PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 14, 2026Journal of Pathology Informatics0 citationsOpen Access

GrandQC AI Tool for Quantitative Artifact Detection in Whole-Slide Images

GrandQC adaptation as an artificial intelligence tool for quantitative artifact detection in hematoxylin and eosin whole-slide images—Simulation of quality control biopsies day

View Full Paper
Ask AI
Bookmark
Share

Authors

GBGonçalo BorrechoPNPedro NinaRSRicardo Santos

Discussion

Loading...

Member takes

Overview

Operational feasibility study evaluates automated artifact assessment in digital pathology biopsies.

Key Points

  • This study aims to evaluate the efficacy of GrandQC in automating quantitative artifact detection in whole-slide images from biopsies.
  • Retrospective analysis of 544 whole-slide images generated from a single day of biopsy workload.
  • Creation of a script to quantify and register pixel data for different artifact types.
  • Statistical analysis performed on the collected artifact data.
  • Detection of artifacts occurred in a median of 24 seconds per whole-slide image.
  • Median percentage of tissue area affected by artifacts was found to be 1.46%.
  • Dark spots and blurring were identified as the most common artifact types.

Cite This Study

Borrecho et al. (2026) studied this question.

synapsesocial.com/papers/6a2e44e4b1cc60ccdea8a46fhttps://doi.org/10.1016/j.jpi.2026.100682
View Full Paper
Ask AI
Bookmark
Share