Diagnostic Pathology最新文献

{"title":"Sjögren's syndrome-focusassist: lymphocytic focus assessment in Sjögren's syndrome: a deep learning and spatial analysis approach.","authors":"Jiajun Zhang, Yi Yang, Xuejing Wang, Yexing Zhang, Benhao Wang, Yuan Zong, Tong Wu, Jiawen Zhao, Xiaoyu Zhao, Wenshuo Tang, Yonghong He, Qian Da, Liting Jiang, Tian Guan, Qiming He","doi":"10.1186/s13000-026-01756-0","DOIUrl":"10.1186/s13000-026-01756-0","url":null,"abstract":"<p><p>Sjögren’s syndrome (SS) is a chronic autoimmune disease whose clinical gold standard relies on precise quantification of lymphocyte foci and lymphocyte density in salivary gland biopsies. However, traditional manual assessment is time-consuming, highly subjective, and lacks consistency. To address these challenges, we propose Sjögren’s syndrome-FocusAssist (SS-FocusAssist), an end-to-end AI-assisted pathology framework for automated focus detection and quantification. At the cell-level detection stage, the system adopts an anchor-free single-stage detector enhanced with Coordinate Attention, improving the model’s ability to capture long-range spatial dependencies and identify minute lymphocytes. This design yields a precision of 95.9% and an mAP@0.5 of 99.1%, representing improvements of 11.1% and 7.3% over the baseline model. At the lesion-level aggregation stage, we introduce Filter-guided Adaptive Clustering (FAC): KDTree is first used to suppress spatial outliers, followed by DBSCAN with adaptive thresholds to form density-consistent lymphocytic foci; Finally, in the quantification stage, we develop an iterative expert-algorithm threshold optimization framework, guided by clinical diagnostic criteria, to achieve an optimal balance between lesion detection fidelity and pathological interpretability. In an independent cohort of 298 cases, SS-FocusAssist achieved a Cohen’s κ of 0.793 compared with dual-expert annotations—a 39% improvement over cell-detection-only methods. These results demonstrate that SS-FocusAssist substantially enhances the accuracy, consistency, and efficiency of SS biopsy interpretation, offering a clinically practical pathway for scalable digital pathology deployment.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12961828/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146156311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SOX17/PAX8 dual immunohistochemical expression in the diagnosis of Müllerian carcinomas.","authors":"Manar Moustafa, Marwa Ahmed Mohamed Abdalrahman, Heba Mahmoud Abdelgeleel","doi":"10.1186/s13000-026-01746-2","DOIUrl":"10.1186/s13000-026-01746-2","url":null,"abstract":"<p><strong>Background: </strong>Metastatic Müllerian carcinomas, including endometrial and ovarian adenocarcinomas, are challenging to diagnose due to factors like similar malignancies, insufficient clinical history, multiorgan dissemination, and small tumor specimens. Immunohistochemistry (IHC) stains are commonly used to identify these cancers. PAX8 is a widely used IHC marker with varying sensitivity levels for different types of gynecologic carcinomas. SOX17, a transcription factor involved in embryonic differentiation and development, has high specificity for ovarian and endometrial carcinomas but is weakly expressed in other epithelial neoplasms.</p><p><strong>Methods: </strong>. 56 endometrial carcinomas cases,56 ovarian cancer case and 56 cases of non-gynecological cancer, were subjected to immunohistochemical (IHC) analysis of SOX17 and PAX8.</p><p><strong>Results: </strong>In endometrial carcinomas, PAX8-high/SOX17-high co-expression strongly favored endometrioid histology (90% vs. 68.8%, p = 0.04), while ovarian high-grade serous carcinomas commonly expressed PAX8 (78.9% high) with heterogeneous SOX17 expression (47.4% high). Notably, double-negative PAX8/SOX17 status completely excluded Müllerian origin in metastases from colorectal, breast, and pulmonary primary tumors (100% specificity), though renal (all PAX8+) and thyroid neoplasms (63.6% PAX8+) required additional markers for distinction. Statistical analyses confirmed subtype-specific trends (p < 0.05 for all applicable comparisons) with loss of SOX17 associated with aggressive histotypes (25% negative in serous versus 10% in endometrioid).</p><p><strong>Conclusions: </strong>Müllerian carcinomas can be distinguished from non-gynecological metastases using PAX8 and SOX17 immunohistochemistry, with PAX8-high/SOX17-high patterns strongly indicating endometrioid differentiation and double-negative results excluding gynecologic origin with consistency in colorectal, breast, and pulmonary carcinomas. Renal and thyroid carcinomas are the diagnostic traps on the basis of PAX8 expression and require additional markers for final classification in metastatic workups.