Journal of Pathology Informatics最新文献

{"title":"Toward comprehensive cellular characterization of H&E slides","authors":"Benjamin Adjadj,&nbsp;Pierre-Antoine Bannier,&nbsp;Guillaume Horent,&nbsp;Sebastien Mandela,&nbsp;Gary Klajer,&nbsp;Aurore Lyon,&nbsp;Kathryn Schutte,&nbsp;Ulysse Marteau,&nbsp;Valentin Gaury,&nbsp;Laura Dumont,&nbsp;Thomas Mathieu,&nbsp;Reda Belbahri,&nbsp;Benoît Schmauch,&nbsp;Eric Durand,&nbsp;Katharina Von Loga,&nbsp;Lucie Gillet","doi":"10.1016/j.jpi.2026.100696","DOIUrl":"10.1016/j.jpi.2026.100696","url":null,"abstract":"<div><div>Cell detection, segmentation, and classification are essential for analyzing tumor microenvironments (TME) on hematoxylin and eosin (H&amp;E) slides. Existing methods suffer from poor performance on understudied cell types (rare or not present in public datasets) and limited cross-domain generalization. To address these shortcomings, we introduce HistoPLUS, a state-of-the-art model for cell analysis, trained on a novel curated pan-cancer dataset of 108,722 nuclei covering 13 cell types. In external validation across 4 independent cohorts, HistoPLUS outperforms current state-of-the-art models in detection quality by 5.2% and overall F1 classification score by 23.7%, while using 5× fewer parameters. In addition, we show that HistoPLUS robustly transfers to two oncology indications unseen during training and allows interpretable biomarker discovery in downstream tasks, outperforming clinical baselines and prior deep learning methods. To support broader TME biomarker research, we release the model weights and inference code.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100696"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CurvReg: Curvature-aware registration for multi-stain alignment of liver biopsies","authors":"Fatemeh Zabihollahy,&nbsp;Cheuk-To Jeremy Yu,&nbsp;David W. Dodington,&nbsp;George M. Yousef","doi":"10.1016/j.jpi.2026.100698","DOIUrl":"10.1016/j.jpi.2026.100698","url":null,"abstract":"<div><div>Accurate alignment of multi-stain liver biopsy whole-slide images is critical for emerging computational pathology workflows, yet remains challenging due to curved biopsy geometry, non-rigid distortions, and substantial stain-dependent appearance variation. We introduce CurvReg, a curvature-aware, stain-independent registration framework designed to address these challenges by decomposing each biopsy into anatomically coherent segments for piecewise affine alignment, followed by deep learning-based deformable refinement operating directly on tissue segmentation masks rather than raw stained images. By estimating deformation from structural geometry rather than stain intensities, CurvReg enforces anatomically plausible warps and substantially improves robustness to staining, imaging, and device variability. We evaluated CurvReg across three multi-stain liver biopsy datasets and an independent public kidney biopsy dataset from the ANHIR challenge. On the internal multi-stain dataset (Dataset #1) containing hematoxylin–eosin (H&amp;E), Masson's trichrome (MT), and CK7 sections with bile duct annotations, pre-registration mean target registration error (TRE) measured 231.5 μm (H&amp;E–MT), 255.3 μm (MT–CK7), and 188.7 μm (H&amp;E–CK7). After registration, TRE decreased to 51.9 μm, 57.9 μm, and 50.9 μm, respectively, with a &gt;70% reduction across all stain pairs (<em>p</em> &lt; 0.001). Dice similarity increased from 0.54–0.60 to 0.95 (H&amp;E–MT), 0.95 (MT–CK7), and 0.96 (H&amp;E–CK7) (<em>p</em> &lt; 0.001). On the internal portal tract and hepatic vein-annotated H&amp;E–MT dataset (Dataset #2), TRE improved from 147.9 to 48.0 μm (corresponding to a 67.5% reduction; <em>p</em> &lt; 0.001) and Dice from 0.76 to 0.98 (<em>p</em> &lt; 0.001). External validation on a heterogeneous multi-center H&amp;E–MT dataset showed similar gains, with TRE reduced from 93.4 to 42.2 μm (&gt;50% reduction; <em>p</em> &lt; 0.001) and Dice increasing from 0.61 to 0.95 (<em>p</em> &lt; 0.001), confirming robust generalization across scanners, staining protocols, and tissue processing variations. Evaluation on the independent ANHIR kidney biopsy dataset (PAS–MT sections) further demonstrated the generalizability of CurvReg to a different tissue type and stain combination, reducing TRE from 107.2 to 81.6 μm (<em>p</em> = 0.024) while improving Dice similarity from 0.90 to 0.97 (<em>p</em> &lt; 0.001). To highlight downstream clinical value, we demonstrate that MT-derived portal tract and hepatic vein segmentations can be accurately transferred onto H&amp;E using CurvReg, enabling consistent vascular delineation within the diagnostic stain.