Journal of Pathology Informatics最新文献

{"title":"Erratum to “After neoadjuvant therapy, axillary sentinel lymph node frozen sections from breast cancer patients are accurately diagnosed using telepathology” [Journal of Pathology Informatics Volume 13, 2022, 100092]","authors":"Valarie McMurtry , Jane M. Poretta , Rachel E. Factor","doi":"10.1016/j.jpi.2025.100427","DOIUrl":"10.1016/j.jpi.2025.100427","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100427"},"PeriodicalIF":0.0,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579645","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 to “Classification of cervical biopsy free-text diagnoses through linear-classifier based natural language processing” [Journal of Pathology Informatics Volume 13, 2022, 100123]","authors":"Jim Wei-Chun Hsu , Paul Christensen , Yimin Ge , S. Wesley Long","doi":"10.1016/j.jpi.2025.100430","DOIUrl":"10.1016/j.jpi.2025.100430","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100430"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550691","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 to “CNViz: An R/Shiny application for interactive copy number variant visualization in cancer” [Journal of Pathology Informatics Volume 13, 2022, 100089]","authors":"Rebecca G. Ramesh , Ashkan Bigdeli , Chase Rushton , Jason N. Rosenbaum","doi":"10.1016/j.jpi.2025.100431","DOIUrl":"10.1016/j.jpi.2025.100431","url":null,"abstract":"","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100431"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550690","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":"Custom R Flexdashboard for molecular genetic pathology quality tracking","authors":"Steven Shen ,&nbsp;Ju-Yoon Yoon","doi":"10.1016/j.jpi.2025.100434","DOIUrl":"10.1016/j.jpi.2025.100434","url":null,"abstract":"<div><div>The practice of modern-day laboratory medicine entails extensive, daily practice of tracking various quality metrics of every molecular test to ensure quality maintenance, as well as for laboratory management. While various third-party tools are commercially available, such represent a significant investment for publicly funded institutions. To automate aspects of this quality management, we developed a custom dashboard, written using R. We used R Studio, a freely available software, and employed the <em>Shiny</em> and <em>Flexdashboard</em> packages to develop the code base for the dashboard. Data for the dashboard were pulled from multiple Excel tracking spreadsheets for different clinical assays. The current dashboard allows for dynamic, automated reporting of case volume, and turn-around time, which are regularly reported metrics to CancerCare Ontario for reimbursement purposes. Workload tracking is also made possible, automating calculations regularly performed for billing purposes. The dashboard summarizes various quality metrics for each assay in a single table, viewable by multiple personnel within a single network. Additional features such as filtering quality metrics by date and customization of a variety of plots were also included. Whereas other informatics solutions may be available, our custom solution represents a low-cost system that alleviates a significant workload from various members of the laboratory medicine department, easing the currently significant administrative burden from the “hands-on” staff. Future work will be focused on further improving the accessibility of the dashboard and the integration of additional molecular assays for quality monitoring.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100434"},"PeriodicalIF":0.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724296","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":"GloFinder: AI-empowered QuPath plugin for WSI-level glomerular detection, visualization, and curation","authors":"Jialin Yue ,&nbsp;Tianyuan Yao ,&nbsp;Ruining Deng ,&nbsp;Siqi Lu ,&nbsp;Junlin Guo ,&nbsp;Quan Liu ,&nbsp;Juming Xiong ,&nbsp;Mengmeng Yin ,&nbsp;Haichun Yang ,&nbsp;Yuankai Huo","doi":"10.1016/j.jpi.2025.100433","DOIUrl":"10.1016/j.jpi.2025.100433","url":null,"abstract":"<div><div>Artificial intelligence (AI) has demonstrated significant success in automating the detection of glomeruli—key functional units of the kidney—from whole slide images (WSIs) in kidney pathology. However, existing open-source tools are often distributed as source code or Docker containers, requiring advanced programming skills that hinder accessibility for non-programmers, such as clinicians. Additionally, current models are typically trained on a single dataset and lack flexibility in adjusting confidence levels for predictions. To overcome these challenges, we introduce GloFinder, a QuPath plugin designed for single-click automated glomerular detection across entire WSIs with online editing through the graphical user interface. GloFinder employs CircleNet, an anchor-free detection framework utilizing circle representations for precise object localization, with models trained on approximately 160,000 manually annotated glomeruli. To further enhance accuracy, the plugin incorporates weighted circle fusion—an ensemble method that combines confidence scores from multiple CircleNet models to produce refined predictions, achieving superior performance in glomerular detection. GloFinder enables direct visualization and editing of results in QuPath, facilitating seamless interaction for clinicians and providing a powerful tool for nephropathology research and clinical practice.