Rapid and robust endoscopic content area estimation: A lean GPU-based pipeline and curated benchmark dataset

TL;DR

This paper introduces a fast, GPU-based method for estimating endoscopic content areas, supported by a new benchmark dataset, outperforming existing approaches in accuracy and speed.

Contribution

The authors present two novel GPU-accelerated algorithms for endoscopic content area estimation and release a curated dataset for benchmarking this task.

Findings

Significant accuracy improvement over U-Net-based methods

Substantial reduction in computational time (0.13 ms vs 11.2 ms per frame)

First publicly available dataset for this task

Abstract

Endoscopic content area refers to the informative area enclosed by the dark, non-informative, border regions present in most endoscopic footage. The estimation of the content area is a common task in endoscopic image processing and computer vision pipelines. Despite the apparent simplicity of the problem, several factors make reliable real-time estimation surprisingly challenging. The lack of rigorous investigation into the topic combined with the lack of a common benchmark dataset for this task has been a long-lasting issue in the field. In this paper, we propose two variants of a lean GPU-based computational pipeline combining edge detection and circle fitting. The two variants differ by relying on handcrafted features, and learned features respectively to extract content area edge point candidates. We also present a first-of-its-kind dataset of manually annotated and pseudo-labelled content areas across a range of surgical indications. To encourage further developments, the curated dataset, and an implementation of both algorithms, has been made public (https://doi.org/10.7303/syn32148000, https://github.com/charliebudd/torch-content-area). We compare our proposed algorithm with a state-of-the-art U-Net-based approach and demonstrate significant improvement in terms of both accuracy (Hausdorff distance: 6.3 px versus 118.1 px) and computational time (Average runtime per frame: 0.13 ms versus 11.2 ms).