Efficient anatomy segmentation in laparoscopic surgery using multi-teacher knowledge distillation

Automatic segmentation of anatomical structures in laparoscopic images or videos is an important prerequisite for visual assistance tools which are designed to increase efficiency and safety during an intervention. In order to be used in a realistic clinical scenario, both high accuracy and real-time capability are required. Current deep learning networks for anatomy segmentation show high accuracy, but are not suitable for real-time clinical application due to their large size. As smaller, real-time capable deep learning networks show lower segmentation performance, we propose a multi-teacher knowledge distillation approach applicable to partially labeled datasets. We leverage the knowledge of multiple anatomy-specific, high-accuracy teacher networks to improve the segmentation performance of a single and efficient student network capable of segmenting multiple anatomies simultaneously. To do so, we minimize the Kullback-Leibler divergence between the normalized anatomy-specific teacher logits and the respective normalized logits of the student. We conduct experiments on the Dresden Surgical Anatomy Dataset, which provides multiple subsets of binary segmented anatomical structures. Results show that our approach can increase the overall Dice score for different real-time capable network architectures for anatomy segmentation.

Subjects

Anatomy Segmentation | Knowledge Distillation | Real-Time | Surgical Computer Vision

DDC Class

600: Technology

Options

Efficient anatomy segmentation in laparoscopic surgery using multi-teacher knowledge distillation