# Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays

arXiv: https://arxiv.org/abs/1807.00958 · HTML: https://mlsanity.com/paper/1807.00958/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 10 of 10)

- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification](https://mlsanity.com/paper/2210.12843/) (2022)
- [AnaXNet: Anatomy Aware Multi-label Finding Classification in Chest X-ray](https://mlsanity.com/paper/2105.09937/) (2021)
- [Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment](https://mlsanity.com/paper/2104.05261/) (2021)
- [Weakly Supervised Thoracic Disease Localization via Disease Masks](https://mlsanity.com/paper/2101.09915/) (2021)
- [ThoraX-PriorNet: A Novel Attention-Based Architecture Using Anatomical Prior Probability Maps for Thoracic Disease Classification](https://mlsanity.com/paper/2210.02998/) (2022)
- [GREN: Graph-Regularized Embedding Network for Weakly-Supervised Disease Localization in X-ray Images](https://mlsanity.com/paper/2107.06442/) (2021)
- [Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance](https://mlsanity.com/paper/2207.00251/) (2022)
- [A distillation based approach for the diagnosis of diseases](https://mlsanity.com/paper/2108.03470/) (2021)
- [Taxlifier: Leveraging Disease Taxonomy for Enhanced Multi-Label Classification in Chest Radiography](https://mlsanity.com/paper/2607.05628/) (2026)

## Abstract (arXiv)

Given image labels as the only supervisory signal, we focus on harvesting, or mining, thoracic disease localizations from chest X-ray images. Harvesting such localizations from existing datasets allows for the creation of improved data sources for computer-aided diagnosis and retrospective analyses. We train a convolutional neural network (CNN) for image classification and propose an attention mining (AM) strategy to improve the model's sensitivity or saliency to disease patterns. The intuition of AM is that once the most salient disease area is blocked or hidden from the CNN model, it will pay attention to alternative image regions, while still attempting to make correct predictions. However, the model requires to be properly constrained during AM, otherwise, it may overfit to uncorrelated image parts and forget the valuable knowledge that it has learned from the original image classification task. To alleviate such side effects, we then design a knowledge preservation (KP) loss, which minimizes the discrepancy between responses for X-ray images from the original and the updated networks. Furthermore, we modify the CNN model to include multi-scale aggregation (MSA), improving its localization ability on small-scale disease findings, e.g., lung nodules. We experimentally validate our method on the publicly-available ChestX-ray14 dataset, outperforming a class activation map (CAM)-based approach, and demonstrating the value of our novel framework for mining disease locations.