Effective semantic segmentation in Cataract Surgery: What matters most?
This work addresses the problem of imbalanced data in surgical video analysis for medical professionals, though it is incremental as it builds on existing methods.
The paper tackles semantic segmentation in cataract surgery videos by proposing neural network design choices to handle class imbalance, achieving state-of-the-art performance on the CaDIS benchmark with significant gains on rare tool classes.
Our work proposes neural network design choices that set the state-of-the-art on a challenging public benchmark on cataract surgery, CaDIS. Our methodology achieves strong performance across three semantic segmentation tasks with increasingly granular surgical tool class sets by effectively handling class imbalance, an inherent challenge in any surgical video. We consider and evaluate two conceptually simple data oversampling methods as well as different loss functions. We show significant performance gains across network architectures and tasks especially on the rarest tool classes, thereby presenting an approach for achieving high performance when imbalanced granular datasets are considered. Our code and trained models are available at https://github.com/RViMLab/MICCAI2021_Cataract_semantic_segmentation and qualitative results on unseen surgical video can be found at https://youtu.be/twVIPUj1WZM.