ViDi: Descriptive Visual Data Clustering as Radiologist Assistant in COVID-19 Streamline Diagnostic
Published in preprint, 2021
Sahithya Ravi, Samaneh Khoshrou and Mykola Pechenizkiy
In this paper, we investigate state-of-the-art models for covid detection from chest-xrays. We generate homogeneous clusters in terms of disease severity and interpret the clusters using favorable and unfavorable saliency maps, which visualize the class discriminating regions of an image. These human-interpretable maps complement radiologist knowledge to investigate the whole batch at once. Keywords: Interpretable Machine learning, human-in-the-loop
Download here