Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling

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.

Cited by in corpus (11)

• ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs
• Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
• VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels
• Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
• ThoraX-PriorNet: A Novel Attention-Based Architecture Using Anatomical Prior Probability Maps for Thoracic Disease Classification
• Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification
• Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features
• Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels
• Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
• Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis