AI RESEARCH

Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling

arXiv CS.CV

ArXi:2508.06805v2 Announce Type: replace Accurate localization of organ boundaries is critical in medical imaging for segmentation, registration, surgical planning, and radiotherapy. While deep convolutional networks (ConvNets) have advanced general-purpose edge detection to near-human performance on natural images, their outputs often lack precise localization, a limitation that is particularly harmful in medical applications where millimeter-level accuracy is required.