Parallel Training Using a CNN-DNN Architecture for Accelerated Development of Diagnostic Models

Abstract

Artificial intelligence has shown promise in assisting radiologists in imaging-based diagnosis across a wide range of diseases. Efficient training of large deep learning models is essential to cope with extremely large data sets or dynamically growing disease data, like in a pandemic like situation. In this retrospective study, we collected 300 CT scans from COVID-19 and non-COVID-19 pneumonia patients from three different centers in Germany. We investigated a hybrid CNN-DNN network model based on image decomposition and localization that naturally supports parallel and efficient training of deep learning models. In total, 156 models with three different architectures were trained to capture features at different levels resulting in 12 patient-level COVID-19 diagnosis models. Diagnostic performance as well as time saving were measured. The highest accuracy was obtained from DenseNet121 and 3D CNN models with a parallel CNN-DNN approach, resulting in $88.78\%$ training, $76.67\%$ validation and $76.03\%$ test accuracy for the DenseNet121 with $4\times 4\times 1$ subdomains and $87.72\%$ training, $76.82\%$ validation and $74.86\%$ test accuracy, respectively, for the 3D CNN with $4\times 4\times 1$ subdomains. The strongest reduction in parallel training time by a factor of $31$ was observed for the 3D CNN model and $4\times 4\times 2$ subdomains. Our parallel training approach improves efficiency as well as performance enabling rapid model development, among others crucial for pandemic preparedness.