The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2608.30835v1 Announce Type: cross Abstract: Background and Objective: Quality control is a prerequisite for whole-slide image analysis, yet the benchmarks on which quality-control methods are c...
arXiv:2609.40083v1 Announce Type: cross Abstract: One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by...
One-class artifact detectors for whole-slide images learn normal tissue from a clean training pool and flag departures from it. The pool is built by a preprocessing pipeline whose tissue-detection ste...
The paper introduces RIQE, a reference-free image quality evaluator for computed tomography that mirrors the NIQE framework used for photographs. Trained on 3,792 full‑dose CT slices from 158 patients, RIQE consistently ranks reduced‑dose reconstructions lower than their full‑dose counterparts and correctly identifies increased noise levels, but its preferences for filtered images do not align with lesion visibility. The authors caution that RIQE should not be the sole metric for selecting or tuning denoising algorithms.
The Natural Image Quality Evaluator (NIQE) scores an image by its statistical distance from a model fitted on pristine images, and its distributed model is fitted on photographs. We release the Radiol...
arXiv:2609.24116v1 Announce Type: new Abstract: Although deep learning has advanced Whole Slide Image (WSI) Analysis, tissue artifacts like bubbles and folds often cause silent failures by concealing...