Enhancing signal detectability in learning-based CT reconstruction with a model observer inspired loss function

arXiv:2402.10010v1 Announce Type: cross
Abstract: Deep neural networks used for reconstructing sparse-view CT data are typically trained by minimizing a pixel-wise mean-squared error or similar loss function over a set of training images. However, networks trained with such pixel-wise losses are prone to wipe out small, low-contrast features that are critical for screening and diagnosis. To remedy this issue, we introduce a novel training loss inspired by the model observer framework to enhance the detectability of weak signals in the …

abstract arxiv cs.cv data eess.iv error function images loss losses mean networks neural networks physics.med-ph pixel set signal small training type view wise