Journal of Pathology Informatics最新文献_第6页

Z-stacking improves AI detection of cellular features, so does extended focus Z-stacking改进了AI对细胞特征的检测，扩展聚焦也是如此

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100599

Tengyou Xu , Hongyan Gu , Xiang Chen , Mohammad Haeri

引用次数: 0

Aggregating multimodal hematopathology data into an analytics-ready database for AI development 将多模态血液病数据聚合到AI开发的分析就绪数据库中

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100601

Nicholas Spies , Ray Linford , Jacob Durtschi , Lauren Zuromski , Ashley Hutchings , Alexandra Rangel , Ryan Shean , Weston Prestwich , Mark Dewey , Brendan O'Fallon , David Ng

引用次数: 0

Partnering to standardization: Clinical study for the first use of DICOM for pathology diagnostics 标准化合作：首次使用DICOM进行病理诊断的临床研究

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100613

Aysegul Ergin Sutcu , Michael White , Jenny Lewis , Xiaozhi Zhou , Theresa L. Thompson , Elin Kindberg , Morgan Filipsson , Rasmus Dencker , Dylan V. Miller , Isaac Lloyd , Eric F. Glassy , Nathash S. Kallichanda , Jonathan E. Zuckerman

引用次数: 0

Digital imaging shows utility for the diagnosis of cardiac amyloid in clinical practice 数字影像在临床上对心脏淀粉样蛋白的诊断具有重要意义

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100608

Justin Burk , Alexander Wein , Cory Bernadt , Jon Ritter , Chieh-Yu Lin

引用次数: 0

Digital pathology slide re-scan requests: A viewer-neutral LIS solution 数字病理切片重新扫描请求：一个观众中立的LIS解决方案

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100594

Chaz Scala , Brendon Perry , Christopher Schottmiller , Chad Swanson , Jean-Pierre New , Latisha Rider , Alyaa Al-Ibraheemi , Sanda Alexandrescu , Dimitra Pouli

引用次数: 0

The evolving role of DICOM in digital pathology DICOM在数字病理学中的演变作用

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-04-03 DOI: 10.1016/j.jpi.2026.100658

Toby C. Cornish , Shubham Dayal , David Ferber , Joseph Chiweshe , Robert Monroe

{"title":"The evolving role of DICOM in digital pathology","authors":"Toby C. Cornish , Shubham Dayal , David Ferber , Joseph Chiweshe , Robert Monroe","doi":"10.1016/j.jpi.2026.100658","DOIUrl":"10.1016/j.jpi.2026.100658","url":null,"abstract":"<div><div>Digital pathology has emerged as a technology with the potential to transform anatomic pathology by enabling remote consultation, computational analysis, streamlined workflows, and more efficient archival of histopathology slides. Interest in digital pathology has steadily grown as health practitioners increasingly recognize its potential to enhance patient care. In the United States, at least 10 whole slide scanners have been cleared or approved by the Food and Drug Administration (FDA), reflecting a growing confidence in this technology. However, widespread adoption has been hampered by the continued proliferation of proprietary, vendor-specific whole slide image formats that limit interoperability between systems. Whereas commonly used whole slide image formats, such as SVS, iSyntax, BIF, MRXS, and NDPI, have proven adequate for siloed deployments, they are less well-suited for integration into enterprise imaging solutions. The Digital Imaging and Communications in Medicine (DICOM) standard, which revolutionized radiology over three decades ago, offers a vendor-neutral whole slide image format that enables seamless exchange of images and metadata across systems, supporting efficient workflows, accurate diagnosis, and secondary use such as artificial intelligence research. This article discusses the use of DICOM in digital pathology, the key benefits it provides, the clear need for digital pathology vendors to adopt it as a native storage format, and other opportunities and barriers to adoption. As digital pathology matures and computational pathology applications proliferate, DICOM adoption represents a critical step toward an interoperable, vendor-neutral imaging ecosystem.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"21 ","pages":"Article 100658"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147802715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast organ-of-origin classification for digital pathology quality control 用于数字病理质量控制的快速器官起源分类

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-04-17 DOI: 10.1016/j.jpi.2026.100663

Witali Aswolinskiy , John K.L. Wong , Myroslav Zapukhlyak , Yulia Kindruk , Marina Pavlova , Roman Laskorunskyi , Martin Paulikat , Christian Aichmüller

{"title":"Fast organ-of-origin classification for digital pathology quality control","authors":"Witali Aswolinskiy , John K.L. Wong , Myroslav Zapukhlyak , Yulia Kindruk , Marina Pavlova , Roman Laskorunskyi , Martin Paulikat , Christian Aichmüller","doi":"10.1016/j.jpi.2026.100663","DOIUrl":"10.1016/j.jpi.2026.100663","url":null,"abstract":"<div><div>Digitizing large histopathology archives requires processing millions of scanned whole-slide images that must be validated rapidly. Automated organ-of-origin classification can accelerate quality control and enable early detection of mislabeled specimens. We developed a deep learning model that classifies the organ of origin from hematoxylin and eosin-stained slides using a single low-resolution thumbnail per slide in under 1 s. For training, we used thumbnails from 16,624 slides from The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC) archives, which contain mostly primary tumor resections. The images were categorized into 14 classes based on the most common primary sites in TCGA: Bladder, Brain, Breast, Colorectal, Kidney, Liver, Lung, Pancreas, Prostate, Skin, Stomach, Thyroid gland, Uterus, and Other (encompassing the remaining tissue types). We evaluated our approach on two independent external cohorts: a 5-class cohort with 2857 slides (Colorectal, Kidney, Liver, Pancreas, and Prostate) and a comprehensive 14-class cohort (12,348 slides). The model achieved 90% balanced accuracy for the 5-class cohort and 62% for the full 14-class cohort. Notably, when considering only the predictions with high confidence, 53% of the large cohort could be classified with 74% balanced accuracy. Manual review of high-confidence misclassifications suggested that some may reflect errors in the ground truth rather than model error. Mean model inference time was 0.2 s per slide on an NVIDIA L4 GPU. Our deep learning approach demonstrates high classification performance with very low inference time, indicating its potential for real-time and cost-effective quality control in digital pathology.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"21 ","pages":"Article 100663"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147951514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing liver fibrosis measurement: Deep learning and uncertainty analysis across multi-center cohorts 加强肝纤维化测量：跨多中心队列的深度学习和不确定性分析

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-03-20 DOI: 10.1016/j.jpi.2026.100653

Marta Wojciechowska , Stefano Malacrino , Dylan Windell , Emma L. Culver , Jessica K. Dyson , on behalf of the UKAIH consortium, Jens Rittscher

{"title":"Enhancing liver fibrosis measurement: Deep learning and uncertainty analysis across multi-center cohorts","authors":"Marta Wojciechowska , Stefano Malacrino , Dylan Windell , Emma L. Culver , Jessica K. Dyson , on behalf of the UKAIH consortium, Jens Rittscher","doi":"10.1016/j.jpi.2026.100653","DOIUrl":"10.1016/j.jpi.2026.100653","url":null,"abstract":"<div><div>Digital pathology enables large multi-center studies of histological specimens, but differences in staining protocols and slide quality can compromise the comparability of quantitative results. We analyzed 686 PicroSirius Red-stained liver biopsies from 4 independent cohorts spanning more than 20 clinical sites to assess how stain variability affects automated fibrosis quantification and model uncertainty. An U-Net ensemble was trained to segment collagen and to estimate pixel- and tile-level predictive uncertainty. Across markedly heterogeneous staining conditions, the ensemble achieved strong segmentation performance (Dice 0.83–0.90) and produced informative uncertainty maps that identified artifacts and out-of-distribution regions. Epistemic uncertainty values were typically below 0.002, providing a practical criterion for flagging unreliable predictions. Our results demonstrate that ensemble-based uncertainty estimation complements stain-standardization efforts by quantifying prediction confidence directly from model outputs, improving the reliability and interpretability of collagen proportionate-area measurements across multi-center datasets. This framework supports more trustworthy and reproducible digital-pathology workflows for fibrosis assessment and other histological applications.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"21 ","pages":"Article 100653"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147710064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pathologist experience and AI use in claudin 18.2 IHC for upper gastrointestinal tract tumors 临床经验及人工智能在claudin 18.2上胃肠道肿瘤免疫组化中的应用

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100616

Otoniel Alejandro González Barbosa , Rodrigo Humberto Girón Cuestas , Juan Eduardo Sebastián Aguirre-Garza , Natalia Vilches Cisneros , José Antonio García Muñiz , Juan Pablo Flores Gutiérrez

引用次数: 0

Enhancing diagnostic insight through intrinsic imaging: A novel approach in digital pathology 通过内在成像增强诊断洞察力：数字病理学的新方法

Journal of Pathology Informatics Pub Date : 2026-04-01 Epub Date: 2026-05-25 DOI: 10.1016/j.jpi.2026.100619

Guillermo Puebla Robles , Abraham Schwartz , Maria Correa Rivas , Emma Fernandez Rapollet , Jose Conde

引用次数: 0