Amfp-Net: Adaptive Multi-Scale Feature Pyramid Network for Diagnosis of Pneumoconiosis from Chest X-Ray Images

Abstract

Early detection of pneumoconiosis through routine health screening of workers in the mining industry is critical for preventing the progression of this incurable disease. Automated pneumoconiosis classification in chest X-ray (CXR) images is challenging due to the low contrast of opacities, inter-class similarity, intra-class variation and the existence of artifacts. Compared to traditional methods, convolutional neural networks (CNNs) have shown significant improvement in pneumoconiosis classification tasks, however, accurate classification remains challenging due to insufficient training data, and inability to focus on semantically meaningful lesion opacities. Most existing CNNs focus on high-level abstract information and ignore low-level detailed object information. Different from natural images where an object occupies large space, the classification of pneumoconiosis depends on the density of small opacities inside the lung. To address these issues, we propose a novel two-stage adaptive multi-scale feature pyramid network (AMFP-Net) for the diagnosis of pneumoconiosis from chest X-rays. The proposed model consists of 1) an adaptive multi-scale context (AMC) block to extract rich contextual and discriminative information and 2) a weighted feature fusion (WFF) module to effectively combine low-level detailed and high-level global semantic information. This two-stage network first segments the lungs to focus more on relevant regions by excluding irrelevant parts of the image, and then utilises the segmented lungs to classify pneumoconiosis into different categories. Extensive experiments on public and private datasets demonstrate that the proposed approach can outperform state-of-the-art (SOTA) methods for both segmentation and classification.

Note:
Funding Declaration: This work was funded in part by Coal Services Health and Safety Trust Project No. 20656, and approved by CSIRO Health and Medical Human Research Ethics Committee, approval number: LR 22/2016.

Conflicts of Interest: None

Ethical Approval: Approved by CSIRO Health and Medical Human Research Ethics Committee, approval number: LR 22/2016.

Keywords: Pneumoconiosis classification, Lung segmentation, Deep neural networks, Adaptive multi-scale feature, Weighted feature fusion, Chest X-ray image