Deep Learning

A Deep Learning Model Predicts Total Knee Replacement (TKR) from MRI

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 New Deep Learning Model Aids in Diagnosis and Health Outcomes of Hip Fractures

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. 

A New Deep Learning Approach for Image Analysis of Osteoarthritis

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.

AI Rivals Expert Radiologists at Detecting Brain Hemorrhages

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

Jae Ho Sohn, MD, MS Talks About the Present and Future of AI in Health Care

A recent video story from the Washington Post looks at artificial intelligence (AI) and its future in health care. Jae Ho Sohn, MD, MS appears on this video.

Applying Advanced Computer Vision and Machine Learning to Study Musculoskeletal Disorders and Osteoporosis

Valentina Pedoia, PhD is a data scientist applying computer vision and machine learning techniques to MRI scans to study musculoskeletal disorders.

A Deep Learning Model Predicts a Diagnosis of Alzheimer’s Disease Using 18F-FDG PET

Artificial intelligence (AI) technology improves the ability of brain imaging to predict Alzheimer's disease, according to a study from UCSF Radiology researchers published in the journal Radiology.

Deep Learning Attacks Joint Degeneration and Osteoarthritis: Musculoskeletal Imaging Research Published in ‘Radiology’

Deep learning has become a powerful tool in radiology in recent years. Researchers at the UC San Francisco Department of Radiology and Biomedical Imaging have started using deep learning methods to characterize joint degeneration and osteoarthritis, which will ultimately reduce the number of total joint replacements.