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100433"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643376","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":"PARAFFIN: A software tool for Pathology Report Automated Feedback for Improved Education of anatomic pathology trainees","authors":"Clarissa E. Jordan,&nbsp;Justin E. Juskewitch,&nbsp;Andrew P. Norgan","doi":"10.1016/j.jpi.2025.100424","DOIUrl":"10.1016/j.jpi.2025.100424","url":null,"abstract":"<div><h3>Background</h3><div>Feedback on the diagnosis and reporting of pathology findings is essential to the training of residents and fellows, but time constraints and other factors can make it difficult to ensure learners are made aware of the outcome of all cases in which they participated. Many trainees attempt to keep track of their cases and later look up final pathology reports in the laboratory information system (LIS); however, this manual and time-consuming process is prone to error and may prevent them from spending time reviewing and learning from these reports.</div></div><div><h3>Methods</h3><div>To address this, we developed a software solution, (<strong>Pa</strong>thology <strong>R</strong>eport <strong>A</strong>utomated <strong>F</strong>eedback <strong>f</strong>or <strong>I</strong>mproved Educatio<strong>n</strong>; “PARAFFIN”), which provides pathology trainees with a weekly email digest containing an attached case log with the date, accession sequence, attending pathologist initials, and final diagnosis text for each case in which they participated. PARAFFIN is implemented as two R scripts running on a Posit Connect server: a data extraction script, which accesses an interactive report from our enterprise analytics SQL server, and a reporting script, which performs recipient-specific filtering and emails the trainee with their personalized case log attached as .txt and .csv files. After implementation, pathology trainees were surveyed about PARAFFIN's impact on report collection and case feedback.</div></div><div><h3>Results</h3><div>Of the total 51 pathology trainees who were receiving PARAFFIN digests at the long-term follow-up timepoint, 20 responded to our survey. 90% (18 of 20) of respondents report that PARAFFIN allows them to spend more time reviewing the content of final anatomic pathology reports, rather than collecting reports. Trainees report utilizing PARAFFIN for feedback on multiple aspects of pathology reporting, with final diagnosis, wording/style of final diagnostic line, and diagnostic comment being most frequently used.</div></div><div><h3>Conclusions</h3><div>Our automated case feedback solution provides trainees with a record of final pathology reports for cases in which they participated, which allows trainees to spend more time reviewing reports for feedback rather than manually collecting them from the LIS.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100424"},"PeriodicalIF":0.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143593458","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":"An international study of stain variability in histopathology using qualitative and quantitative analysis","authors":"Catriona Dunn ,&nbsp;David Brettle ,&nbsp;Chantell Hodgson ,&nbsp;Robert Hughes ,&nbsp;Darren Treanor","doi":"10.1016/j.jpi.2025.100423","DOIUrl":"10.1016/j.jpi.2025.100423","url":null,"abstract":"<div><div>Hematoxylin and eosin (H&amp;E) staining accounts for over 80% of slides stained worldwide. Although routinely used, there are high levels of variation between labs due to different staining methods. Staining is a pivotal part of slide preparation, but quality control is largely subjective, with overall clinical assurance provided by external quality assessment (EQA) services, underpinned by expert assessment. Digital pathology offers the potential to provide objective quantification of stain, through color analysis, to augment EQA assessment.</div><div>This large-scale study evaluated H&amp;E staining in 247 international labs participating in the UK NEQAS CPT EQA programme. Tissue sections were circulated to each lab to stain using their routine H&amp;E staining protocol. The slides were reviewed by independent expert UK NEQAS CPT assessors, and quantitative digital analysis was conducted, comprising of H&amp;E color deconvolution and color difference determination (ΔE).</div><div>Most labs (69%) achieved an EQA score indicating good or excellent staining, with high inter-observer concordance to support this (92.5% within one mark of each other). H&amp;E color difference, ΔE, showed 60% of labs were within 2 ΔE of the mean, which is considered as only perceptible through close observation. There was little correlation found between H&amp;E intensity and assessor score, however, the H&amp;E intensity ratio indicated a trend with assessor score suggesting there may be an optimal stain relationship that should be investigated further.</div><div>The presented hybrid analysis combines expert analysis with objective data. This has the potential to inform upon optimal tissue staining and allows us to consider quantitative standards of H&amp;E staining in pathology practice.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100423"},"PeriodicalIF":0.0,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579644","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":"Assessing the quality of whole slide images in cytology from nuclei features","authors":"Paul Barthe ,&nbsp;Romain Brixtel ,&nbsp;Yann Caillot ,&nbsp;Benoît Lemoine ,&nbsp;Arnaud Renouf ,&nbsp;Vianney Thurotte ,&nbsp;Ouarda Beniken ,&nbsp;Sébastien Bougleux ,&nbsp;Olivier Lézoray","doi":"10.1016/j.jpi.2025.100420","DOIUrl":"10.1016/j.jpi.2025.100420","url":null,"abstract":"<div><h3>Background and objective</h3><div>Implementation of machine learning and artificial intelligence algorithms into digital pathology laboratories faces several challenges, notably the variation in whole slide image preparation protocols. The diversity of preparation pipelines forces algorithms to be protocol-dependant. Moreover, the error susceptibility of each stage in the preparation process implies a need of quality control tools. To address these challenges, this article introduces a straightforward, interpretable, and computationally efficient quality control module to ensure optimal algorithmic performance.