JP-7856030-B2 - Programs, ultrasound diagnostic equipment, ultrasound diagnostic systems, imaging diagnostic equipment, and training equipment.

Inventors

• 松本 洋日
• 武田 義浩

Assignees

• コニカミノルタ株式会社

Dates

Publication Date

20260511

Application Date

20230314

Claims (16)

1. A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, A program that enables a computer to implement an output function that outputs an inference result associated with the detection target from a second ultrasonic image data based on a received signal from an ultrasonic probe, using a machine learning model trained with training data including the following: The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap . The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular pericardial boundary, The second region information is the region information of the valve annulus end. program.
2. A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, A program that enables a computer to implement an output function that outputs an inference result associated with the detection target from a second ultrasonic image data based on a received signal from an ultrasonic probe, using a machine learning model trained with training data including the following: The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. program.
3. An ultrasonic probe that transmits and receives ultrasound waves to and from a subject, An inference unit that uses a machine learning model to output an inference result associated with the detection target from a second ultrasonic image data based on the received signal received by the ultrasonic probe, An ultrasound diagnostic device having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular pericardial boundary, The second region information is the region information of the valve annulus end. Ultrasound diagnostic equipment.
4. An ultrasonic probe that transmits and receives ultrasound waves to and from a subject, An inference unit that uses a machine learning model to output an inference result associated with the detection target from a second ultrasonic image data based on the received signal received by the ultrasonic probe, An ultrasound diagnostic device having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinate associated with the detection target and the confidence level, The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. Ultrasound diagnostic equipment.
5. An inference unit that uses a machine learning model to generate a confidence score associated with the detection target from a second ultrasonic image data based on the received signal from the ultrasonic probe, and obtains the coordinates of the maximum confidence score based on the confidence score. An ultrasound diagnostic device having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular membrane boundary, The second region information is the region information of the valve annulus end. Ultrasound diagnostic equipment.
6. An inference unit that uses a machine learning model to generate a confidence score associated with the detection target from a second ultrasonic image data based on the received signal from the ultrasonic probe, and obtains the coordinates of the maximum confidence score based on the confidence score. An ultrasound diagnostic device having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. Ultrasound diagnostic equipment.
7. An ultrasonic probe that transmits and receives ultrasound waves to and from a subject, An output unit that uses a machine learning model to output an inference result associated with the detection target from a second ultrasonic image data based on the received signal received by the ultrasonic probe, An ultrasound diagnostic system having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular membrane boundary, The second region information is the region information of the valve annulus end. Ultrasound diagnostic system.
8. An ultrasonic probe that transmits and receives ultrasound waves to and from a subject, An output unit that uses a machine learning model to output an inference result associated with the detection target from a second ultrasonic image data based on the received signal received by the ultrasonic probe, An ultrasound diagnostic system having, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. Ultrasound diagnostic system.
9. An image diagnostic device having an inference unit that uses a machine learning model to output an inference result associated with a detection target from a second ultrasonic image data based on a received signal received by an ultrasonic transducer, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is first position information indicating a part of the detection target in the first ultrasonic image data, or second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular pericardial boundary, The second region information is the region information of the valve annulus end. Medical imaging equipment.
10. An image diagnostic device having an inference unit that uses a machine learning model to output an inference result associated with a detection target from a second ultrasonic image data based on a received signal received by an ultrasonic transducer, The aforementioned machine learning model, A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, It is trained using training data that includes, The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. Medical imaging equipment.
11. A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, Perform machine learning using training data that includes the following: The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The detection target is the region for measuring the left ventricular ejection fraction. The first region information is region information of the left ventricular pericardial boundary, The second region information is the region information of the valve annulus end. training equipment.
12. A first ultrasonic image data based on the received signal received by the ultrasonic probe, The first ground truth data is first region information associated with the detection target of the first ultrasonic image data, A second ground truth data which is a first position information indicating a part of the detection target in the first ultrasonic image data, or a second region information indicating a part of the detection target in the first ultrasonic image data, Perform machine learning using training data that includes the following: The second correct answer data is the second region information, The second region information includes the distance from the first position coordinates associated with the detection target and the confidence level. The second region information is first heatmap information obtained by converting information including the distance from the first position coordinates associated with the detection target and the confidence level into a heatmap. The area to be detected is the region for measuring the diameter of the inferior vena cava. The first region information is the region information of the inferior vena cava, The second region information is region information of the hepatic vein point. training equipment.
13. The program according to claim 1 or 2, wherein the training data further comprises a third ground truth data which is a second location information associated with the detection target of the first ultrasonic image data, or a third region information based on the second location information .
14. The program according to claim 1 or claim 2 , wherein the machine learning model is composed of a convolutional neural network.
15. The ultrasonic diagnostic apparatus according to claim 5 or 6 , wherein the inference unit recognizes the shape of the object to be detected based on the coordinates of the maximum confidence value and outputs information about the shape of the object to be detected.
16. The ultrasonic diagnostic apparatus according to claim 5 or 6, wherein the inference unit determines the measurement position of the detection target based on the coordinates of the maximum confidence value, measures the detection target based on the measurement position, and outputs the measurement information of the measured detection target.

