Democratizing Artificial Intelligence in Healthcare: A Study of Model Development Across Two Institutions Incorporating Transfer Learning

TL;DR

This study demonstrates that transfer learning enables efficient development of AI models for cardiac image segmentation across institutions with limited data, reducing training time and maintaining acceptable accuracy.

Contribution

It provides a practical methodology for applying transfer learning to medical imaging, facilitating model sharing and adaptation between institutions.

Findings

Transfer learning improves model performance with sparse labels.

Using TL reduces development time for new models.

Acceptable segmentation accuracy achieved with limited data.

Abstract

The training of deep learning models typically requires extensive data, which are not readily available as large well-curated medical-image datasets for development of artificial intelligence (AI) models applied in Radiology. Recognizing the potential for transfer learning (TL) to allow a fully trained model from one institution to be fine-tuned by another institution using a much small local dataset, this report describes the challenges, methodology, and benefits of TL within the context of developing an AI model for a basic use-case, segmentation of Left Ventricular Myocardium (LVM) on images from 4-dimensional coronary computed tomography angiography. Ultimately, our results from comparisons of LVM segmentation predicted by a model locally trained using random initialization, versus one training-enhanced by TL, showed that a use-case model initiated by TL can be developed with sparse labels with acceptable performance. This process reduces the time required to build a new model in the clinical environment at a different institution.