</div></div><div><h3>Methods</h3><div>The proposed quality control module ensures algorithmic performance by representing an algorithm by a reference whole slide image preparation protocol validated on it. Then, inspired by data description methods, a preparation protocol is represented by nuclei feature distributions, obtained for several whole slide images it has produced. The quality of a preparation protocol is evaluated according to several reference preparation protocols, by comparing their feature distributions with a weighted distance.</div></div><div><h3>Results</h3><div>Through empirical analysis conducted on seven distinct preparation protocols, we demonstrated that the proposed method build a quality module that clearly discriminates each preparation. Additionally, we showed that this module performs well on more larger and realistic corpus from laboratories routine, detecting quality deviations.</div></div><div><h3>Conclusion</h3><div>Even if the proposed method necessitates minimal data and few computational resources, we showed that it is interpretable and relevant on realistic corpus from several laboratories' routine. We strongly believe in the necessity of quality control from the algorithmic perspective and hope this kind of approach will be extended to improve quality and reliability of digital pathology whole slide images.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100420"},"PeriodicalIF":0.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143478615","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":"“Pathologists in Venice – Real World Cases for an Immersive Training Experience”: Education, Gaming, and Show","authors":"Stefano Marletta ,&nbsp;Albino Eccher ,&nbsp;Aldo Scarpa ,&nbsp;Angelo Paolo Dei Tos ,&nbsp;Valentina Angerilli ,&nbsp;Elena Bellan ,&nbsp;Fatima Carneiro ,&nbsp;Matteo Fassan ,&nbsp;Marta Sbaraglia ,&nbsp;Stuart Schnitt ,&nbsp;Liron Pantanowitz ,&nbsp;Fabio Pagni ,&nbsp;Vincenzo L'Imperio","doi":"10.1016/j.jpi.2024.100418","DOIUrl":"10.1016/j.jpi.2024.100418","url":null,"abstract":"<div><div>An international meeting entitled “Pathologists in Venice: Real World Cases for an Immersive Training Experience” took place on December 12 and 13, 2024 in Venice, Italy. More than 100 pathologists from all over the world were brought together to join four opinion leaders in different pathology fields. By matching real-time whole slide imaging-based navigation exposure with a technologically cutting-edge gaming format, the meeting engaged and provided the attendees with an innovative and immersive educational approach to real-world compelling scenarios they are likely to encounter in their daily practice.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100418"},"PeriodicalIF":0.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465104","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 novel rotation and scale-invariant deep learning framework leveraging conical transformers for precise differentiation between meningioma and solitary fibrous tumor","authors":"Mohamed T. Azam ,&nbsp;Hossam Magdy Balaha ,&nbsp;Akshitkumar Mistry ,&nbsp;Khadiga M. Ali ,&nbsp;Bret C. Mobley ,&nbsp;Nalin Leelatian ,&nbsp;Sanjay Bhatia ,&nbsp;Murat Gokden ,&nbsp;Norman Lehman ,&nbsp;Mohammed Ghazal ,&nbsp;Ayman El-Baz ,&nbsp;Dibson D. Gondim","doi":"10.1016/j.jpi.2025.100422","DOIUrl":"10.1016/j.jpi.2025.100422","url":null,"abstract":"<div><div>Meningiomas, the most prevalent tumors of the central nervous system, can have overlapping histopathological features with solitary fibrous tumors (SFT), presenting a significant diagnostic challenge. Accurate differentiation between these two diagnoses is crucial for optimal medical management. Currently, immunohistochemistry and molecular techniques are the methods of choice for distinguishing between them; however, these techniques are expensive and not universally available. In this article, we propose a rotational and scale-invariant deep learning framework to enable accurate discrimination between these two tumor types. The proposed framework employs a novel architecture of conical transformers to capture both global and local imaging markers from whole-slide images, accommodating variations across different magnification scales. A weighted majority voting schema is utilized to combine individual scale decisions, ultimately producing a complementary and more accurate diagnostic outcome. A dataset comprising 92 patients (46 with meningioma and 46 with SFT) was used for evaluation. The experimental results demonstrate robust performance across different validation methods. In train-test evaluation, the model achieved 92.27% accuracy, 87.77% sensitivity, 97.55% specificity, and 92.46% F1-score. Performance further improved in 4-fold cross-validation, achieving 94.68% accuracy, 96.05% sensitivity, 93.11% specificity, and 95.07% F1-score. These findings highlight the potential of AI-based diagnostic approaches for precise differentiation between meningioma and SFT, paving the way for innovative diagnostic tools in pathology.</div></div>","PeriodicalId":37769,"journal":{"name":"Journal of Pathology Informatics","volume":"17 ","pages":"Article 100422"},"PeriodicalIF":0.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519352","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}