Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling

arXiv:2404.03991v1 Announce Type: cross
Abstract: Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accurately and predict detailed labels, resulting in diminished performance compared to processing at original resolutions. This situation exemplifies the trade-off between efficiency and accuracy, with higher downsampling factors further impairing segmentation outcomes. Preserving information during downsampling is especially critical for medical image …

abstract arxiv capacity cs.cv cs.lg downsampling edge eess.iv images labels leads loss network network training objects performance processing resources segmentation small training type via