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

Source: [DeepPyram: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos](<https://www.sota2.com/research/paper/68fa6ab41e209131cea29e35>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T14:42:26.547Z

Authors: Negin Ghamsarian, Mario Taschwer, klaus Schoeffmann

Published: 2021-09-11T19:31:52.000Z

## 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 instances make the designation of a unique network quite challenging. This paper proposes a semantic segmentation network termed as DeepPyram that can achieve superior performance in segmenting relevant objects in cataract surgery videos with varying issues. This superiority mainly originates from three modules: (i) Pyramid View Fusion, which provides a varying-angle global view of the surrounding region centering at each pixel position in the input convolutional feature map; (ii) Deformable Pyramid Reception, which enables a wide deformable receptive field that can adapt to geometric transformations in the object of interest; and (iii) Pyramid Loss that adaptively supervises multi-scale semantic feature maps. These modules can effectively boost semantic segmentation performance, especially in the case of transparency, deformability, scalability, and blunt edges in objects. The proposed approach is evaluated using four datasets of cataract surgery for objects with different contextual features and compared with thirteen state-of-the-art segmentation networks. The experimental results confirm that DeepPyram outperforms the rival approaches without imposing additional trainable parameters. Our comprehensive ablation study further proves the effectiveness of the proposed modules.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.05352>)

[PDF](<https://arxiv.org/pdf/2109.05352.pdf>)