Systems and methods for digital transformation of medical images and fibrosis detection
AssigneeUniversity of Louisville Research Foundation, Inc.
InventorsAyman S. El-Baz, Dibson Gondim, Ahmed Naglah, Fahmi Khalifa
Life of this patent
Estimating the term…
Abstract
A novel system and method for accurate detection and quantification of fibrous tissue produces a virtual medical image of tissue treated with a second stain based on a received medical image of tissue treated with a first stain using a computer-implemented trained deep learning model. The model is trained to learn the deep texture patterns associated with collagen fibers using conditional generative adversarial networks to detect and quantify fibrous tissue.
Claims18
-23. (canceled)
A computer-implemented method for assessing fibrosis, comprising:
- receiving a first medical image of a tissue treated with a first stain;
- generating, using a machine learning model and the first medical image, a second medical image of the tissue treated with a second stain, wherein the first stain and the second stain are non-identical stains;
- identifying fibrous tissue in the second medical image;
- and
- assessing fibrosis based on the identified fibrous tissue in the second medical image.
A computer-implemented method for transforming medical images, comprising:
- receiving a first medical image of a tissue treated with a first stain;
- generating, using a machine learning model and the first medical image, a second medical image of the tissue treated with a second stain, wherein the first stain and the second stain are non-identical stains;
- and
- wherein the generating includes segmenting the first medical into a first plurality of tiles, generating a second plurality of tiles using the machine learning model, and stacking the second plurality of tiles to generate the second medical image.
Dependencies are inferred from the claim text.