Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling

TL;DR

This paper introduces Probabilistic-CAM pooling, a novel method enabling lesion localization in chest X-rays using only image-level labels, outperforming existing methods in both classification and localization tasks.

Contribution

The paper proposes PCAM pooling, a new global pooling technique that enhances weakly supervised lesion localization by probabilistically leveraging CAM's localization ability.

Findings

PCAM pooling outperforms state-of-the-art baselines in classification and localization.

Visual maps show sharper boundaries around lesions with PCAM.

Method is open-sourced for community use.

Abstract

Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning. However, current deep learning based approaches often require strong supervision, e.g. annotated bounding boxes, for training such systems, which is infeasible to harvest in large-scale. We present Probabilistic Class Activation Map (PCAM) pooling, a novel global pooling operation for lesion localization with only image-level supervision. PCAM pooling explicitly leverages the excellent localization ability of CAM during training in a probabilistic fashion. Experiments on the ChestX-ray14 dataset show a ResNet-34 model trained with PCAM pooling outperforms state-of-the-art baselines on both the classification task and the localization task. Visual examination on the probability maps generated by PCAM pooling shows clear and sharp boundaries around lesion regions compared to the localization heatmaps generated by CAM. PCAM pooling is open sourced at https://github.com/jfhealthcare/Chexpert.