From Lab to Pocket: A Novel Continual Learning-based Mobile Application for Screening COVID-19

TL;DR

A novel continual learning-based approach for screening COVID-19 and presents the design and implementation of a mobile application that demonstrates the ability to adapt to evolving datasets, including data collected from different locations or hospitals, varying virus strains, and diverse clinical presentations, without retraining from scratch.

Abstract

Artificial intelligence (AI) has emerged as a promising tool for predicting COVID-19 from medical images. In this paper, we propose a novel continual learning-based approach and present the design and implementation of a mobile application for screening COVID-19. Our approach demonstrates the ability to adapt to evolving datasets, including data collected from different locations or hospitals, varying virus strains, and diverse clinical presentations, without retraining from scratch. We have evaluated state-of-the-art continual learning methods for detecting COVID-19 from chest X-rays and selected the best-performing model for our mobile app. We evaluated various deep learning architectures to select the best-performing one as a foundation model for continual learning. Both regularization and memory-based methods for continual learning were tested, using different memory sizes to develop the optimal continual learning model for our app. DenseNet161 emerged as the best foundation model with 96.87\% accuracy, and Learning without Forgetting (LwF) was the top continual learning method with an overall performance of 71.99\%. The mobile app design considers both patient and doctor perspectives. It incorporates the continual learning DenseNet161 LwF model on a cloud server, enabling the model to learn from new instances of chest X-rays and their classifications as they are submitted. The app is designed, implemented, and evaluated to ensure it provides an efficient tool for COVID-19 screening. The app is available to download from https://github.com/DannyFGitHub/COVID-19PneumoCheckApp.

Figures (7)

• Figure 1: An overview of our methodology.
• Figure 2: In addition to the original unaltered dataset, cropping and lung segmentation were used as preprocessing strategies. Another set of images was generated by individually applying histogram equalization to each preprocessing strategy.
• Figure 3: This architecture encompasses a mobile application, continual learning server, and a database.
• Figure 4: Diagram illustrating the interaction between the View, ViewModel, and Model in the MVVM design pattern.
• Figure 5: Depiction of the sequential operation of the Chest X-ray validator (Classifier 1) and the inference logic for the continual learning model (Classifier 2), demonstrating the application's approach to image validation and disease classification.