A Dual-Branch Network for Diagnosis of Thorax Diseases From Chest X-Rays

• Published in: IEEE journal of biomedical and health informatics Vol. 26; no. 12; pp. 6081 - 6092
• Main Authors: Chowdary, G. Jignesh, Kanhangad, Vivek
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Chest; Chest X-ray Classification; Chest X-ray Segmentation; Classification; Datasets; Diagnosis; Diseases; Feature extraction; Humans; Image segmentation; Lung; Lungs; Medical diagnosis; Medical diagnostic imaging; Multi-label Classification; Neural networks; Neural Networks, Computer; Nodules; Radiography, Thoracic - methods; Recurrent neural networks; Segmentation; Thorax; Thorax - diagnostic imaging; Thorax Disease Diagnosis; Transfer learning; X ray analysis; X-ray imaging; X-Rays
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2022.3215694

Automated chest X-ray analysis has a great potential for diagnosing thorax diseases since errors in diagnosis have always been a concern among radiologists. Being a multi-label classification problem, achieving accurate classification remains challenging. Several studies have focused on accurately segmenting the lung regions from the chest X-rays to deal with the challenges involved. The features extracted from the lung regions typically provide precise clues for diseases like nodules. However, such methods ignore the features outside the lung regions, which have been shown to be crucial for diagnosing conditions like cardiomegaly. Therefore, in this work, we explore a dual-branch network-based framework that relies on features extracted from the lung regions as well as the entire chest X-rays. The proposed framework uses a novel network named R-I UNet for segmenting the lung regions. The dual-branch network in the proposed framework employs two pre-trained AlexNet models to extract discriminative features, forming two feature vectors. Each feature vector is fed into a recurrent neural network consisting of a stack of gated recurrent units with skip connections. Finally, the resulting feature vectors are concatenated for classification. The proposed models achieve state-of-the-art performance for both segmentation and classification tasks on the benchmark datasets. Specifically, our lung segmentation model achieves a 5-fold cross-validation accuracy of 98.18<inline-formula><tex-math notation="LaTeX">\%</tex-math></inline-formula> and 99.14<inline-formula><tex-math notation="LaTeX">\%</tex-math></inline-formula> on Montgomery (MC) and JSRT datasets. For classification, the proposed approach achieves state-of-the-art AUC for 9 out of 14 diseases with a mean AUC of 0.842 on the NIH ChestXray14 dataset.