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12931085/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146149412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hobnail hemangioma-a systematic review and a case report of an intraoral lesion with Dabska tumor-like features.","authors":"Elina Mari Susanna Salasuo, Riitta Hannele Pajukanta, Jetta Kelppe, Jouko Lohi, Tommy Wilkman, Hellevi Merja Anneli Ruokonen, Tuula Anneli Salo","doi":"10.1186/s13000-026-01750-6","DOIUrl":"10.1186/s13000-026-01750-6","url":null,"abstract":"<p><p>Hobnail hemangioma is a rare, benign vascular neoplasm. Intraoral lesions are extremely rare. To date, only seven intraoral cases of hobnail hemangiomas and two intraoral cases of Dabska tumors have been described in the English-language literature. This article presents a hobnail hemangioma case with papillary intralymphatic angioendothelioma (Dabska tumor)-like features on the gingiva of a 7-year-old female. Hobnail hemangiomas are benign lesions, but they display worrisome features on microscopic examination and can be confused with malignant vascular neoplasms. Histologically hobnail hemangiomas demonstrate superficial dilated, vascular structures with prominent hobnail endothelial cells and deeper, collagen dissecting thinner neoplastic vessels which in some cases may raise a worrisome pseudoangiosarcomatous histologic view. It is important to set an accurate diagnosis of hobnail hemangioma to diminish the risk of diagnosing these lesions as malignant tumors thus avoiding unnecessarily aggressive therapy.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12983637/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146149396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interobserver agreement among pathologists in the histopathological diagnosis and classification of colorectal polyps.","authors":"Elham Jafari, Mahdiye Lashkarizadeh, Nazanin Zeinali Nezhad, Haniye Rahmani","doi":"10.1186/s13000-026-01764-0","DOIUrl":"10.1186/s13000-026-01764-0","url":null,"abstract":"<p><strong>Objective: </strong>To assess interobserver agreement among pathologists in the diagnosis and classification of colorectal polyps.</p><p><strong>Methods: </strong>This cross-sectional study was conducted at Afzalipour Educational and Medical Center from 2017 to 2018. Three experienced pathologists independently evaluated 253 colorectal polyp specimens, encompassing a spectrum of neoplastic and non-neoplastic lesions. Polyps were classified into six categories and dysplasia was graded. Interobserver agreement was assessed using weighted Cohen's kappa coefficient.</p><p><strong>Results: </strong>The mean age of patients was 51.09 ± 20.11 years, with an average polyp size of 6.6 ± 0.6 mm. Most polyps (49.8%) were located in the colon, with 69.1% measuring 1-5 mm. Neoplastic polyps constituted 59.3% of the samples. Interobserver agreement for overall histopathological diagnosis was good (κ = 0.66). Agreement was very good for carcinoma in situ (κ = 0.87), good for adenomatous (κ = 0.78) and juvenile polyps (κ = 0.76), moderate for hyperplastic polyps (κ = 0.45), and poor for Inflammatory Polyps (κ = 0.16), solitary rectal ulcer (κ = 0.12), and sessile serrated polyps (κ = 0.14). Agreement on dysplasia grading was fair (κ = 0.32).</p><p><strong>Conclusion: </strong>While agreement was good for adenomatous polyps and carcinoma, considerable variability exists in diagnosing certain polyp types and grading dysplasia. These findings highlight the need for standardized criteria and additional training to improve consistency in colorectal polyp assessment, particularly for serrated lesions and dysplasia grading.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12983503/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146149464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"StainStyleSampler: clustering-based sampling of whole slide image appearances.","authors":"Maya Maya Barbosa Silva, Sabine Leh, Hrafn Weishaupt","doi":"10.1186/s13000-026-01752-4","DOIUrl":"10.1186/s13000-026-01752-4","url":null,"abstract":"<p><p>The appearance of whole slide biopsy images is greatly affected by various factors such as laboratory procedures or the choice of digital slide scanners. The resulting variations in image styles within and across batches of histological images represent one of the major obstacles to the development of generalizable machine learning algorithms. To overcome this challenge, a lot of research has focused on stain normalization and stain augmentation techniques. While such approaches provide effective strategies to reduce stain variation or increase stain invariance, respectively, they typically involve only limited modelling or sampling of the underlying stain style distribution. Tools for a streamlined sampling of different aspects of such a distribution, which would be crucial e.g. for explicitly evaluating machine learning robustness across or with respect to major stain styles, remain largely missing. Here, we present the StainStyleSampler, a toolkit for (i) the exploration and modelling of stain style variations, and (ii) the automated sampling of images or styles capturing the core components of this variation. The tool enables the extraction of various colour features and deconvolved stain components, visualization of such features directly or after dimensionality reduction, modelling of style distributions using binning, clustering, and density mapping, and automated sampling of the most representative reference images. We believe that this software will equip pathologists and computer-scientists with a more versatile set of tools that can substantially aid in both the exploration and sampling of stain variation across whole slide images.