Accelerating COVID-19 Differential Diagnosis with Explainable Ultrasound Image Analysis

Abstract

Controlling the COVID-19 pandemic largely hinges upon the existence of fast, safe, and highly-available diagnostic tools. Ultrasound, in contrast to CT or X-Ray, has many practical advantages and can serve as a globally-applicable first-line examination technique. We provide the largest publicly available lung ultrasound (US) dataset for COVID-19 consisting of 106 videos from three classes (COVID-19, bacterial pneumonia, and healthy controls); curated and approved by medical experts. On this dataset, we perform an in-depth study of the value of deep learning methods for differential diagnosis of COVID-19. We propose a frame-based convolutional neural network that correctly classifies COVID-19 US videos with a sensitivity of 0.98+-0.04 and a specificity of 0.91+-08 (frame-based sensitivity 0.93+-0.05, specificity 0.87+-0.07). We further employ class activation maps for the spatio-temporal localization of pulmonary biomarkers, which we subsequently validate for human-in-the-loop scenarios in a blindfolded study with medical experts. Aiming for scalability and robustness, we perform ablation studies comparing mobile-friendly, frame- and video-based architectures and show reliability of the best model by aleatoric and epistemic uncertainty estimates. We hope to pave the road for a community effort toward an accessible, efficient and interpretable screening method and we have started to work on a clinical validation of the proposed method. Data and code are publicly available.

8 pages, 4 figures

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
• COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images
• POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS)
• Computer Vision For COVID-19 Control: A Survey
• COVID-19: A Survey on Public Medical Imaging Data Resources

Cited by in corpus (6)

• A Systematic Collection of Medical Image Datasets for Deep Learning
• Ultrasound Diagnosis of COVID-19: Robustness and Explainability
• The Role of Pleura and Adipose in Lung Ultrasound AI
• Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis
• USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning
• Unsupervised discovery of Interpretable Visual Concepts