paper-with-me

Papers

Efficient Special Stain Classification

2026-02-10 · Oskar Thaeter, Christian Grashei, Anette Haas, Elisa Schmoeckel, Han Li, Peter J. Schüffler arxiv

Stains are essential in histopathology to visualize specific tissue characteristics, with Haematoxylin and Eosin (H&E) serving as the clinical standard. However, pathologists frequently utilize a variety of special stains for the diagnosis of specific morphologies. Maintaining accurate metadata for these slides is critical for quality control in clinical archives and for the integrity of computational pathology datasets. In this work, we compare two approaches for automated classification of stains using whole slide images, covering the 14 most commonly used special stains in our institute alongside standard and frozen-section H&E. We evaluate a Multi-Instance Learning (MIL) pipeline and a proposed lightweight thumbnail-based approach. On internal test data, MIL achieved the highest performance (macro F1: 0.941 for 16 classes; 0.969 for 14 merged classes), while the thumbnail approach remained competitive (0.897 and 0.953, respectively). On external TCGA data, the thumbnail model generalized best (weighted F1: 0.843 vs. 0.807 for MIL). The thumbnail approach also increased throughput by two orders of magnitude (5.635 vs. 0.018 slides/s for MIL with all patches). We conclude that thumbnail-based classification provides a scalable and robust solution for routine visual quality control in digital pathology workflows.

📄 PDF Abstract BibTeX arXiv:2602.09989

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

StainNet: Scaling Self-Supervised Foundation Models on Immunohistochemistry and Special Stains for Computational Pathology

2025-12-11 · Jiawen Li, Jiali Hu, Xitong Ling, Yongqiang Lv 외 arxiv

Foundation models trained with self-supervised learning (SSL) on large-scale histological images have significantly accelerated the development of computational pathology. These models can serve as backbones for region-o…

Multiple Instance LearningSelf-Supervised Learning

DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases

2023-04-21 · Taiji Kurami, Takuya Ishikawa, Kazuhiro Hotta

Endoscopic Ultrasound-Fine Needle Aspiration (EUS-FNA) is used to examine pancreatic cancer. EUS-FNA is an examination using EUS to insert a thin needle into the tumor and collect pancreatic tissue fragments. Then collec…

image-classificationImage Classification

Deep learning-based transformation of the H&E stain into special stains

2020-08-20 · Kevin de Haan, Yijie Zhang, Jonathan E. Zuckerman, Tairan Liu 외

Pathology is practiced by visual inspection of histochemically stained slides. Most commonly, the hematoxylin and eosin (H&E) stain is used in the diagnostic workflow and it is the gold standard for cancer diagnosis. How…

Diagnostic

Interdisciplinary Business Games on Sustainable Development: Theoretical Foundations and Prospects of Implementation

2015-05-28

The article defines the place of business games among all games in general based on the classification by F.G. Junger; it provides critical analysis of existing business games types; it also formulates requirements and l…

RestainNet: a self-supervised digital re-stainer for stain normalization

2022-02-28 · Bingchao Zhao, Jiatai Lin, Changhong Liang, Zongjian Yi 외

Color inconsistency is an inevitable challenge in computational pathology, which generally happens because of stain intensity variations or sections scanned by different scanners. It harms the pathological image analysis…

Self-Supervised Learning