Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks

arXiv:2306.14572v2 Announce Type: replace-cross
Abstract: Feature-Imitating-Networks (FINs) are neural networks that are first trained to approximate closed-form statistical features (e.g. Entropy), and then embedded into other networks to enhance their performance. In this work, we perform the first evaluation of FINs for biomedical image processing tasks. We begin by training a set of FINs to imitate six common radiomics features, and then compare the performance of larger networks (with and without embedding the FINs) for three experimental tasks: COVID-19 detection …

abstract arxiv biomedical cs.cv cs.lg deep learning eess.iv embedded entropy evaluation feature features form image image processing networks neural networks performance processing reliability speed statistical tasks type work