Description

This disclosure relates to machine learning models, programs, ultrasound diagnostic equipment, ultrasound diagnostic systems, imaging diagnostic equipment, and training equipment. Recent advancements in deep learning technology have led to the use of machine learning models in a variety of applications. For example, in the medical field, the use of machine learning models in image diagnosis using ultrasound image data has been proposed. Special Publication No. 2020-519369Japanese Patent Publication No. 2021-164573 Figure 1 is a schematic diagram showing the training and inference processes of a machine learning model according to one embodiment of the present disclosure.Figure 2A shows an example ultrasound image of the left ventricular region, and Figure 2B shows an example ultrasound image of the inferior vena cava diameter.Figure 3 is a schematic diagram showing a machine learning model for the left ventricular region according to one embodiment of the present disclosure.Figure 4 is a schematic diagram showing the training and inference processes of a machine learning model according to another embodiment of the present disclosure.Figure 5 is a schematic diagram showing the training and inference processes of a machine learning model according to another embodiment of the present disclosure.Figure 6 is a schematic diagram showing the training and inference processes of a machine learning model according to another embodiment of the present disclosure.Figure 7 is a schematic diagram showing an ultrasonic diagnostic apparatus according to one embodiment of the present disclosure.Figure 8 is a block diagram showing the hardware configuration of an ultrasound diagnostic apparatus according to one embodiment of the present disclosure.Figure 9 is a block diagram showing the hardware configuration of a training device and an image diagnostic device according to one embodiment of the present disclosure.Figure 10 is a block diagram showing the functional configuration of a training device according to one embodiment of the present disclosure.Figure 11A shows training data for the left ventricular region according to one embodiment of the present disclosure, and Figure 11B shows the ground truth data for region detection results according to one embodiment of the present disclosure.Figure 12 is a schematic diagram showing the training process of a machine learning model for EF measurement according to one embodiment of the present disclosure.Figure 13 is a block diagram showing the functional configuration of an ultrasound diagnostic device according to one embodiment of the present disclosure.Figure 14 shows the network architecture of a machine learning model for EF measurement according to one embodiment of the present disclosure.Figure 15 is a schematic diagram showing the detection of a target area for EF measurement according to one embodiment of the present disclosure.Figures 16A to 16C are schematic diagrams showing a contour extraction process according to one embodiment of the present disclosure.Figure 17A shows training data for the inferior vena cava region according to one embodiment of the present disclosure, and Figure 17B shows the ground truth data for region detection results according to one embodiment of the present disclosure.Figure 18 is a schematic diagram showing the training process of a machine learning model for IVC diameter measurement according to one embodiment of the present disclosure.Figure 19 shows the network architecture of a machine learning model for IVC diameter measurement according to one embodiment of the present disclosure.Figure 20A shows training data for the left ventricular region according to one embodiment of the present disclosure, and Figure 20B shows the ground truth data for region detection results according to one embodiment of the present disclosure.Figure 21 is a schematic diagram showing the training process of a machine learning model for EF measurement according to one embodiment of the present disclosure.Figure 22 shows a network architecture of a machine learning model for EF measurement according to one embodiment of the present disclosure.Figure 23 is a schematic diagram showing the detection of a target area for EF measurement according to one embodiment of the present disclosure.Figure 24A shows training data for the inferior vena cava region according to one embodiment of the present disclosure, and Figure 24B shows the ground truth data for region detection results according to one embodiment of the present disclosure.Figure 25 is a schematic diagram showing the detection of the target area for IVC diameter measurement according to one embodiment of the present disclosure.Figure 26 shows a network architecture of a machine learning model for IVC diameter measurement according to one embodiment of the present disclosure. The embodiments of this disclosure will be described below with reference to the drawings. [Summary of this disclosure] In the fo