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100698"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148854391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Dutch Nationwide Pathology Databank and its central role in health research","authors":"Albert G. Siebers,&nbsp;Quirinus J.M. Voorham,&nbsp;Chantal C.H.J. Kuijpers,&nbsp;Annette H. Bruggink,&nbsp;Paul A. Seegers,&nbsp;Esther C. van den Broek,&nbsp;Menno Hoogeveen,&nbsp;Michiel van den Brand,&nbsp;Carolien H.M. van Deurzen,&nbsp;Robby E. Kibbelaar","doi":"10.1016/j.jpi.2026.100695","DOIUrl":"10.1016/j.jpi.2026.100695","url":null,"abstract":"<div><div>The Dutch Nationwide Pathology Databank (Palga) was established in 1971 and achieved nationwide coverage of all Dutch pathology departments in 1991. It serves as the central repository for pathology data across the Netherlands. Palga manages a nationwide IT infrastructure enabling the collection, structuring, and secure sharing of pathology data from all Dutch pathology departments. This unique infrastructure supports diagnostics in patient care by enabling pathologists to access nationwide patient pathology histories and by supporting standardized, structured reporting, particularly in population-based screening programs and oncological pathology. It also serves as a valuable resource for secondary data use, supporting scientific research and healthcare policy decision-making.</div><div>This article provides an overview of the Palga infrastructure, with a focus on its embedded scientific database for secondary use. It describes how pathology data are collected, structured, and shared, and explains how data are securely processed in compliance with current legislation, with particular emphasis on safe secondary use.</div><div>Secure secondary use of pathology data is expected to increasingly advance evidence-based healthcare research for the benefit of society. Palga's nationwide infrastructure provides substantial added value for patient care, health research, and healthcare quality improvement, while enabling responsible and socially valuable secondary data use through collaboration and robust legal and ethical governance.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100695"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13463248/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148726240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum regarding missing Declaration of Competing Interest statements in previously published articles","authors":"","doi":"10.1016/j.jpi.2026.100709","DOIUrl":"10.1016/j.jpi.2026.100709","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100709"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148843298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benefits of high-magnification and color information in computational pathology—An exploratory review","authors":"Nico Haisch,&nbsp;Friederike Liesche-Starnecker,&nbsp;Gregor Grambow,&nbsp;Daniel Hieber","doi":"10.1016/j.jpi.2026.100701","DOIUrl":"10.1016/j.jpi.2026.100701","url":null,"abstract":"<div><h3>Introduction</h3><div>The analysis of gigapixel high-resolution whole-slide images (WSIs) with rich color information using deep learning (DL) models is a routine task in computational pathology (CPath). However, the necessity of such information-rich inputs remains insufficiently explored.</div></div><div><h3>Objectives</h3><div>This literature study aims to collect evidence for the benefit, or its absence, of using WSIs with high magnification levels and full color information in CPath DL models.</div></div><div><h3>Methods</h3><div>Due to the scarcity of domain-specific studies, the exploratory review includes research from related domains, such as broader medical imaging and computer vision in general. The search was conducted using different permutations of keywords in established databases such as IEEE Xplore and PubMed. The retrieved literature was pre-screened by a researcher and relevant work was screened by two researchers independently.</div></div><div><h3>Results</h3><div>The analyzed literature reinforces the lack of direct empirical evidence for using high magnification WSIs with full color information in CPath. Conversely, some findings suggest that reducing image resolution can often maintain high DL accuracy for many classification and detection tasks. Similarly, thoughtful reduction of color information, such as advanced grayscale conversions, can preserve critical diagnostic features with minimal impact on DL performance.</div></div><div><h3>Conclusion</h3><div>The review underscores the need to critically re-examine prevailing conventions on WSI magnification and color usage to optimize DL-driven CPath applications. The lack of direct evidence warrants further research and the establishment of reliable benchmarks in this domain.