Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function
This addresses the problem of manual lesion segmentation for medical experts, though it appears incremental as it builds on existing U-Net architectures with a modified loss function.
The authors tackled automatic liver lesion segmentation in CT scans by proposing a pipeline using cascaded 2D U-Nets and a Tversky loss function, achieving competitive scores in the LiTS challenge with high detection sensitivity.
At present, lesion segmentation is still performed manually (or semi-automatically) by medical experts. To facilitate this process, we contribute a fully-automatic lesion segmentation pipeline. This work proposes a method as a part of the LiTS (Liver Tumor Segmentation Challenge) competition for ISBI 17 and MICCAI 17 comparing methods for automatics egmentation of liver lesions in CT scans. By utilizing cascaded, densely connected 2D U-Nets and a Tversky-coefficient based loss function, our framework achieves very good shape extractions with high detection sensitivity, with competitive scores at time of publication. In addition, adjusting hyperparameters in our Tversky-loss allows to tune the network towards higher sensitivity or robustness.