Are Convolutional Neural Networks Trained on <scp>ImageNet</scp> Images Wearing <scp>Rose‐Colored</scp> Glasses?: A Quantitative Comparison of <scp>ImageNet</scp>, Computed Tomographic, Magnetic Resonance, Chest <scp>X‐Ray</scp>, and <scp>Point‐of‐Care</scp> Ultrasound Images for Quality

Abstract

Point-of-care ultrasound (US) quality is significantly different from that of ImageNet and other medical images. This brings considerable implications for convolutional neural network training with medical images for various applications, which may be even more significant in the case of US images. Ultrasound deep learning developers should consider pretraining networks from scratch on US images, as training techniques used for CT, CXR, and MR images may not apply to US.