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100701"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148770085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scalable, modular whole-slide imaging pipelines for low-resource settings: A practical framework and open notebook implementation","authors":"Alfred Githuka,&nbsp;Ulysses G.J. Balis,&nbsp;Ye Chan Kim,&nbsp;Eileen M. Weinheimer-Haus,&nbsp;Christopher L. Williams,&nbsp;Jerome I. Cheng,&nbsp;Kelou Yao,&nbsp;John Blau,&nbsp;Jessica A. Baker,&nbsp;Priscilla Njenga,&nbsp;Winny Chepkemoi,&nbsp;Robert K. Parker,&nbsp;Akbar K. Waljee,&nbsp;Shahin Sayed,&nbsp;Mansoor N. Saleh","doi":"10.1016/j.jpi.2026.100692","DOIUrl":"10.1016/j.jpi.2026.100692","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100692"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to: “Imaging bridges pathology and radiology”, Journal of Pathology Informatics, Volume 14, 2023, 100298","authors":"Martin-Leo Hansmann,&nbsp;Frederick Klauschen,&nbsp;Wojciech Samek,&nbsp;Klaus-Robert Müller,&nbsp;Emmanuel Donnadieu,&nbsp;Sonja Scharf,&nbsp;Sylvia Hartmann,&nbsp;Ina Koch,&nbsp;Jörg Ackermann,&nbsp;Liron Pantanowitz,&nbsp;Hendrik Schäfer,&nbsp;Patrick Wurzel","doi":"10.1016/j.jpi.2026.100690","DOIUrl":"10.1016/j.jpi.2026.100690","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100690"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148730017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A protocol for evaluating robustness to H&E staining variation in computational pathology models","authors":"Lydia A. Schoenpflug,&nbsp;Nikki J. van den Berg,&nbsp;Sonali Andani,&nbsp;Nanda Horeweg,&nbsp;Jurriaan Barkey Wolf,&nbsp;Tjalling Bosse,&nbsp;Viktor Koelzera,&nbsp;Maxime W. Lafarge","doi":"10.1016/j.jpi.2026.100702","DOIUrl":"10.1016/j.jpi.2026.100702","url":null,"abstract":"<div><div>Sensitivity to staining variation remains a major barrier to deploying computational pathology (CPath) models as hematoxylin and eosin (H&amp;E) staining varies across labs, requiring systematic assessment of how this variability affects model prediction. Yet, current evaluation practices rarely attribute performance changes to specific, measurable staining properties, limiting interpretable robustness assessment under controlled conditions. We introduce a three-step protocol that explicitly simulates H&amp;E staining variation toward known, measurable targets, supporting controlled assessment of model performance shifts. Step 1: Select reference staining conditions, Step 2: Characterize test set staining properties, Step 3: Apply CPath model(s) under simulated reference staining conditions. Here, we construct a new reference staining library based on the PLISM dataset. As a use case, we evaluate 306 microsatellite instability (MSI) classification models on the SurGen colorectal cancer dataset (<em>n</em> = 738), including 300 attention-based multiple instance learning models trained on TCGA-COAD/READ across three feature extractors (UNI2-h, H-Optimus-1, and Virchow2), and six public models. Classification performance was measured as AUC, and robustness as the min-max AUC range across four simulated staining conditions (low/high H&amp;E intensity, low/high H&amp;E color similarity). Across models and staining conditions, classification performance ranged from AUC 0.769–0.911 (Δ = 0.142). Robustness ranged from 0.007 to 0.079 (Δ = 0.072), and showed a weak inverse correlation with classification performance (Pearson <em>r</em> = −0.28, 95% CI [−0.39, −0.17]). Thus, using MSI classification in colorectal cancer as a use case, we demonstrate that the proposed evaluation protocol enables robustness-informed CPath model selection and provides insight into how H&amp;E staining conditions affect model performance, with the potential to support reliable deployment across clinical settings. Code and reference library are publicly available at <span><span>https://huggingface.co/datasets/CTPLab-DBE-UniBas/staining-robustness-evaluation</span><svg><path></path></svg></span> and <span><span>https://github.com/CTPLab/staining-robustness-evaluation</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100702"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148843302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Slide-free FIBI histology for improved quantitative vascular network analysis in breast cancer: Integrating vessel geometry and topology metrics","authors":"Shael Brown,&nbsp;Nathan Anderson,&nbsp;Jazmin Orozco,&nbsp;Richard Levenson","doi":"10.1016/j.jpi.2026.100697","DOIUrl":"10.1016/j.jpi.2026.100697","url":null,"abstract":"<div><div>Digital pathology increasingly seeks to extract quantitative vascular and