Harnessing Intra-group Variations Via a Population-Level Context for Pathology Detection
This work addresses a critical obstacle in medical imaging for pathology detection, though it is incremental as it primarily refines existing methods with limited adaptation to texture-based images.
The study tackled the problem of insufficient separability between healthy and pathological samples in pathology detection models, especially for texture-based medical images, by introducing a population-level context via a graph-theoretic approach called PopuSense, which improved separability in contrast-based images.
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 to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Proof-of-concept experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model.