Meeting Banner
Abstract #4014

Self-supervised Pretraining on OAI data for 3D Knee MRI Analysis

Xinxin Wang1,2,3, Liam Hazan4, Mingrui Yang1,2, Simona Rabinovici-Cohen4, and Xiaojuan Li1,2,5
1Program of Advanced Musculoskeletal Imaging (PMAI), Cleveland Clinic, Cleveland, OH, United States, 2Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, United States, 3Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH, United States, 4IBM Research Labs, IBM Research, Haifa, Israel, 5Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States

Synopsis

Keywords: Diagnosis/Prediction, Machine Learning/Artificial Intelligence, Knee MRI; Pretrained model

Motivation: Self-supervised pretraining is efficient and requires no labeled data, yet it is understudied for 3D knee MRI analysis.

Goal(s): Our goal is to develop a self-supervised pretraining model and explore its potential for 3D knee MRI analysis.

Approach: We use DINO pipeline for self-supervised training on OAI data and apply the pretrained model to downstream tasks, comparing it with training from scratch and a supervised pretrained model.

Results: Our OAI-DINO pretrained model significantly outperforms training from scratch on downstream tasks, offers comparable segmentation results and improves classification performance over the supervised pretrained model.

Impact: Our study has leveraged the OAI database and demonstrated the effectiveness of self-supervised pretraining for 3D knee MRI. Our approach enhances downstream task performance, inspiring further study on advancing automated 3D medical imaging analysis without labeled data.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords