An X-Ray is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation
This is an archival link-post for our preprint, which can be found here. Figure 1: SAE-Rad identifies clinically relevant and interpretable features within radiological images. We illustrate a number of pathological and instrumentation features relevant for producing radiology reports. We add annotations (green arrows) to emphasize the presence of each...