Small Organ Segmentation in Whole-body MRI using a Two-stage FCN and Weighting Schemes
This work addresses segmentation of small organs in medical imaging for healthcare applications, but it is incremental as it builds on existing coarse-to-fine strategies.
The paper tackled the problem of segmenting small organs in whole-body MRI, which is challenging due to anatomical variation and class imbalance, and achieved improved segmentation accuracy using a two-stage approach with weighting schemes.
Accurate and robust segmentation of small organs in whole-body MRI is difficult due to anatomical variation and class imbalance. Recent deep network based approaches have demonstrated promising performance on abdominal multi-organ segmentations. However, the performance on small organs is still suboptimal as these occupy only small regions of the whole-body volumes with unclear boundaries and variable shapes. A coarse-to-fine, hierarchical strategy is a common approach to alleviate this problem, however, this might miss useful contextual information. We propose a two-stage approach with weighting schemes based on auto-context and spatial atlas priors. Our experiments show that the proposed approach can boost the segmentation accuracy of multiple small organs in whole-body MRI scans.