Medical Imaging
FULLY AUTOMATED SEMANTIC FAT SEGMENTATION ON CT EXAMS OF THE CHEST, ABDOMEN, AND PELVIS USING DEEP LEARNING
WARF: P230242US01
Inventors: John Garrett, Perry Pickhardt
The Invention
UW Madison researchers have developed a new, fully automated, deep learning based fat segmentation tool for CT images of the pelvis, abdomen and chest. The tool provides more accurate segmentation of fat from fat mimics, resulting in a more reliable fat measurement for the identification of metabolic disorders and other biomarker assessments. The method was built using pytorch and MIT open-source machine learning architectures and was trained on a curated data set of images obtained under the researcher’s Opportunistic Screening Consortium in Abdominal Radiology (OSCAR) project.
Additional Information
For More Information About the Inventors
Tech Fields
For current licensing status, please contact Jeanine Burmania at [javascript protected email address] or 608-960-9846