# Brain Tumor Segmentation on MRI with Missing Modalities

## TL;DR

This paper introduces a robust brain tumor segmentation method for MRI that handles missing modalities using self-supervised training and domain adaptation, improving clinical applicability.

## Contribution

It proposes a novel neural network architecture with self-supervised channel dropout and domain adaptation to effectively segment tumors with missing MRI modalities.

## Key findings

- Segmentation quality varies with missing modality.
- The method effectively recovers information from missing channels.
- Contributions align with clinical screening routines.

## Abstract

Brain Tumor Segmentation from magnetic resonance imaging (MRI) is a critical technique for early diagnosis. However, rather than having complete four modalities as in BraTS dataset, it is common to have missing modalities in clinical scenarios. We design a brain tumor segmentation algorithm that is robust to the absence of any modality. Our network includes a channel-independent encoding path and a feature-fusion decoding path. We use self-supervised training through channel dropout and also propose a novel domain adaptation method on feature maps to recover the information from the missing channel. Our results demonstrate that the quality of the segmentation depends on which modality is missing. Furthermore, we also discuss and visualize the contribution of each modality to the segmentation results. Their contributions are along well with the expert screening routine.