Magneto-Optical disk), 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).

[0051] The measurement unit 27, under the control of the control unit 29, reads the ultrasound image stored in the image memory 26 and performs measurements of the subject at the examination location corresponding to the ultrasound image based on the read ultrasound image. The measurement unit 27 can measure, for example, the dimensions of anatomical structures within the breast as seen in the ultrasound image, based on the examiner's input via the input device 30.

[0052] The measurement result memory 28 stores the results measured by the measurement unit 27, linked to the ultrasound image used for the measurement, under the control of the control unit 29. For the measurement result memory 28, recording media such as flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, or USB memory can be used.

[0053] The input device 30 receives input operations from the inspector and sends the input information to the control unit 29. The input device 30 is composed of, for example, a keyboard, mouse, trackball, touchpad, and touch panel, or other devices for the inspector to perform input operations.

[0054] The notification unit 31 provides notification to the examiner. In particular, if the breast body marks 71L and 71R that the body mark setting unit 25 automatically set based on the examination position estimated by the voice analysis unit 24 differ from the body marks entered by the examiner via the input device 30, the notification unit 31 notifies the examiner of the error by displaying a message on the monitor 23 or by other means.

[0055] The processor 43 of the main body 2, which includes an image generation unit 21, a display control unit 22, a sound analysis unit 24, a body mark setting unit 25, a measurement unit 27, a control unit 29, and a notification unit 31, is composed of a CPU (Central Processing Unit) and a control program for causing the CPU to perform various processes. However, it 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 thereof.

[0056] Furthermore, the image generation unit 21, display control unit 22, sound analysis unit 24, body mark setting unit 25, measurement unit 27, control unit 29, and notification unit 31 of the processor 43 can be partially or entirely integrated into a single CPU or the like.

[0057] Next, an example of the operation of the ultrasound diagnostic device according to the embodiment will be explained using the flowchart in Figure 6.

[0058] First, in step S1, the breast body mark 71L or 71R is automatically set based on the audio during the examination. This process in step S1 consists of the processes in steps S11 to S14, as shown in the flowchart in Figure 7.

[0059] In step S11, the voice acquisition sensor 3 acquires audio, including the conversation between the examiner and the subject during the examination. In step S12, the voice analysis unit 24 analyzes the voice acquired by the voice acquisition sensor 3 in step S11 during the examination to calculate a first probability that the current examination location is the left breast and a second probability that the current examination location is the right breast. Step S12 consists of steps S21 to S23, as shown in the flowchart in Figure 8.

[0060] In step S21, the speech analysis unit 24 converts the speech acquired in step S11 into a string. In doing so, the speech analysis unit 24 may use, for example, the method described in U.S. Patent Application Publication No. 2002 / 0059069, or known statistical methods such as those described in "Frederick Jelinek (1998), "Statistical Methods for Speech Recognition", MIT Press, ISBN 0-262-10066-5".

[0061] In step S22, the voice analysis unit 24 extracts a specific string representing a feature related to the examination location from the string obtained in step S21. At this time, the voice analysis unit 24 has pre-stored, for example, multiple strings related to the examination of the right breast and multiple strings related to the examination of the left breast, and can extract a specific string by comparing these pre-stored strings with the string obtained by converting the voice using pattern matching or the like.

[0062] In step S23, the voice analysis unit 24 calculates a first probability that the examination location is the left breast and a second probability that the examination location is the right breast, based on the specific string extracted in step S22. The voice analysis unit 24 stores prior probabilities for the first probability and the second probability, and weights the first and second probabilities based on the number of strings representing features related to the extracted examination location. For example, the voice analysis unit 24 can weight each prior probability such that it increases the first probability and decreases the second probability if a certain number of strings related to the left breast are extracted compared to the strings related to the right breast. Also, the voice analysis unit 24 can weight each prior probability such that it increases the second probability and decreases the first probability if a certain number of strings related to the right breast are extracted compared to the strings related to the left breast.

[0063] By performing the processes in steps S21 to S23 in this manner, the process in step S12 is completed.

[0064] In the subsequent step S13, the voice analysis unit 24 estimates whether the examination location is the left breast or the right breast based on the first and second probabilities calculated in step S12. The voice analysis unit 24 has a predetermined probability threshold, and for example, it can identify the left breast as the examination location when the first probability is equal to or greater than the probability threshold, and identify the right breast as the examination location when the second probability is equal to or greater than the probability threshold.