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12973866/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146124120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantification of interstitial fibrosis in digitized kidney biopsies using deep neural networks.","authors":"Neda Soleimani, Zahra Hajizadeh, Maryam Mohammadi, Sahand Mohammadzadeh","doi":"10.1186/s13000-026-01763-1","DOIUrl":"10.1186/s13000-026-01763-1","url":null,"abstract":"<p><p>INTRODUCTION: Interstitial fibrosis in kidney biopsy is an established marker of disease prognosis and chronicity. Conventional manual grading by pathologists is subjective and variable. Computational methods may reduce this variability. METHODS: We developed a deep learning framework using a ResNet-50 architecture with transfer learning to classify interstitial fibrosis on trichrome-stained renal biopsy images. A total of 2000 biopsies were screened; 162 were excluded due to poor slide quality, leaving 1838 cases (1154 native, 684 transplant). A single expert nephropathologist provided ground-truth fibrosis scores, categorized as < 5% (minimal), 5–25% (mild), 26–50% (moderate), and > 50% (severe). RESULTS: The model achieved an overall accuracy of 73% (95% CI: 65–81%) with substantial agreement with the pathologist (κ = 0.68). Stratified analysis showed 78% accuracy for native kidneys and 67% for transplant biopsies. CONCLUSION: Our CNN-based framework shows promise for standardizing fibrosis assessment in kidney biopsies. However, the absence of external validation remains a key limitation, and further multi-center studies are required. </p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":""},"PeriodicalIF":3.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12958591/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Guidelines for the adoption of digital pathology in clinical pathology units recommended by the polish society of pathologists.","authors":"Łukasz Szylberg, Justyna Durślewicz, Łukasz Chmura, Witold Rezner, Artur Bartczak, Andrzej Marszałek","doi":"10.1186/s13000-026-01762-2","DOIUrl":"10.1186/s13000-026-01762-2","url":null,"abstract":"<p><p>These guidelines provide a clear and practical framework for the effective implementation of digital pathology (DP) in routine anatomical pathology practice. Digital pathology, defined as the digitization of microscope slide into high-resolution whole slide images, is transforming the diagnostic workflow by enabling remote access, improved image analysis, integration with artificial intelligence (AI), and enhanced data management. While digital systems are becoming increasingly integrated into pathology laboratories, the physical archiving of microscope slides remains a legal and procedural requirement in many countries, particularly for histological and cytological materials. As DP continues to evolve globally, the establishment of clear standards, technical requirements, validation procedures, and interoperability guidelines is essential to maintain diagnostic accuracy, patient safety, and system reliability. These recommendations address key technical, organizational, and legal aspects of DP implementation, with an emphasis on ensuring consistent quality and minimizing variability in diagnostic outcomes. The outlined approach supports the safe and effective adoption of DP as an integral element of modern digital healthcare.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":"13"},"PeriodicalIF":3.5,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12874716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146092341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pathology of peripheral neuroblastic tumors.","authors":"Miriam R Conces, Yuichi Shibui, Hiroyuki Shimada","doi":"10.1186/s13000-026-01758-y","DOIUrl":"10.1186/s13000-026-01758-y","url":null,"abstract":"<p><p>Neuroblastoma is the most prevalent extracranial solid tumor in pediatric age populations worldwide and the most common neoplastic disease diagnosed in the first year of life. The term neuroblastoma often encompasses all peripheral neuroblastic tumors (pNTs including neuroblastoma, ganglioneuroblastoma, and ganglioneuroma) of neural crest origin. Since pNTs demonstrate a wide range of clinical