The Utility of the Virtual Imaging Trials Methodology for Objective Characterization of AI Systems and Training Data
This work addresses the problem of unreliable AI in medical imaging for clinicians and researchers, offering an incremental improvement through objective assessment methods.
The study tackled the challenge of credibility in AI models for medical imaging by exploring Virtual Imaging Trials (VIT) methodologies, finding that models trained on diverse datasets achieved external testing AUCs of 0.73-0.76 for CT and 0.70-0.73 for CXR, with a substantial performance drop in external validation highlighting data diversity importance.
Purpose: The credibility of Artificial Intelligence (AI) models for medical imaging continues to be a challenge, affected by the diversity of models, the data used to train the models, and applicability of their combination to produce reproducible results for new data. In this work, we aimed to explore whether emerging Virtual Imaging Trials (VIT) methodologies can provide an objective resource to approach this challenge. Approach: The study was conducted for the case example of COVID-19 diagnosis using clinical and virtual computed tomography (CT) and chest radiography (CXR) processed with convolutional neural networks. Multiple AI models were developed and tested using 3D ResNet-like and 2D EfficientNetv2 architectures across diverse datasets. Results: Model performance was evaluated using the area under the curve (AUC) and the DeLong method for AUC confidence intervals. The models trained on the most diverse datasets showed the highest external testing performance, with AUC values ranging from 0.73-0.76 for CT and 0.70-0.73 for CXR. Internal testing yielded higher AUC values (0.77-0.85 for CT and 0.77-1.0 for CXR), highlighting a substantial drop in performance during external validation, which underscores the importance of diverse and comprehensive training and testing data. Most notably, the VIT approach provided objective assessment of the utility of diverse models and datasets, while offering insight into the influence of dataset characteristics, patient factors, and imaging physics on AI efficacy. Conclusions: The VIT approach enhances model transparency and reliability, offering nuanced insights into the factors driving AI performance and bridging the gap between experimental and clinical settings.