Visual Transformers and Convolutional Neural Networks for Disease Classification on Radiographs: A Comparison of Performance, Sample Efficiency, and Hidden Stratification

Abstract

Although DeiT models had lower wAUCs than CNNs for chest radiograph and extremity domains, the differences may be negligible in clinical practice. DeiT-B had sample efficiency similar to that of DenseNet121 and may be less susceptible to certain types of hidden stratification.<b>Keywords:</b> Computer-aided Diagnosis, Informatics, Neural Networks, Thorax, Skeletal-Appendicular, Convolutional Neural Network (CNN), Feature Detection, Supervised Learning, Machine Learning, Deep Learning <i>Supplemental material is available for this article.</i> © RSNA, 2022.