DML‐OFA: Deep mutual learning with online feature alignment for the detection of COVID‐19 from chest x‐ray images

• Published in: Concurrency and Computation: Practice and Experience
• Main Authors: Liang, Zhihao, Lu, Huijuan, Ming, Zhendong, Chai, Zhuijun, Yao, Yudong
• Other Authors: Science and Technology Program of Zhejiang Province, Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China
• Format: Article in Journal/Newspaper
• Language: English
• Published: Wiley 2024
• Subjects: DML
• Online Access: http://dx.doi.org/10.1002/cpe.8023; https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.8023

Summary COVID‐19 is a novel coronavirus‐induced disease and automatic identification of COVID‐19 using computer‐assisted methods can facilitate faster diagnostic efficiency. Current research typically employs a single model for COVID‐19 identification, while implicit and complementary knowledge between heterogeneous networks is neglected. To address these issues, we propose a new model based on deep mutual learning with online feature alignment called DML‐OFA to more effectively diagnose COVID‐19. First, we use a traditional deep mutual learning (DML) framework to allow two parallel heterogeneous networks to learn from each other to form two effective feature extractors. In addition, we embed the adaptive feature fusion classifier and logits ensembling module in the proposed DML‐OFA, which can simultaneously learn implicit complementary knowledge from feature maps and logits. We evaluated DML‐OFA on four public datasets: Covid‐chestxray‐dataset, ChestXRay2017, Coronavirus‐dataset and COVIDx. The results showed that our model attains 97.10 Accuracy, 97.28 Specificity, 96.21 Recall, 97.45 Precision, and 96.82 F1‐score, which outperforms other previous related works.