behaviors, including spontaneous regression, tumor differentiation/maturation, and aggressive progression refractory to even intensive treatment modalities, these tumors are believed to be distinguished into different biological/molecular groups. For the practical purpose, risk classification systems have been developed based on combinations of so-called prognostic factors.In this review of pNTs, we describe a history of pathology, summarize epidemiology and clinical features, and outline International Neuroblastoma Pathology Classification (INPC). Then we discuss advantages and limitations of core needle biopsy and conventional biopsy of neuroblastoma. Besides the INPC, we also describe other prognostic factors, such as age at diagnosis, clinical stage, and molecular/genetic factors, since they are included in widely used Risk Classification Systems. Additionally, we discuss further molecular abnormalities closely associated with highly aggressive neruoblastomas. Towards the end, we touch on rapidly advancing technologies for establishing an artificial intelligence-assisted INPC system.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":"22"},"PeriodicalIF":3.5,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12922415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146084797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel immunohistochemical staining method of frozen sections improves the intraoperative diagnosis of Sclerosing Pneumocytoma and bronchiolar adenoma.","authors":"Qingqing Liu, Jiadi Luo, Qingchun Liang","doi":"10.1186/s13000-026-01757-z","DOIUrl":"10.1186/s13000-026-01757-z","url":null,"abstract":"<p><p>BACKGROUND: Sclerosing Pneumocytoma (SP) and Bronchial Adenoma (BA) are rare benign tumors that are morphologically difficult to differentiate from lung adenocarcinoma during intraoperative diagnosis. Effective IHC on frozen section might be beneficial for their recognition. This study introduced a novel IHC method that could be applied to intraoperative frozen sections. Its performance was well demonstrated, and the improvement in pathological diagnosis and surgical decisions was analyzed. METHODS: Comparative cohorts of SP and BA were established from surgical samples. The influence of the novel method was analyzed using self-controlled samples. The diagnostic efficacy of the novel IHC on frozen sections was tested using selected markers. The impact of IHC using frozen sections on the pathological evaluations and surgical operations was analyzed. RESULTS: The new IHC protocol on frozen sections demonstrated superior performance. Compared to IHC on FFPE, the overall accuracy of the selected markers was satisfactory. It improved the diagnostic accuracy of junior pathologists, with the correct diagnosis rate increasing from 38.7% to 93.6% in SP and from 49.1% to 94.5% in BA. Additionally, the rate of lobectomy and segmentectomy decreased from 54.2% to 38.7% in the SP cohort. A unique group featuring single-layered bronchiolar adenomatoid lesions was described. CONCLUSIONS: The optimized IHC protocol for frozen sections enhances intraoperative diagnostic accuracy, facilitating improved surgical decision-making for SP and BA, thereby enhancing the management of diseases that require accurate intraoperative diagnosis. The clinical application of the new IHC method and the special group of adenomatoid lesions warrant further investigations. </p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":"20"},"PeriodicalIF":3.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12918003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146050861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pediatric malignant testicular germ cell tumors: a developmental and comparative perspective.","authors":"Sonja Chen, Andres Matoso","doi":"10.1186/s13000-026-01765-z","DOIUrl":"10.1186/s13000-026-01765-z","url":null,"abstract":"<p><p>Malignant testicular germ cell tumors exhibit significant histologic diversity, particularly across pediatric age groups. Prepubertal patients more commonly develop yolk sac tumors, whereas postpubertal adolescents are more likely to present with mixed germ cell tumors arising from germ cell neoplasia in situ. Although clinical presentations may vary, histologic evaluation and immunohistochemistry remain the cornerstone of diagnosis. Additionally, molecular findings-especially the presence of isochromosome 12p-play a crucial role in prognosis. This review underscores the developmental origins and heterogeneity of malignant testicular germ cell tumors in pediatric populations and provides some contrast with their development in adults.</p>","PeriodicalId":11237,"journal":{"name":"Diagnostic Pathology","volume":" ","pages":"19"},"PeriodicalIF":3.5,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12918240/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146060747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}