Deep Learning

Models trained on other pathologies can be adapted to identify MS lesions with smaller datasets.

The first ci² Specialized Research Group meeting of 2024 introduced UCSF's new large language model tools that are now available to researchers, clinicians, and staff.

The UC San Francisco Department of Radiology and Biomedical Imaging noted a significant milestone for both the department and the UCSF Center for Intelligent Imaging (ci²) - full deployment of an artificial intelligence (AI)-enabled portable x-ray device into our clinical environment.

A trio of imaging informatics experts looked at everything radiology departments need to consider before purchasing AI. Marc Kohli, MD and John Mongan, MD were authors on this article, recently published in the Journal of the American College of Radiology. 

A team from the UCSF Center for Intelligent Imaging (ci2) developed a deep learning pipeline for diagnostic worklist prioritization and generalizability in assessing anterior cruciate ligament (ACL) lesions.

A paper from a team of scientists at the UCSF Ci2 won the 2020 Best Paper Award at Medical Imaging with Deep Learning (MIDL) earlier this month.

This study from the UCSF Center for Intelligent Imaging (ci2) is a great example of the use of deep learning methods for new discovery.

A team of radiologists and orthopedists from the Center for Intelligent Imaging, or Ci2, at UCSF recently investigated the feasibility of automatic identificaiton and classification of hip fractures using deep learning. 

The purpose of the study from UCSF's MQIR group was to develop a multitask, deep learning model for grading hip osteoarthritis features on radiographs and compare its performance to that of attending-level radiologists.

Richly annotated training data vastly improves deep learning algorithm's accuracy.