Harnessing Intra-group Variations Via a Population-Level Context for Pathology Detection

arXiv:2403.02307v1 Announce Type: cross
Abstract: Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks …

abstract arxiv bias context contrast cs.cv detection eess.iv images medical notion pathology performance population samples study texture type via