CXR-Net: A Multitask Deep Learning Network for Explainable and Accurate Diagnosis of COVID-19 Pneumonia From Chest X-Ray Images

Abstract

Accurate and rapid detection of COVID-19 pneumonia is crucial for optimal patient treatment. Chest X-Ray (CXR) is the first-line imaging technique for COVID-19 pneumonia diagnosis as it is fast, cheap and easily accessible. Currently, many deep learning (DL) models have been proposed to detect COVID-19 pneumonia from CXR images. Unfortunately, these deep classifiers lack the transparency in interpreting findings, which may limit their applications in clinical practice. The existing explanation methods produce either too noisy or imprecise results, and hence are unsuitable for diagnostic purposes. In this work, we propose a novel explainable CXR deep neural Network (CXR-Net) for accurate COVID-19 pneumonia detection with an enhanced pixel-level visual explanation using CXR images. An Encoder-Decoder-Encoder architecture is proposed, in which an extra encoder is added after the encoder-decoder structure to ensure the model can be trained on category samples. The method has been evaluated on real world CXR datasets from both public and private sources, including healthy, bacterial pneumonia, viral pneumonia and COVID-19 pneumonia cases. The results demonstrate that the proposed method can achieve a satisfactory accuracy and provide fine-resolution activation maps for visual explanation in the lung disease detection. The Average Accuracy, Sensitivity, Specificity, PPV and F1-score of models in the COVID-19 pneumonia detection reach 0.992, 0.998, 0.985 and 0.989, respectively. Compared to current state-of-the-art visual explanation methods, the proposed method can provide more detailed, high-resolution, visual explanation for the classification results. It can be deployed in various computing environments, including cloud, CPU and GPU environments. It has a great potential to be used in clinical practice for COVID-19 pneumonia diagnosis.

A Multi-Task Deep Learning Framework for Simultaneous Detection of Thoracic Pathology through Image Classification

“…The achieved accuracy for CT scan images was 98.78% and for X-ray images was around 84.67%. The authors in [27] described a new framework that relies on the encoder-decoder multi-task model. They have used the CXR real-world dataset which contains healthy, bacterial pneumonia, viral pneumonia, and COVID-19 pneumonia images.…”

Deep Learning and Federated Learning for Screening COVID-19: A Review

“…Recent research publications on AI for the management or detection of COVID-19 are available . Some of these papers concentrate on FL approaches [133][134][135][136][137][138][139][140][141][142][143][144][145], some on survey work on DL [146][147][148][149][150][151][152][153][154], and yet others on original research works on DL [125][126][127][128][129][130][131][132][155][156][157][158][159][160][161][162][163][164][165].…”

Recent Machine Learning and Deep Learning Theories and Methods for COVID-19 Diagnosis

“…The problem of interpreting the very difficult output of current deep learning models is compounded by the lack of reliable measures of uncertainty [49]. Interpretability is key to medical diagnosis, and understanding the reasons for decisions is viewed as important as the need for decisions [50]. Interpretable machine learning and deep learning techniques are actively being researched to address this issue [51][52][53], but they remain a challenge in many applications.…”