DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos

TL;DR

DeepPyramid introduces a novel neural network architecture with pyramid view fusion, deformable receptive fields, and adaptive multi-scale supervision, significantly improving semantic segmentation accuracy in cataract surgery videos.

Contribution

The paper presents DeepPyramid, a new segmentation network with three innovative modules designed to handle complex surgical structures more effectively.

Findings

Achieves 3.66% higher IoU than previous methods.

Effectively handles transparency and deformability in surgical structures.

Outperforms existing approaches with state-of-the-art results.

Abstract

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these surgeries make the designation of a unique network quite challenging. This paper proposes a semantic segmentation network, termed DeepPyramid, that can deal with these challenges using three novelties: (1) a Pyramid View Fusion module which provides a varying-angle global view of the surrounding region centering at each pixel position in the input convolutional feature map; (2) a Deformable Pyramid Reception module which enables a wide deformable receptive field that can adapt to geometric transformations in the object of interest; and (3) a dedicated Pyramid Loss that adaptively supervises multi-scale semantic feature maps. Combined, we show that these modules can effectively boost semantic segmentation performance, especially in the case of transparency, deformability, scalability, and blunt edges in objects. We demonstrate that our approach performs at a state-of-the-art level and outperforms a number of existing methods with a large margin (3.66% overall improvement in intersection over union compared to the best rival approach).