US-20260128156-A1 - SYSTEMS FOR PROVIDING CONTEXT-BASED ASSISTANCE DURING AN ULTRASOUND IMAGING WORKFLOW

US20260128156A1US 20260128156 A1US20260128156 A1US 20260128156A1US-20260128156-A1

Abstract

Systems are provided for providing context-based chatbot assistance during an ultrasound imaging workflow. In one example, an ultrasound imaging system includes an artificial intelligence (AI) processing circuit. The AI processing circuit is configured to receive image data obtained by a transducer; generate a natural language input based on the image data configured to prompt a response; input the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system; identify, from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information regarding the ultrasound imaging workflow; generate the response based on the portion of the contextual information and the processed image data; and provide the response.

Inventors

Svein Arne Aase
Erik Normann Steen

Assignees

GE Precision Healthcare LLC

Dates

Publication Date: 20260507
Application Date: 20241106

Claims (20)

1 . An ultrasound imaging system comprising: a transducer configured to transmit and receive an ultrasound signal; a matching layer configured to have an acoustic impedance between a tissue to be imaged and a material of the transducer; a damping block configured to absorb ultrasound energy; and an artificial intelligence (AI) processing circuit configured to: receive image data obtained by the transducer; generate a natural language input based on the image data, the natural language input configured to prompt a response from the AI processing circuit based on the natural language input; input the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system; identify, from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information regarding the ultrasound imaging workflow; generate the response based on the portion of the contextual information and the processed image data; and provide, to a user via a display of the ultrasound imaging system, the response.
2 . The ultrasound imaging system of claim 1 , wherein the AI processing circuit is further configured to receive at least one of a text input or a voice input from the user, wherein the at least one of the text input or the voice input is configured to prompt the response from a chatbot generated by AI processing circuit.
3 . The ultrasound imaging system of claim 1 , wherein the AI processing circuit is configured to: encode a selectable element with the natural language input; present, to the user via the display, the selectable element encoded with the natural language input; and receive a selection of the selectable element from the user, wherein the selection of the selectable element is configured to input the natural language input to the machine learning model.
4 . The ultrasound imaging system of claim 3 , wherein the selectable element is one of a plurality of selectable elements each encoded with one of a plurality of natural language inputs, and wherein the AI processing circuit is configured to: generate the plurality of selectable elements; and present the plurality of selectable elements to the user via the display of the ultrasound imaging system.
5 . The ultrasound imaging system of claim 4 , wherein at least one of the plurality of selectable elements is generated based on the AI processing circuit detecting an interaction of the user with the display of the ultrasound imaging system.
6 . The ultrasound imaging system of claim 1 , wherein providing the response comprises at least one of providing a textual response via a chatbot, providing an audible response, or changing an operating characteristic of the ultrasound imaging system.
7 . The ultrasound imaging system of claim 6 , wherein changing the operating characteristic of the ultrasound imaging system comprises changing at least one of a mode, a view, an acquisition parameter, or a measurement setting.
8 . The ultrasound imaging system of claim 1 , wherein the AI processing circuit comprises at least one of a large language model or a visual language model.
9 . The ultrasound imaging system of claim 8 , wherein the AI processing circuit comprises a retrieval-augmented generation model and wherein generating the response comprises: querying a retrieval model configured to search a medical information database for data relating to the ultrasound imaging workflow; combining the data relating to the ultrasound imaging workflow with the natural language input to create an augmented prompt; applying the augmented prompt to the at least one of the large language model or the visual language model; and generating the response based on the augmented prompt.
10 . The ultrasound imaging system of claim 1 , wherein the database of contextual information comprises at least one of a real-time status of the ultrasound imaging workflow, a current configuration of the display of the ultrasound imaging system, patient medical history, a user guide associated with the ultrasound imaging system, or a medical information database.
11 . An ultrasound imaging system comprising: a transducer configured to transmit and receive an ultrasound signal; a matching layer configured to have an acoustic impedance between a tissue to be imaged and a material of the transducer; a damping block configured to absorb ultrasound energy; and a processing circuit comprising a processor coupled to a memory device storing instructions thereon that, when executed, cause the processing circuit to perform operations comprising: receiving, by an artificial intelligence (AI) processing circuit, image data obtained by the transducer; generating a natural language input based on the image data, the natural language input configured to prompt a response from the AI processing circuit based on the natural language input; inputting the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system; identifying, from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information related to the ultrasound imaging workflow; generating, using the AI processing circuit, the response based on the portion of the contextual information and the processed image data; and providing, to a user via a display of the ultrasound imaging system, the response.
12 . The ultrasound imaging system of claim 11 , wherein the operations further comprise receiving at least one of a text input or a voice input from the user, wherein the at least one of the text input or the voice input is configured to prompt the response from a chatbot generated by the AI processing circuit.
13 . The ultrasound imaging system of claim 11 , wherein the operations comprise: encoding a selectable element with the natural language input; presenting, to the user via the display, the selectable element encoded with the natural language input; and receiving a selection of the selectable element from the user, wherein the selection of the selectable element is configured to input the natural language input to the machine learning model.
14 . The ultrasound imaging system of claim 13 , wherein the selectable element is one of a plurality of selectable elements each encoded with one of a plurality of natural language inputs, and wherein the operations comprise: generating the plurality of selectable elements; and presenting the plurality of selectable elements to the user via the display of the ultrasound imaging system.
15 . The ultrasound imaging system of claim 11 , wherein the AI processing circuit comprises a retrieval-augmented generation model and at least one of a large language model or a visual language model, and wherein generating the response comprises: querying, by the AI processing circuit, a retrieval model configured to search a medical information database for data relating to the ultrasound imaging workflow; combining, by the AI processing circuit, the data relating to the ultrasound imaging workflow with the natural language input to create an augmented prompt; applying, by the AI processing circuit, the augmented prompt to the at least one of the large language model or the visual language model; and generating, by the AI processing circuit, the response based on the augmented prompt.
16 . A method comprising: receiving, by an artificial intelligence (AI) processing circuit, image data obtained by an ultrasound probe of an ultrasound imaging system; generating, by the AI processing circuit, a natural language input based on the image data, the natural language input configured to prompt a response from the AI processing circuit based on the natural language input; inputting, by the AI processing circuit, the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system; identifying, by the AI processing circuit and from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information regarding the ultrasound imaging workflow; generating, by the AI processing circuit, the response based on the portion of the contextual information and the processed image data; and providing, by the AI processing circuit and to a user via a display, the response.
17 . The method of claim 16 , further comprising receiving, by the AI processing circuit, at least one of a text input or a voice input from the user, wherein the at least one of the text input or the voice input is configured to prompt the response from a chatbot generated by the AI processing circuit.
18 . The method of claim 16 , wherein the method comprises: encoding, by the AI processing circuit, a selectable element with the natural language input; presenting, by the AI processing circuit and to the user via the display, the selectable element encoded with the natural language prompt; and receiving, by the AI processing circuit a selection of the selectable element from the user, wherein the selection of the selectable element is configured to input the natural language prompt to the machine learning model.
19 . The method of claim 16 , wherein the AI processing circuit comprises a retrieval-augmented generation model and at least one of a large language model or a visual language model, and wherein generating the response comprises: querying, by the AI processing circuit, a retrieval model configured to search a medical information database for data relating to the ultrasound imaging workflow; combining, by the AI processing circuit, the data relating to the ultrasound imaging workflow with the natural language input to create an augmented prompt; applying, by the AI processing circuit, the augmented prompt to the at least one of the large language model or the visual language model; and generating, by the AI processing circuit, the response based on the augmented prompt.
20 . The method of claim 16 , wherein providing the response comprises at least one of providing a textual response via a chatbot, providing an audible response, or changing an operating characteristic of the ultrasound imaging system, and wherein changing the operating characteristic of the ultrasound imaging system comprises changing at least one of a mode, a view, an acquisition parameter, or a measurement setting.