[0065] In step S14, the body mark setting unit 25 sets one of the left or right breast body marks 71L and 71R based on the inspection position estimated in step S13.

[0066] In this way, step S1 automatically and accurately sets the breast body mark 71L or 71R based on the audio during the ultrasound examination. Furthermore, it does not require an expensive and complex device configuration to estimate the examination position. For example, despite the inexpensive and simple device configuration, the examiner does not need to manually set the breast body mark 71L or 71R, preventing the examiner from setting the wrong breast body mark 71L or 71R. Once the process in step S1 is completed, the process proceeds to step S2.

[0067] In step S2, the control unit 29 determines whether or not sound has been acquired by the sound acquisition sensor 3. The control unit 29 can determine that sound has been acquired by the sound acquisition sensor 3 if the sound analysis unit 24 receives sound including the conversation between the examiner and the subject from the sound acquisition sensor 3, and can determine that sound has not been acquired by the sound acquisition sensor 3 if the sound analysis unit 24 does not receive sound including the conversation between the examiner and the subject from the sound acquisition sensor 3.

[0068] If it is determined in step S2 that voice has been acquired by the voice acquisition sensor 3, the process proceeds to step S3. In step S3, the voice analysis unit 24 analyzes the voice acquired in step S2 and converts it into a string, in the same manner as in step S11. In step S4, the voice analysis unit 24 estimates the inspection position based on the string obtained in step S3, in the same manner as in step S12.

[0069] In step S5, the body mark setting unit 25 determines whether the inspection position estimated in step S4 corresponds to the current breast body mark 71L or 71R set in step S1. If it is determined that the inspection position estimated in step S4 corresponds to the current breast body mark 71L or 71R and is compatible with the breast body mark 71L or 71R, the process proceeds to step S6.

[0070] In step S6, the ultrasound probe 1 scans the subject's breast, and an ultrasound image representing a tomographic view of the breast is acquired. At this time, the transmitting / receiving circuit 12 generates an acoustic signal by performing so-called reception focus processing under the control of the control unit 29. The acoustic signal generated by the transmitting / receiving circuit 12 is sent to the image generation unit 21. The image generation unit 21 generates an ultrasound image using the acoustic signal sent from the transmitting / receiving circuit 12. The ultrasound images acquired in this manner are sent to the display control unit 22 and the image memory 26.

[0071] In step S7, the ultrasound image acquired in step S6 and the breast body mark 71L or 71R set in step S1 are displayed on the monitor 23. The ultrasound image acquired in step S6 and the breast body mark 71L or 71R set in step S1 are linked to each other and stored in the image memory 26.

[0072] In step S8, the control unit 29 determines whether or not to terminate the ultrasound examination. For example, if the examiner inputs an instruction to terminate the ultrasound examination via the input device 30, the control unit 29 determines to terminate the current ultrasound examination. Alternatively, if the examiner does not input an instruction to terminate the ultrasound examination via the input device 30, the control unit 29 determines to continue the current examination.

[0073] If it is determined in step S8 to continue the ultrasound examination, the process returns to step S2. Thereafter, as long as it is determined in step S2 that sound has been acquired, the estimated examination position is determined to match the current breast body mark 71L or 71R, and it is determined in step S8 to continue the examination, the process from step S2 to step S8 is repeated. In this repetition of steps S2 to step S8, the examiner continues the ultrasound examination while moving the ultrasound probe 1 over the subject.

[0074] Furthermore, if, in step S5, the examiner moves the examination area of ​​the subject from one breast to the other, and it is determined that the examination position estimated in step S4 does not match the breast body mark 71L or 71R set in step S1, the process proceeds to step S9.

[0075] In step S9, the body mark setting unit 25 changes to the breast body mark 71L or 71R corresponding to the examination position estimated in step S4. This ensures that breast body marker 71L or 71R, corresponding to the current examination position, is correctly set. Once step S9 is complete, proceed to step S6.

[0076] Furthermore, if the control unit 29 determines in step S2 that the voice acquisition sensor 3 has not acquired any sound, the processing in steps S3 to S5 and step S9 is skipped, and the process proceeds to step S6.

