AOSSM 2023 Annual Meeting Recordings no CME-Deep Learning Accurately Predicts Supraspinatus Pathology on Shoulder Magnetic Resonance Imaging

Deep Learning Accurately Predicts Supraspinatus Pathology on Shoulder Magnetic Resonance Imaging

Video Transcription

Video Summary

In this video, the speaker discusses the use of deep learning for medical imaging analysis in orthopedics. They specifically focus on the RAD ImageNet database, which contains 1.4 million images of CTs, MRIs, and ultrasounds from different anatomical locations. The images were labeled by radiologists, and the speaker's team used this database to develop a deep learning model for identifying rotator cuff pathology on shoulder MRIs. They achieved a high accuracy of 98.9%, with sensitivity at 98.7% and specificity at 100%. The speaker suggests that the RAD ImageNet database can be a valuable resource for external validation in the future.

Asset Caption

Ryan Ingebritsen, BS

Keywords

deep learning

medical imaging analysis

orthopedics

RAD ImageNet database

rotator cuff pathology