Interpretability-guided Data Augmentation for Robust Segmentation in Multi-centre Colonoscopy Data

TL;DR

This paper proposes an interpretability-guided data augmentation method to improve the robustness and generalizability of deep learning models for multi-centre colonoscopy image segmentation, addressing variability across different medical centres.

Contribution

The paper introduces a novel data augmentation technique based on interpretability saliency maps that enhances model robustness in multi-centre colonoscopy segmentation tasks.

Findings

Improved segmentation robustness across different models and domains.

Effective in multi-centre polyp detection datasets.

Quantitative and qualitative validation of the approach.

Abstract

Multi-centre colonoscopy images from various medical centres exhibit distinct complicating factors and overlays that impact the image content, contingent on the specific acquisition centre. Existing Deep Segmentation networks struggle to achieve adequate generalizability in such data sets, and the currently available data augmentation methods do not effectively address these sources of data variability. As a solution, we introduce an innovative data augmentation approach centred on interpretability saliency maps, aimed at enhancing the generalizability of Deep Learning models within the realm of multi-centre colonoscopy image segmentation. The proposed augmentation technique demonstrates increased robustness across different segmentation models and domains. Thorough testing on a publicly available multi-centre dataset for polyp detection demonstrates the effectiveness and versatility of our approach, which is observed both in quantitative and qualitative results. The code is publicly available at: https://github.com/nki-radiology/interpretability_augmentation