PIMMS: Permutation Invariant Multi-Modal Segmentation
This addresses the challenge of flexible imaging protocols in hospitals, enabling algorithms to work with available data without requiring operational changes, though it appears incremental as it builds on existing segmentation methods.
The paper tackles the problem of MRI segmentation when modality labels are missing or unreliable in clinical settings, introducing PIMMS, a permutation invariant multi-modal segmentation technique that can perform inference without using modality labels and achieves comparable or better performance than a baseline model that uses labels.
In a research context, image acquisition will often involve a pre-defined static protocol and the data will be of high quality. If we are to build applications that work in hospitals without significant operational changes in care delivery, algorithms should be designed to cope with the available data in the best possible way. In a clinical environment, imaging protocols are highly flexible, with MRI sequences commonly missing appropriate sequence labeling (e.g. T1, T2, FLAIR). To this end we introduce PIMMS, a Permutation Invariant Multi-Modal Segmentation technique that is able to perform inference over sets of MRI scans without using modality labels. We present results which show that our convolutional neural network can, in some settings, outperform a baseline model which utilizes modality labels, and achieve comparable performance otherwise.