microenvironmental features from routine histology images, but thin-section hematoxylin and eosin (H&amp;E) slides can fragment vessels and obscure their spatial organization, constraining downstream computational analysis. Slide-free fluorescence-imitating brightfield imaging (FIBI) produces histology-like images directly from fresh or fixed tissue or from already prepared paraffin blocks within minutes and can better preserve apparent microvascular continuity in breast cancer and other specimens. In this exploratory digital pathology study, we acquired paired FIBI and H&amp;E images from paraffin-embedded breast tissue blocks, manually segmented blood vessels in tumor and tumor-adjacent stroma, and quantified vascular architecture using both standard geometry-based metrics and topology-derived descriptors of inter-vessel arrangement, including a persistent-homology-based “vessel spacing” metric that captures multiscale clustering. Here, geometry refers to properties of individual vessels (size, length, and branching), whereas topology summarizes how vessels are arranged as a network, including how closely or loosely they cluster. FIBI images exhibited an easily appreciable increase in vascular information compared with matched H&amp;E slides, with vessels appearing more continuous and more clearly resolved in both geometry (e.g., larger area, more branched, etc.) and network topology (e.g., decreased inter-vessel separation). Motivated by this qualitative impression of increased informational content, the goal of this study was to quantitatively assess and validate these differences by contrasting complementary geometry and topology-derived metrics of vessels in pairs of H&amp;E and FIBI images. In particular, persistent homology-derived topology metrics provided information that was not linearly explained by standard geometric descriptors. Together, these findings demonstrate a practical digital pathology pipeline that integrates slide-free FIBI acquisition, vessel annotation, geometry- and topology-based feature extraction, and suggest that FIBI-derived vascular signatures, particularly when coupled with automated vessel segmentation, may provide informative input for future computational and artificial intelligence-based pathology models, and potentially clinical applications.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100697"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148770084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-class semantic segmentation of oral cancer tissues on whole-slide images: A SuperPixel enhanced deep learning approach","authors":"Fabian León,&nbsp;Anne Champagnac,&nbsp;Mathieu Dupoy,&nbsp;Jean-Michel Fayette,&nbsp;Tamás Dániel Csűry,&nbsp;Laurent Duraffourg,&nbsp;Pierre Saintigny","doi":"10.1016/j.jpi.2026.100699","DOIUrl":"10.1016/j.jpi.2026.100699","url":null,"abstract":"<div><div>Oral cancer remains a significant global health challenge, where early and accurate histopathological diagnosis is essential for improving patient outcomes. Whereas deep learning has shown promise in assisting pathologists, current methods face significant challenges by the need for exhaustive manual annotations, class imbalance, and limited contextual insight from patch-based analyses. This work introduces a deep learning method for the automated semantic segmentation of 10 different tissue types within oral cancer tumor regions of interest (ROIs) on whole-slide images (WSIs). To reduce annotation burden and enhance precision, a superpixel-based approach is proposed for data annotation and incorporated a superpixel refinement step during inference to improve boundary delineation while reducing noisy pixels. The model was rigorously evaluated across nine combinations of architectures and backbones, using 444.038 patches from 10 different patients for training and validation (via a 5-fold Leave-One-Fold-Out Group K-Fold Cross-Validation) and 78.103 patches from two independent patients for testing. The present approach achieved a robust average accuracy of 0.921 and micro Intersection over Union (IoU) of 0.859, demonstrating robust results even in under-represented and morphologically diverse tissue classes. Despite challenges related to class imbalance and local context limitations, the proposed methodology consistently provided high-quality predictions. Furthermore, seamless integration into the open-source QuPath platform enables WSI ROI reconstruction, highlighting its potential for real-world clinical deployment in oral cancer diagnostics.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"22 ","pages":"Article 100699"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148770086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}