2 papers
cs.CV2025
GRASPing Anatomy to Improve Pathology Segmentation
Keyi Li, Alexander Jaus, Jens Kleesiek +1
Radiologists rely on anatomical understanding to accurately delineate pathologies, yet most current deep learning approaches use pure pattern recognition and ignore the anatomical…
cs.CV2024
Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks
Alexander Jaus, Constantin Seibold, Simon Reià +6
We present Connected-Component~(CC)-Metrics, a novel semantic segmentation evaluation protocol, targeted to align existing semantic segmentation metrics to a multi-instance detecti…