Description

FIELD Embodiments of the subject matter disclosed herein relate to ultrasound imaging, and more particularly, to providing assistance during an ultrasound imaging workflow using contextual information regarding the ultrasound imaging workflow. BACKGROUND During a medical imaging workflow, a plurality of medical images of a patient are obtained by a technician, such as a sonographer, to measure or detect various aspects of anatomical features present within the medical images. These images and measurements are subsequently analyzed by a clinician, such as a cardiologist or radiologist, to observe a condition or to identify any abnormalities. SUMMARY An embodiment relates to an ultrasound imaging system. The ultrasound imaging system includes a transducer configured to transmit and receive an ultrasound signal, a matching layer configured to have an acoustic impedance between a tissue to be imaged and a material of the transducer, a damping block configured to absorb ultrasound energy, and an artificial intelligence (AI) processing circuit. The AI processing circuit is configured to process image data obtained by the transducer. The AI processing circuit is configured generate a natural language input configured to prompt a response from the AI processing circuit based on the natural language input. The AI processing circuit is configured to input the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system. The AI processing circuit is configured to identify, from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information regarding the ultrasound imaging workflow. The AI processing circuit is configured to generate the response based on the portion of the contextual information and the processed image data. The AI processing circuit is configured to provide, to a user via a display of the ultrasound imaging system, the response. Another embodiment relates to an ultrasound imaging system. The ultrasound imaging system includes a transducer configured to transmit and receive an ultrasound signal, a matching layer configured to have an acoustic impedance between a tissue to be imaged and a material of the transducer, a damping block configured to absorb ultrasound energy, and a processing circuit. The processing circuit includes a processor coupled to a memory device, and the memory device stores instructions thereon that, when executed, cause the processing circuit to perform operations including processing, using an artificial intelligence (AI) processing circuit, image data obtained by the transducer, generating a natural language input configured to prompt a response from the AI processing circuit based on the natural language input, inputting the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system, identifying, from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information related to the ultrasound imaging workflow, generating, using the AI processing circuit, the response based on the portion of the contextual information and the processed image data, and providing, to a user via a display of the ultrasound imaging system, the response. Another embodiment relates to a method. The method includes processing, by an artificial intelligence (AI) processing circuit, image data obtained by an ultrasound probe of an ultrasound imaging system. The method includes generating, by the AI processing circuit, a natural language input configured to prompt a response from the AI processing circuit based on the natural language input. The method includes inputting, by the AI processing circuit, the natural language input to a machine learning model during an ultrasound imaging workflow performed by the ultrasound imaging system. The method includes identifying, by the AI processing circuit and from a database of contextual information relating to the ultrasound imaging system, a portion of the contextual information regarding the ultrasound imaging workflow. The method includes generating, by the AI processing circuit, the response based on the portion of the contextual information and the processed image data. The method includes providing, by the AI processing circuit and to a user via a display, the response. This summary is illustrative only and is not intended to be in any way limiting. Other aspects, inventive features, and advantages of the devices or processes described herein will become apparent in the detailed description set forth herein, taken in conjunction with the accompanying figures, wherein like reference numerals refer to like elements. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of an ultrasound imaging system, according to an example embodiment. FIG. 2 is an illustration of the ultrasound imaging system of FIG.