[0077] In step S8, if the control unit 29 determines that the ultrasound examination is complete, the operation of the ultrasound diagnostic device according to the flowchart in Figure 6 is terminated.

[0078] As described above, according to the ultrasound diagnostic apparatus of the embodiment of the present invention, the sound analysis unit 24 analyzes the sound acquired by the sound acquisition sensor 3 during the ultrasound examination to estimate whether the current examination position is on the left or right breast of the subject, and the body mark setting unit 25 automatically sets the breast body mark 71L or 71R based on the estimated examination position. Therefore, despite the inexpensive and simple device configuration, the breast body mark 71L or 71R can be accurately set.

[0079] Although the image generation unit 21 is described as being provided in the main body 2 of the device, it can also be provided in the ultrasonic probe 1 instead.

[0080] Furthermore, although it is explained that the voice acquisition sensor 3 is provided in the ultrasound diagnostic apparatus independently of the ultrasound probe 1 and the main unit 2, it can be attached to the ultrasound probe 1 or to the main unit 2. In addition, the voice acquisition sensor 3 can be attached, for example, to headphones and earphones worn by the examiner.

[0081] Furthermore, although it is explained that breast body marks 71L or 71R are automatically set in step S1, breast body marks 71L or 71R can also be manually entered by the examiner, for example, by selecting breast body marks 71L or 71R via the input device 30. In this case, if it is determined in step S5 that the examination position estimated in step S4 does not match the breast body mark 71L or 71R manually entered in step S1, then in step S9, breast body mark 71L or 71R corresponding to the examination position estimated in step S4 is set. Therefore, even if breast body marks 71L or 71R are manually entered in step S1, breast body marks 71L or 71R are accurately set.

[0082] Furthermore, the flowchart in Figure 6 can also be modified to include a measurement process performed by the measurement unit 27. For example, after the ultrasound image and breast body mark 71L or 71R are displayed on the monitor 23 and stored in the image memory 26 in step S7, the measurement unit 27 can perform the measurement. In this case, the measurement unit 27 reads the ultrasound image saved in step S7 from the image memory 26 and measures the dimensions of anatomical structures in the ultrasound image based on the examiner's input via the input device 30. The measurement results obtained by the measurement unit 27 in this manner are stored in the measurement result memory 28.

[0083] Furthermore, if breast body marks 71L or 71R are manually entered by the examiner and the estimated examination position does not match the set breast body mark 71L or 71R, the examiner can be notified of an error. This embodiment will be explained using the flowchart in Figure 9. The flowchart in Figure 9 shows the operation in which step S31 is performed instead of step S1, step S32 is performed instead of step S5, and step S33 is performed instead of step S9 in the flowchart in Figure 6. Note that steps S2 to S4 and steps S6 to S8 in the flowchart in Figure 9 are the same as steps S2 to S4 and steps S6 to S8 in the flowchart in Figure 6, so a detailed explanation of these processes will be omitted.

[0084] First, in step S31, the breast body mark 71L or 71R is entered by the examiner through the input device 30. In the following step S2, the control unit 29 determines whether or not sound has been acquired during the ultrasound examination by the sound acquisition sensor 3. If it is determined in step S2 that sound has been acquired, the process proceeds to step S3.

[0085] In step S3, the voice analysis unit 24 analyzes the voice acquired in step S2 and calculates a first probability that the examination location is the left breast and a second probability that the examination location is the right breast. In step S4, the voice analysis unit 24 estimates the current inspection location based on the first and second probabilities calculated in step S3.

[0086] In the subsequent step S32, the control unit 29 determines whether the inspection position estimated in step S4 matches the breast body mark 71L or 71R entered by the inspector in step S31. If it is determined in step S32 that the current inspection position matches the breast body mark 71L or 71R entered in step S31, the unit proceeds to step S6; otherwise, it proceeds to step S33.

[0087] In step S33, the notification unit 31 notifies the examiner of the error by displaying a message on the monitor 23. By confirming the error notification, the examiner can reset the correct breast body mark 71L or 71R to match the current examination position. This ensures that the breast body mark 71L or 71R is accurately set to match the examination position. Once the process in step S33 is completed, the operation of the ultrasound diagnostic device according to the flowchart in Figure 9 is finished.

