Multi-Contrast MRI Segmentation Trained on Synthetic Images
This addresses the challenge of data scarcity in medical imaging by enabling effective segmentation with synthetic data, though it is incremental as it builds on existing synthetic generation methods.
The paper tackled the problem of multi-contrast MRI segmentation by training on synthetic images, achieving segmentation accuracies of 93.91% to 95.33% for muscle, fat, bone, and bone marrow, which were not significantly different from results using real images (94.68% to 96.82%).
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.