Meeting Banner
Abstract #3575

Transfer learning framework for knee plane prescription

Radhika Madhavan1, Andre Maximo2, Chitresh Bhushan1, Soumya Ghose1, Dattesh D Shanbhag3, Uday Patil3, Matthew Frick4, Kimberly K Amrami4, Desmond Teck Beng Yeo1, and Thomas K Foo1
1GE Global Research, Niskayuna, NY, United States, 2GE Healthcare, Rio de Janeiro, Brazil, 3GE Healthcare, Bangalore, India, 4Mayo Clinic, Rochester, MN, United States

On model deployment, ideally deep learning models should be able learn continuously from new data, but data privacy concerns in medical imaging do not allow for ready sharing of training data. Retraining with incremental data generally leads to catastrophic forgetting. In this study, we evaluated the performance of a knee plane prescription model by retraining with incremental data from a new site. Increasing the number of incoming training data sets and transfer learning significantly improved test performance. We suggest that partial retraining and distributed learning frameworks may be more suitable for retraining of incremental data.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here