Paper
InfoMask: Masked Variational Latent Representation to Localize Chest\n Disease
The scarcity of richly annotated medical images is limiting supervised deep\nlearning based solutions to medical image analysis tasks, such as localizing\ndiscriminatory radiomic disease signatures. Therefore, it is desirable to\nleverage unsupervised and weakly supervised models. Most recent weakly\nsupervised localization methods apply attention maps or region proposals in a\nmultiple instance learning formulation. While attention maps can be noisy,\nleading to erroneously highlighted regions, it is not simple to decide on an\noptimal window/bag size for multiple instance learning approaches. In this\npaper, we propose a learned spatial masking mechanism to filter out irrelevant\nbackground signals from attention maps. The proposed method minimizes mutual\ninformation between a masked variational representation and the input while\nmaximizing the information between the masked representation and class labels.\nThis results in more accurate localization of discriminatory regions. We tested\nthe proposed model on the ChestX-ray8 dataset to localize pneumonia from chest\nX-ray images without using any pixel-level or bounding-box annotations.\n
Authors: Taghanaki, Saeid Asgari · Havaei, Mohammad · Berthier, Tess · Dutil, Francis · Di Jorio, Lisa · Hamarneh, Ghassan · Bengio, Yoshua