Runtime Freezing: Dynamic Class Loss for Multi-Organ 3D Segmentation
This work addresses class imbalance issues in medical image segmentation, which is incremental as it builds on existing loss strategies.
The authors tackled the problem of class imbalance in multi-organ 3D segmentation by proposing dynamic class-based loss strategies, resulting in improved segmentation performance on a challenging dataset.
Segmentation has become a crucial pre-processing step to many refined downstream tasks, and particularly so in the medical domain. Even with recent improvements in segmentation models, many segmentation tasks remain difficult. When multiple organs are segmented simultaneously, difficulties are due not only to the limited availability of labelled data, but also to class imbalance. In this work we propose dynamic class-based loss strategies to mitigate the effects of highly imbalanced training data. We show how our approach improves segmentation performance on a challenging Multi-Class 3D Abdominal Organ dataset.