cs.CVNov 6, 2026

The APL Doesn't Fall Far From The Tree: Unsupervised Artefact Prototype Learning in Histopathology

Authors: Emilia Agasi, Charlie Gourley, C. Simon Herrington, Robert L. Hollis, T. Ian Simpson

Organizations: School of Informatics, University of Edinburgh · CRUK Scotland Centre, Institute of Genetics and Cancer, University of Edinburgh

Abstract

Histopathology foundation models provide rich representations of tissue morphology, but technical artefacts in whole slide images introduce noise that may impact diagnostic accuracy. We introduce Artefact Prototype Learning (APL), a novel approach to detecting these artefacts that exploits the geometry of pre-trained embedding spaces without manual labels or fine-tuning. Rather than treating artefacts as isolated outliers, APL computes prototypes of out-of-distribution patches and uses them to distinguish artefact-associated patterns from tissue. Evaluation on a single-centre dataset shows that APL outperforms prior methods GrandQC and HistoART in detecting artefacts such as blur, dark spots, slide edges and pen marks, but struggles with tissue folds and blood. These results show that frozen pre-trained embeddings already carry information that allows artefact detection without expensive labels or vast computational resources.

Figures & tables

Explore similar work

CardsList
  1. The Effect of Tissue Detection on False Positives of Diffusion-Based Artifact Detection in Histopathology

    Sep 30, 2026Konstantinos Moutselos, Ilias MaglogiannisComputational PathologyDiffusion-Based OOD Detection

  2. Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation

    Jun 27, 2026Yishu Zhang, Shushan Wu, Zhenzhong Zhang +8Batch Effect CorrectionComputational Pathology

  3. Vision-Language Models as Zero-Annotation Oracles in Histopathology

    Jun 15, 2026Vishal Jain, Giorgio Buzzanca, Sarah Cechnicka +6Computational PathologyHistopathology Image Segmentation