Continuous model refinement via synthetic image generation from non-image feedback
Techniques are described for refining or updating medical image inferencing models post deployment using synthetic images generated from non-image data feedback. In an example, a system can comprise a memory that stores computer-executable components and a processor that executes the computer-executable components stored in the memory. The computer-executable components can comprise an image generation component that generates synthetic medical images based on feedback information associated with performance of a medical image inferencing model received in association with application of the medical image inferencing model to medical images in a deployment environment, wherein the feedback information excludes image data. The computer-executable components can further comprise a refinement component that updates the medical image inferencing model using the synthetic images and a model updating process.
1 . A system, comprising:
a memory that stores computer-executable components; and
a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
a synthetic image generation component that generates, using a synthetic image generation model, synthetic medical images based on feedback information associated with performance of a medical image inferencing model received in association with application of the medical image inferencing model to medical images in a deployment environment, wherein the feedback information comprises text data and wherein the synthetic image generation model generates the synthetic images based on the text data and without input data comprising image data;
a refinement component that updates the medical image inferencing model using the synthetic images and a model updating process.
2 . The system of claim 1 , wherein the feedback information comprises non-image data regarding attributes of at least some of the medical images, and wherein the feedback information excludes the medical images.
3 . The system of claim 2 , wherein the at least some of the medical images correspond to a subset of the medical images for which the performance of the medical image inferencing model is associated with one or more negative performance criteria.
4 . The system of claim 1 , wherein the feedback information comprises non-image data relating to results of the medical image inferencing model.
5 . The system of claim 1 , wherein the synthetic image generation model comprises a machine learning model.
6 . The system of claim 1 , wherein the model updating process comprise a machine learning process.
7 . The system of claim 1 , wherein the medical image inferencing model comprises a first machine learning model that was trained on a training dataset comprising first medical images, wherein the synthetic image generation component generates the synthetic medical images using a second machine learning model that generates the synthetic medical images based on textual description data and without input data comprising the image data or additional image data, and wherein the second machine learning model was trained on training textual description data associated with the first medical images.
8 . The system of claim 7 , wherein the computer-executable-components further comprise:
a training component that trains the first machine learning model and the second machine learning model.
9 . The system of claim 1 , wherein the feedback information comprises automated assessment data regarding an assessment of at least one of, the performance, at least some of the medical images, or results of the medical image inferencing model, the automated assessment data generated using one or more artificial intelligence assessment models.
10 . The system of claim 1 , wherein the feedback information comprises metadata associated with at least some of the medical images.
11 . The system of claim 1 , wherein the feedback information comprises clinical report data associated with at least some of the medical images.
12 . The system of claim 1 , wherein the feedback information comprises user provided feedback regarding an assessment of at least one of, the performance, at least some of the medical images, or results of the medical image inferencing model.
13 . The system of claim 12 , wherein the computer-executable components further comprise:
a feedback component that facilitates receiving the user provided feedback using one or more feedback tools associated with a medical imaging application in association with reviewing the results using the medical imaging application.
14 . A method, comprising:
generating, by a system comprising a processor and using a synthetic image generation model, synthetic medical images based on feedback information associated with performance of a medical image inferencing model received in association with application of the medical image inferencing model to medical images in a deployment environment, wherein the feedback information comprises text data and wherein the synthetic image generation model generates the synthetic images based on the text data and without input data comprising image data;
updating, by the system, the medical image inferencing model using the synthetic images and a model updating process.
15 . The method of claim 14 , wherein the feedback information comprises non-image data regarding attributes of at least some of the medical images, and wherein the feedback information excludes the medical images.
16 . The method of claim 14 , wherein the feedback information comprises non-image data relating to results of the medical image inferencing model.
17 . The method of claim 14 , wherein the synthetic image generation model comprises a machine learning model.
18 . The method of claim 14 , wherein the medical image inferencing model comprises a first machine learning model that was trained on a training dataset comprising first medical images and wherein the synthetic image generation model comprises a second machine learning model was trained on training textual description data associated with the first medical images.
19 . A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
generating, using a synthetic image generation model, synthetic medical images based on feedback information associated with performance of a medical image inferencing model received in association with application of the medical image inferencing model to medical images in a deployment environment, wherein the feedback information comprises text data and wherein the synthetic image generation model generates the synthetic images based on the text data and without input data comprising image data; and
updating the medical image inferencing model using the synthetic images and a model updating process.
20 . The non-transitory machine-readable storage medium of claim 19 , wherein the medical image inferencing model comprises a first machine learning model that was trained on a training dataset comprising first medical images and wherein the synthetic image generation model comprises a second machine learning model was trained on training textual description data associated with the first medical images.