BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification

TL;DR

This paper introduces BoMD, a novel method for robust multi-label chest X-ray classification from noisy labels, leveraging semantic descriptors to improve accuracy and robustness in medical imaging tasks.

Contribution

The paper proposes a new approach that detects and re-labels noisy samples in multi-label CXR datasets using semantic descriptors, enhancing classification robustness.

Findings

Achieves state-of-the-art accuracy on noisy multi-label CXR datasets.

Demonstrates robustness to label noise in diverse datasets.

Outperforms existing methods in multi-label classification benchmarks.

Abstract

Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually annotated with clean labels. However, given the high cost of such manual annotation, new medical imaging classification problems may need to rely on machine-generated noisy labels extracted from radiology reports. Indeed, many Chest X-ray (CXR) classifiers have already been modelled from datasets with noisy labels, but their training procedure is in general not robust to noisy-label samples, leading to sub-optimal models. Furthermore, CXR datasets are mostly multi-label, so current noisy-label learning methods designed for multi-class problems cannot be easily adapted. In this paper, we propose a new method designed for the noisy multi-label CXR learning, which detects and smoothly re-labels samples from the dataset, which is then used to train common multi-label classifiers. The proposed method optimises a bag of multi-label descriptors (BoMD) to promote their similarity with the semantic descriptors produced by BERT models from the multi-label image annotation. Our experiments on diverse noisy multi-label training sets and clean testing sets show that our model has state-of-the-art accuracy and robustness in many CXR multi-label classification benchmarks.