Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning

TL;DR

This paper introduces a weakly supervised learning framework for COVID-19 lesion localization and segmentation on chest CT images, reducing annotation bias and labeling costs by using only image-level labels.

Contribution

It presents a novel data-driven approach combining generative adversarial networks and lesion-specific decoders for unbiased lesion detection with minimal supervision.

Findings

Outperforms existing methods on two COVID-19 datasets

Effectively localizes lesions with only image-level labels

Reduces annotation bias and labeling effort

Abstract

Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images. Due to the nature of blurred boundaries, the supervised segmentation methods usually suffer from annotation biases. To support unbiased lesion localisation and to minimise the labeling costs, we propose a data-driven framework supervised by only image-level labels. The framework can explicitly separate potential lesions from original images, with the help of a generative adversarial network and a lesion-specific decoder. Experiments on two COVID-19 datasets demonstrate the effectiveness of the proposed framework and its superior performance to several existing methods.