Multi-Contrast MRI Segmentation Trained on Synthetic Images

TL;DR

This paper demonstrates that training MRI segmentation models on synthetically generated multi-contrast images can achieve accuracy comparable to models trained on real images, reducing the need for extensive real data collection.

Contribution

The study introduces a method for training MRI segmentation models exclusively on synthetic images across multiple contrasts, showing comparable performance to real-image training.

Findings

Segmentation accuracy on synthetic training data up to 93.91% for muscle.

Synthetic training results are not significantly different from real data training.

High-quality segmentation achieved across multiple tissue types using synthetic images.

Abstract

In our comprehensive experiments and evaluations, we show that it is possible to generate multiple contrast (even all synthetically) and use synthetically generated images to train an image segmentation engine. We showed promising segmentation results tested on real multi-contrast MRI scans when delineating muscle, fat, bone and bone marrow, all trained on synthetic images. Based on synthetic image training, our segmentation results were as high as 93.91\%, 94.11\%, 91.63\%, 95.33\%, for muscle, fat, bone, and bone marrow delineation, respectively. Results were not significantly different from the ones obtained when real images were used for segmentation training: 94.68\%, 94.67\%, 95.91\%, and 96.82\%, respectively.