X-RAY COMPUTED TOMOGRAPHY APPARATUS, MEDICAL INFORMATION PROCESSING APPARATUS, AND MEDICAL INFORMATION PROCESSING METHOD
An X-ray computed tomography (CT) apparatus according to an embodiment includes an X-ray tube, an X-ray detector, and processing circuitry. The X-ray tube generates an X-ray. The X-ray detector detects the X-ray emitted from the X-ray tube and having passed a subject. The processing circuitry reconstructs CT image data based on an output from the X-ray detector. The processing circuitry generates a prompt to be input to a generative model, the prompt including observation information about the CT image data. The processing circuitry obtains an answer including medical information about the subject from the generative model, in response to an input of the prompt to the generative model. The processing circuitry outputs reliability of the answer based on the prompt and the answer.
1 . An X-ray computed tomography (CT) apparatus comprising:
an X-ray tube that generates an X-ray;
an X-ray detector that detects the X-ray emitted from the X-ray tube and having passed a subject; and
processing circuitry configured to:
reconstruct CT image data based on an output from the X-ray detector,
generate a prompt to be input to a generative model, the prompt including observation information about the CT image data,
obtain an answer including medical information from the generative model, in response to an input of the prompt to the generative model, and
output reliability of the answer based on the prompt and the answer.
2 . A medical information processing apparatus comprising processing circuitry configured to:
generate a prompt to be input to a first generative model, in accordance with a user's input,
obtain an answer including medical information from the first generative model, in response to an input of the prompt to the first generative model, and
output reliability of the answer based on the prompt and the answer.
3 . The medical information processing apparatus according to claim 2 , wherein the processing circuitry is configured to:
extract a first named entity from the prompt,
extract a second named entity from the answer,
search a medical information database using the first named entity and the second named entity as a search condition, to identify document data based on how many times the first named entity and the second named entity appear,
calculate a similarity of the document data relative to the prompt and the answer, based on a first vector and a second vector, the first vector representing a vectorization of the document data, the second vector representing a vectorization of the prompt and the answer, and
determine the reliability based on the similarity.
4 . The medical information processing apparatus according to claim 3 , wherein
the processing circuitry is configured to identify document data in which the first named entity and the second named entity appear a largest number of times.
5 . The medical information processing apparatus according to claim 2 , wherein the processing circuitry is configured to:
extract a first named entity from the prompt,
extract a second named entity from the answer,
search a medical information database using the first named entity and the second named entity as a search condition, to calculate a hit count under the search condition, and
determine the reliability based on the hit count.
6 . The medical information processing apparatus according to claim 2 , wherein the processing circuitry is configured to:
extract a first named entity from the prompt,
extract a second named entity from the answer,
calculate a number of mutually corresponding named entities in the first named entity and the second named entity, and
determine the reliability based on the number of mutually corresponding named entities.
7 . The medical information processing apparatus according to claim 6 , wherein the processing circuitry is configured to:
generate an inquiry prompt for inquiring about reliability of the answer, based on the prompt and the answer,
obtain an output from the first generative model or a second generative model different from the first generative model, in response to an input of the inquiry prompt to the first generative model or the second generative model, and
output the reliability in accordance with the obtained output from the first generative model or the second generative model.
8 . The medical information processing apparatus according to claim 2 , wherein the processing circuitry is configured to:
generate an inquiry prompt for inquiring about reliability of the answer,
obtain an output from the first generative model or a second generative model different from the first generative model, in response to an input of the inquiry prompt, the prompt, and the answer to the first generative model or the second generative model, and
output the reliability in accordance with the obtained output from the first generative model or the second generative model.
9 . The medical information processing apparatus according to claim 2 , further comprising:
a display that displays the reliability and a basis for the reliability.
10 . The medical information processing apparatus according to claim 2 , further comprising:
a display that displays the prompt and the answer with the reliability.
11 . A medical information processing method comprising:
generating a prompt to be input to a generative model, in accordance with a user's input;
inputting the prompt to the generative model;
obtaining an answer including medical information from the generative model; and
outputting reliability of the answer based on the prompt and the answer.