Z-Stack Scanning can Improve AI Detection of Mitosis: A Case Study of Meningiomas
🤖 AI Summary
Digital pathology AI systems often underperform in detecting mitotic figures in meningiomas due to limited depth-of-field in conventional single-plane whole-slide images (WSIs), leading to suboptimal diagnostic reliability.
Method: We acquired both single-plane and Z-stack WSIs from 22 H&E-stained meningioma slides across three digital pathology scanners, then developed and evaluated three deep learning–based mitosis detection pipelines.
Contribution/Results: This study provides the first quantitative evidence that Z-stack imaging significantly improves AI detection sensitivity for mitoses (+17.14%, *p* < 0.01) without compromising precision. The performance gain is consistent across all scanner–AI combinations, demonstrating robustness. These findings confirm that Z-stack acquisition enhances AI robustness for focal-depth–sensitive microstructures—such as mitotic figures—and establish a generalizable, empirically validated technical strategy to improve the reliability of AI-assisted pathological diagnosis.
Application Category
📝 Abstract
Z-stack scanning is an emerging whole slide imaging technology that captures multiple focal planes alongside the z-axis of a glass slide. Because z-stacking can offer enhanced depth information compared to the single-layer whole slide imaging, this technology can be particularly useful in analyzing small-scaled histopathological patterns. However, its actual clinical impact remains debated with mixed results. To clarify this, we investigate the effect of z-stack scanning on artificial intelligence (AI) mitosis detection of meningiomas. With the same set of 22 Hematoxylin and Eosin meningioma glass slides scanned by three different digital pathology scanners, we tested the performance of three AI pipelines on both single-layer and z-stacked whole slide images (WSIs). Results showed that in all scanner-AI combinations, z-stacked WSIs significantly increased AI's sensitivity (+17.14%) on the mitosis detection with only a marginal impact on precision. Our findings provide quantitative evidence that highlights z-stack scanning as a promising technique for AI mitosis detection, paving the way for more reliable AI-assisted pathology workflows, which can ultimately benefit patient management.
Problem
Research questions and friction points this paper is trying to address.
Z-stack scanning technique
Artificial Intelligence
Meningioma cell division
Innovation
Methods, ideas, or system contributions that make the work stand out.
Z-Stack scanning technology
AI performance enhancement
medical diagnostics potential
🔎 Similar Papers
No similar papers found.
