Pre-trained convolutional neural network with transfer learning by artificial illustrated images classify power Doppler ultrasound images of rheumatoid arthritis joints

This research aimed to study the classification performance of a pre-trained convolutional neural network (CNN) with transfer learning by artificial images of the joint ultrasonography in rheumatoid arthritis (RA). We focused on abnormal synovial vascularity and created 870 artificial ultrasound joint images based on the European League Against Rheumatism/Outcome Measure in Rheumatology scoring system. One CNN, the Visual Geometry Group (VGG)-16 was trained with transfer learning using the 870 artificial images for initial training and the original plus five additional images for second training. Actual joint ultrasound images obtained from patients with RA were used for testing our models. We obtained 156 actual ultrasound joint images from 74 patients with RA. Our initial model showed moderate classification performance, but grade 1 was especially low (area under curve (AUC) 0.59). In our second model, grade 1 showed improvement (AUC 0.73). We concluded that artificial images were useful for training VGG-16. Our novel approach of using artificial images as an alternative to actual images for training CNN has the potential to be applied in medical imaging fields that face difficulties in collecting real clinical images.