Deep Mining External Imperfect Data for Chest X-ray Disease Screening

by   Luyang Luo, et al.

Deep learning approaches have demonstrated remarkable progress in automatic Chest X-ray analysis. The data-driven feature of deep models requires training data to cover a large distribution. Therefore, it is substantial to integrate knowledge from multiple datasets, especially for medical images. However, learning a disease classification model with extra Chest X-ray (CXR) data is yet challenging. Recent researches have demonstrated that performance bottleneck exists in joint training on different CXR datasets, and few made efforts to address the obstacle. In this paper, we argue that incorporating an external CXR dataset leads to imperfect training data, which raises the challenges. Specifically, the imperfect data is in two folds: domain discrepancy, as the image appearances vary across datasets; and label discrepancy, as different datasets are partially labeled. To this end, we formulate the multi-label thoracic disease classification problem as weighted independent binary tasks according to the categories. For common categories shared across domains, we adopt task-specific adversarial training to alleviate the feature differences. For categories existing in a single dataset, we present uncertainty-aware temporal ensembling of model predictions to mine the information from the missing labels further. In this way, our framework simultaneously models and tackles the domain and label discrepancies, enabling superior knowledge mining ability. We conduct extensive experiments on three datasets with more than 360,000 Chest X-ray images. Our method outperforms other competing models and sets state-of-the-art performance on the official NIH test set with 0.8349 AUC, demonstrating its effectiveness of utilizing the external dataset to improve the internal classification.


page 1

page 2

page 3

page 7


Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks

Recently, there have been several successful deep learning approaches fo...

Rethinking annotation granularity for overcoming deep shortcut learning: A retrospective study on chest radiographs

Deep learning has demonstrated radiograph screening performances that ar...

Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation

The recent trend of integrating multi-source Chest X-Ray datasets to imp...

Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification

Chest X-rays are an important and accessible clinical imaging tool for t...

A Relational-learning Perspective to Multi-label Chest X-ray Classification

Multi-label classification of chest X-ray images is frequently performed...

Semantically Redundant Training Data Removal and Deep Model Classification Performance: A Study with Chest X-rays

Deep learning (DL) has demonstrated its innate capacity to independently...

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

Given image labels as the only supervisory signal, we focus on harvestin...

Please sign up or login with your details

Forgot password? Click here to reset