[0088] Here, the notification unit 31 can also notify the examiner of an error by means other than displaying a message on the monitor 23. For example, if the ultrasound diagnostic device is equipped with a speaker (not shown), the notification unit 31 can notify the examiner of an error by emitting a sound from the speaker. Also, for example, if the ultrasound diagnostic device is equipped with a lamp (not shown), the notification unit 31 can notify the examiner of an error by turning on or flashing the lamp. [Explanation of symbols]

[0089] 1 Ultrasound probe, 2 Main unit, 3 Sound acquisition sensor, 11 Transducer array, 12 Transmit / receive circuit, 21 Image generation unit, 22 Display control unit, 23 Monitor, 24 Sound analysis unit, 25 Body mark setting unit, 26 Image memory, 27 Measurement unit, 28 Measurement result memory, 29 Control unit, 30 Input device, 31 Notification unit, 41 Image acquisition unit, 43 Processor, 51 Pulsar, 52 Amplifier unit, 53 AD conversion unit, 54 Beamformer, 55 Signal processing unit, 56 DSC, 57 Image processing unit, 71L, 71R Breast body mark, 73 Axillary region, A Inner upper region, B Inner lower region, C Outer upper region, D Outer lower region.

Claims

1. An ultrasound diagnostic device for an examiner to perform an ultrasound examination on the breast of a subject, A sound acquisition sensor that acquires sound during the ultrasound examination, A voice analysis unit converts the voice acquired by the voice acquisition sensor into a string, extracts features related to the subject's examination location from the converted string, calculates a first probability that the examination location is the left breast and a second probability that it is the right breast, and estimates the examination location based on the first and second probabilities. A body mark setting unit selects and sets one of the left or right breast body marks based on the examination position of the subject estimated by the voice analysis unit. An ultrasound diagnostic device equipped with the following features.

2. The ultrasound diagnostic apparatus according to claim 1, wherein the sound analysis unit detects a series of operational transitions of the ultrasound examination by analyzing the sound acquired by the sound acquisition sensor, and estimates the examination position based on the detected series of operational transitions.

3. The ultrasound diagnostic apparatus according to claim 1 or 2, further comprising an input device that accepts input of either the left or right breast body marks by an input operation by the examiner prior to the ultrasound examination.

4. The system includes a notification unit that notifies the inspector, The ultrasound diagnostic apparatus according to claim 3, wherein the notification unit notifies an error if the breast body mark selected by the body mark setting unit is different from the breast body mark input through the input device.

5. The ultrasound diagnostic apparatus according to claim 3, in which, if the breast body mark selected by the body mark setting unit is different from the breast body mark input through the input device, the body mark setting unit sets the breast body mark selected based on the examination position of the subject estimated by the voice analysis unit in place of the breast body mark input through the input device.

6. The ultrasound diagnostic apparatus according to claim 1, wherein the sound analysis unit calculates the first probability and the second probability based on the respective prior probabilities corresponding to the specific examination sequence when there is a specific examination sequence for ultrasound examination of the left and right breasts.

7. The ultrasound diagnostic apparatus according to claim 1, wherein the voice analysis unit increases the weight of the calculation of the first and second probabilities based on the voice data when voice data including a conversation between the subject and the examiner in accordance with established guidelines is acquired by the voice acquisition sensor.

8. Ultrasound probe and An image acquisition unit that acquires an ultrasound image of the subject's breast by transmitting and receiving an ultrasound beam using the ultrasound probe, The monitor that displays the ultrasound image and An ultrasound diagnostic apparatus according to claim 1 or 2, comprising:

9. The ultrasound diagnostic apparatus according to claim 8, wherein the breast body mark selected by the body mark setting unit is displayed on the monitor together with the ultrasound image.

10. A method for controlling an ultrasound diagnostic device used by an examiner to perform an ultrasound examination on the breast of a subject, During the ultrasound examination, the sound is acquired. The acquired audio is converted into a string, features related to the subject's examination location are extracted from the converted string, a first probability that the examination location is the left breast and a second probability that it is the right breast are calculated, and the examination location is estimated based on the first and second probabilities. Based on the estimated examination position of the subject, one of the left or right breast body marks is selected and set. A method for controlling an ultrasound diagnostic device.

Images