EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)

TL;DR

EndoBoost is a versatile, plug-and-play module that significantly reduces false positives in polyp detection during colonoscopy by leveraging generative learning and anomaly detection, supported by a new real-world dataset.

Contribution

This work introduces EndoBoost, a novel post-hoc false positive suppression module, and the FPPD-13 dataset for real-world polyp detection challenges.

Findings

EndoBoost effectively reduces false positives in polyp detection.

The FPPD-13 dataset captures real-world false positives in colonoscopy.

The anomaly detection approach outperforms supervised methods in open-world scenarios.

Abstract

The advance of computer-aided detection systems using deep learning opened a new scope in endoscopic image analysis. However, the learning-based models developed on closed datasets are susceptible to unknown anomalies in complex clinical environments. In particular, the high false positive rate of polyp detection remains a major challenge in clinical practice. In this work, we release the FPPD-13 dataset, which provides a taxonomy and real-world cases of typical false positives during computer-aided polyp detection in real-world colonoscopy. We further propose a post-hoc module EndoBoost, which can be plugged into generic polyp detection models to filter out false positive predictions. This is realized by generative learning of the polyp manifold with normalizing flows and rejecting false positives through density estimation. Compared to supervised classification, this anomaly detection paradigm achieves better data efficiency and robustness in open-world settings. Extensive experiments demonstrate a promising false positive suppression in both retrospective and prospective validation. In addition, the released dataset can be used to perform 'stress' tests on established detection systems and encourages further research toward robust and reliable computer-aided endoscopic image analysis. The dataset and code will be publicly available at http://endoboost.miccai.cloud.