Publications by authors named "Shuangchun Gui"
MT4MTL-KD: A Multi-Teacher Knowledge Distillation Framework for Triplet Recognition.
IEEE Trans Med Imaging
April 2024
The recognition of surgical triplets plays a critical role in the practical application of surgical videos. It involves the sub-tasks of recognizing instruments, verbs, and targets, while establishing precise associations between them. Existing methods face two significant challenges in triplet recognition: 1) the imbalanced class distribution of surgical triplets may lead to spurious task association learning, and 2) the feature extractors cannot reconcile local and global context modeling.
View Article and Find Full Text PDFArticle Synopsis
- - Formalizing surgical activities as triplets of instruments, actions, and target anatomies helps enhance the understanding of tool-tissue interactions, improving AI assistance in image-guided surgeries.
- - The CholecTriplet2022 challenge expands the previous work by adding weakly-supervised localization of surgical tools and modeling their activities as ‹instrument, verb, target› triplets.
- - The paper outlines a baseline method and presents 10 new deep learning algorithms, while also comparing their effectiveness and analyzing results to provide insights for future surgical research.