While overall segmentation performance of both architectures was similar for structure-specific models, SegFormer-based models showed a trend toward better performance than DeepLabv3-based models in segmentation of the pancreas, the spleen, and the ureter (Table 1 , Fig. 2 , Supplementary Fig. 2, Supplemental Digital Content 1, http://links.lww.com/JS9/A792 ).
← all excerpts
Anatomy segmentation in laparoscopic surgery: comparison of machine learning and human expertise - an experimental study.
1
—
—