Truace
Subscribe

French data show up to 25.5% of lab tissue slides have technical flaws that can hinder AI

Study title: Current quality challenges in H&E preparation: The critical foundation for increased use of digital pathology and AI emergence

A peer-reviewed analysis of French national external quality assessment data from 2019-2024 and a 2024 survey found frequent H&E preparation issues: up to 25.5% of slides had technical imperfections such as sectioning, thickness, and stretching problems, and 8.3% to 23.8% had suboptimal staining with poor nucleo-cytoplasmic contrast or intensity fluctuations.

Read the study abstract

Hematoxylin and Eosin (H&E) glass slide preparation is fundamental to histopathology. Pathologists' expertise routinely mitigates potential issues due to quality variability into or across laboratories, ensuring diagnostic accuracy. However, as artificial intelligence (AI) induced by whole slide imaging (WSI) emerges as a future advancement in pathology, a shift toward greater technical standardisation of the preparations or adaptive algorithms deserves consideration. This study examined longitudinal data (2019-…

By the Truvace desk1 min read1 sourceEvidence: Moderate · 60/100 — Observational study · 1 independent sourcePeer-reviewedTRV-2026-1087· cite & verify
Current quality challenges in H&E preparation: The critical foundation for increased use of digital pathology and AI emergence
"Respiratory bronchiolitis" by Pulmonary Pathology is licensed under CC BY-SA 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/2.0/.

In brief

The findings matter because AI induced by whole slide imaging depends on consistent high-quality slides; without pre-analytical standardization, AI deployment faces higher computational costs, environmental impact, and ethical transparency risks, and it remains uncertain whether adaptive algorithms can compensate or whether labs outside France show similar defect rates.

Main points

  1. Analysis used longitudinal data (2019-2024) from the French national external quality assessment programme plus a 2024 national survey.
  2. Technical imperfections included issues from microtomic sectioning, excessive thickness, and tissue stretching.
  3. Staining problems were mainly insufficient nucleo-cytoplasmic contrast or intensity fluctuations.
  4. Authors argue against reliance on hypothetical post-hoc algorithmic compensation for poor inputs.

The problem

Up to a quarter of H&E slides in French labs showed technical preparation imperfections and up to 23.8% showed suboptimal staining, creating inconsistent inputs that undermine robust AI performance from whole slide imaging.

The rundown

The study quantified defects across French laboratories using EQA assessments, finding preparation imperfections linked to microtomy, thickness, and stretching, and staining defects linked to contrast and intensity.

Pathologists currently mitigate variability to ensure diagnostic accuracy, but the authors warn this human compensation will not scale to AI workflows that need standardized inputs.

The authors advocate sustained quality improvement at the source before large-scale AI integration, rather than expecting algorithms to correct poor slides after scanning.

Sources

  1. Peer-reviewedVirchows Archiv2026-09-12

The debate