Tissue Detection Determines False Positives in Diffusion-Based Histopathology Artifact Detection

2026-09-30

AI Summary

This study addresses the high false positive rate of diffusion models in pathological artifact detection caused by the overlooked tissue preprocessing step. For the first time, we demonstrate that tissue detection is a non-neutral procedure and reveal a strong correlation between the proportion of transparent space and false positives. Leveraging the TCGA dataset and an external cohort, this work employs entropy-based tissue segmentation to optimize training pool construction and proposes a label-free statistical metric for evaluating data pool quality. Experimental results show that the proposed method reduces the false positive rate from 0.102 to 0.016 while maintaining sensitivity, and decreases false alarms on the external cohort by approximately 20%. These findings establish the critical role of tissue detection in one-class anomaly detection frameworks.

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 a preprocessing pipeline whose tissue-detection step is usually treated as neutral. We tested whether it is. On 16 annotated TCGA slides, we rebuilt the clean pool of a diffusion-based detector with different tissue detection methods and compared the resulting models in a four-fold cross-validation. Per-slide saturation-Otsu detection excluded normal tissue, chiefly tissue with large clear spaces such as adipose tissue and alveolar parenchyma, and on slides with thick marker ink kept the ink while excluding ordinary tissue. Replacing it with entropy-based detection reduced the false-positive fraction on held-out clean slides from 0.102 to 0.016, in every fold and with a second training seed, without loss of sensitivity; the gain came from the composition of the pool, not its size. Across three tissue detection methods, false positives followed the fraction of such clear-space tissue in the pool, a statistic that needs no labels or training (0.103, 0.016 and 0.009). The effect did not carry over at the same size to a nearest-neighbour detector on foundation-model features. On an external cohort, the curated pool lowered clean-control false positives by about 20%, far less than within TCGA, and the remaining cross-center loss was not explained by stain differences. For one-class quality control, tissue detection decides what the model learns as normal and should be chosen and reported accordingly.

Problem

• Histopathology artifact detection
• Tissue detection
• False positives
• One-class learning
• Whole-slide images

Innovation

• Histopathology Artifact Detection
• Diffusion Model
• One-class Learning
• Tissue Detection
• False Positive Reduction