Endocrine Pathology最新文献

{"title":"Multicentric Retrospective Analysis of Oncocytic Adrenocortical Carcinoma: Insights into Clinical and Management Strategies.","authors":"Antonio Prinzi, Valentina Guarnotta, Guido Di Dalmazi, Letizia Canu, Filippo Ceccato, Francesco Ferraù, Giuseppe Badalamenti, Manuela Albertelli, Maria Cristina De Martino, Giuseppe Fanciulli, Roberta Modica, Angelo Pani, Francesco Arcidiacono, Ignazio Barca, Francesca Donnarumma, Lorenzo Zanatta, Marianna Torchio, Ylenia Alessi, Chiara Vitiello, Francesco Frasca, Pasqualino Malandrino","doi":"10.1007/s12022-025-09857-0","DOIUrl":"https://doi.org/10.1007/s12022-025-09857-0","url":null,"abstract":"<p><p>Oncocytic adrenocortical carcinoma (OAC) is a rare variant of conventional adrenocortical carcinoma (ACC), characterized by oncocytic tumor cells comprising more than 90% of the tumor. Due to its rarity, there is a lack of reliable data on the clinicopathological features and outcomes of OAC. The aim of this study was to assess the clinical presentation, treatment modalities, and outcomes of patients with OAC, comparing these results with a cohort of patients with conventional ACC. Data from 9 referral centers in Italy on 44 patients with OAC were retrospectively analyzed and compared with data from 145 patients with conventional ACC. Patients with OAC had a smaller median tumor size, more favorable resection margin status, and lower incidences of venous invasion and persistent/recurrent disease during follow-up. Additionally, patients with OAC exhibited longer times to progression (TTP) and overall survival (OS) compared to patients with conventional ACC. Multivariable analyses identified Ki67 and tumor size as features independently associated with disease progression during post-surgical follow-up, while Ki67 and distant metastases at diagnosis were independently associated with OS in OAC patients. After complete tumor removal, the risk of recurrent disease was higher in patients with either Ki67 ≥ 20% or ENSAT stage III/IV. OAC appears to have a more indolent clinical course and better prognosis than conventional ACC. Similar to conventional ACC, Ki67 remains a significant prognostic marker for OAC and, along with ENSAT stage, serves as a reliable biomarker for identifying patients who may benefit from adjuvant mitotane therapy.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"11"},"PeriodicalIF":11.3,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11991974/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Tissue Thickness on Computational Quantification of Features in Whole Slide Images for Diagnostic Pathology.","authors":"Manav Shah, António Polónia, Mónica Curado, João Vale, Andrew Janowczyk, Catarina Eloy","doi":"10.1007/s12022-025-09855-2","DOIUrl":"10.1007/s12022-025-09855-2","url":null,"abstract":"<p><p>Tissue section thickness (TST) is an understudied variable in digital pathology that significantly impacts both visual assessments and computational analyses. This study systematically examines the effects of TST on whole slide images (WSIs) and nuclear-level features using thyroid tissue samples (n = 144) prepared at thicknesses ranging from 0.5 to 10 µm. By minimizing preanalytical variables and batch effects, we aimed to isolate TST as the primary factor in our experiment. Visual assessments indicated that thinner Sects. (0.5-3 µm) were more transparent with distinct cellular features, while thicker Sects. (5-10 µm) appeared darker with increased staining intensity and artifacts. Quantitative analyses were performed using open-source tools such as HistoQC for WSI quality control, HoverNet for nuclear segmentation, and feature extraction with Scikit-learn and Mahotas. Both WSI and nuclear-level metrics were significantly influenced by TST. The Haralick texture feature of difference entropy, which measures texture complexity, showed a 13.7% decrease in nuclei as TST increased, indicating fewer complex textures in thicker sections. Additionally, intensity decreased substantially with thicker tissue, dropping by 26.1% at the WSI level and 30.4% at the nuclear level. WSI contrast exhibited an increase of 92.6% when transitioning from 0.5 to 10 µm. These findings demonstrate that variations in TST can obscure or alter the appearance of biological signals, complicating both visual diagnostics and computationally extracted features. The study highlights the need for standardized tissue section thickness protocols, alongside consistent reporting of these standards, to ensure accuracy and reliability in both visual evaluations and computational analyses within digital pathology workflows.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"10"},"PeriodicalIF":11.3,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11978545/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143813045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DLL3 Expression in Neuroendocrine Carcinomas and Neuroendocrine Tumours: Insights From a Multicentric Cohort of 1294 Pulmonary and Extrapulmonary Neuroendocrine Neoplasms.","authors":"Maxime Schmitt, Hanibal Bohnenberger, Detlef Klaus Bartsch, Daniel-Christoph Wagner, Anne-Sophie Litmeyer, Albert Grass, Anja Rinke, Christine Koch, Marcus Kremer, Matthias Evert, Bruno Märkl, Alexander Quaas, Markus Eckstein, Konrad Steinestel, Carsten Denkert, Katja Steiger, Günter Klöppel, Atsuko Kasajima, Markus Tschurtschenthaler, Sebastian Foersch, Moritz Jesinghaus","doi":"10.1007/s12022-025-09854-3","DOIUrl":"10.1007/s12022-025-09854-3","url":null,"abstract":"<p><p>Delta-like ligand 3 (DLL3) is frequently expressed in pulmonary small cell neuroendocrine carcinoma (SCNEC) and has emerged as a promising therapeutic target. However, limited data on DLL3 expression in other neuroendocrine neoplasms (NEN), such as extrapulmonary SCNEC, large cell neuroendocrine carcinomas (LCNEC), mixed neuroendocrine-non-neuroendocrine neoplasms (MiNEN), gastroenteropancreatic neuroendocrine tumours (GEP-NET), and pulmonary carcinoids, impedes an estimation if other types of NEN might be suitable candidates for anti-DLL3 therapies. We evaluated DLL3 expression in 1294 NEN and 479 non-neuroendocrine carcinomas, correlating the findings with histological subtypes, tumour localisation, and overall survival (OS). Furthermore, we explored the concordance of DLL3 expression during metastatic progression in 67 paired primary NEN and metastases. DLL3 expression was significantly higher in NEC (64.0%) compared to GEP-NET and pulmonary carcinoids (10.1%, p < 0.001), particularly in SCNEC (80.4%), followed by LCNEC (62.6%) and MiNEN (28.6%). DLL3 was common in pulmonary carcinoids (41.5%), but rare in GEP-NET (5.1%) and non-neuroendocrine carcinomas (1.3%). Overall DLL3 expression was highly concordant between metastases and corresponding primary NEN (92.5%, p < 0.001). In univariable analyses, DLL3-expressing pulmonary carcinoids (p = 0.005) and GEP-NET (p = 0.018) were associated with decreased OS, but this was not retained in multivariable analyses adjusting for stage and grade (p = n. s.). No prognostic impact was observed in pulmonary (p = 0.708) or GEP-NEC (p = 0.87). Our study highlights significant differences in DLL3 expression across NEN subtypes and localisations, with largely concordant expression in metastases. DLL3-based therapies may be effective in many NEC and pulmonary carcinoids, while DLL3 appears to be a minor therapeutic target for GEP-NET and non-neuroendocrine carcinomas.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"9"},"PeriodicalIF":11.3,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953094/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143736177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Next-Generation Immunohistochemistry in Thyroid Neoplasm: A Practical Review on the Applications in Diagnosis and Molecular Classification.","authors":"Jonathan P Rivera, Jen-Fan Hang","doi":"10.1007/s12022-025-09851-6","DOIUrl":"10.1007/s12022-025-09851-6","url":null,"abstract":"<p><p>An integrative histologic and molecular classification of thyroid tumors has become clinically relevant due to the potential role in risk stratification and selection of targeted therapy. In this review, we discuss the applications of six \"next-generation\" immunohistochemical markers, namely BRAF V600E (clone VE1), RAS Q61R (clone SP174), pan-TRK (clone EPR 17341), ALK (clones 5A4 or D5F3), PTEN, and β-catenin in the pathologic diagnosis and molecular classification of thyroid tumors. These biomarkers allow the in situ examination of tumor tissue and assist in the diagnosis and pathologic staging by highlighting tumor border and patterns of invasion, identifying isolated tumor cells in lymph nodes, distinguishing lymph node metastasis from benign intranodal thyroid inclusions, and diagnosing multicentric thyroid carcinomas with discordant molecular drivers. Furthermore, it can identify specific thyroid neoplasms that may occur sporadically or may be associated with hereditary syndromes. The next-generation immunohistochemistry provides a novel solution to challenging issues in thyroid pathology and fast turn-around time for accurate molecular classification and further guidance of therapeutic management.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"8"},"PeriodicalIF":11.3,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11925991/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143671869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Refining NTRK Fusion Detection in Papillary Thyroid Carcinoma Through Pan-TRK Immunohistochemistry and Histopathologic Features.","authors":"Hyun Lee, Sue Youn Kim, Ji Min Park, Seung-Hyun Jung, Ozgur Mete, Chan Kwon Jung","doi":"10.1007/s12022-025-09852-5","DOIUrl":"10.1007/s12022-025-09852-5","url":null,"abstract":"<p><p>NTRK fusions are rare but recurrent driver alterations in papillary thyroid carcinoma (PTC), with therapeutic significance due to the availability of targeted TRK inhibitors. Pan-TRK immunohistochemistry (IHC) provides a practical approach for the identification of NTRK fusions; however, its application and reliability in routine pathology require further exploration. This study is aimed at evaluating the diagnostic utility of pan-TRK IHC for detecting NTRK fusions in PTC, assessing its correlation with histopathologic features, and developing a diagnostic algorithm. We analyzed 107 BRAF p.V600E-negative PTC cases using pan-TRK IHC, correlating staining patterns with molecular data and histopathologic features. RNA-based targeted sequencing confirmed gene fusions. NTRK fusion-positive tumors were enriched in distinct histopathologic features, including BRAF-like PTC with predominant follicular architecture, clear cells, and secretory-like cells. Findings such as tumor cell stratification, glomeruloid structures, and papillae with subfollicle formation (microfollicles within papillary structures) were associated with both NTRK and RET fusion-positive PTCs. Correlation of pan-TRK IHC and molecular testing results identified non-specific reactivity or false positivity in 62% of pan-TRK IHC-positive PTCs, including cases with RET fusions, BRAF fusion, or no detectable fusion. However, pan-TRK IHC with high H-scores (≥ 110) was observed exclusively in cases with NTRK fusions. For cases with lower H-scores (< 110), integrating histopathologic features improved the identification of fusion-driven PTCs. While our series further supports the limitations of pan-TRK IHC, a diagnostic algorithm that combines pan-TRK IHC H-scores and histopathologic patterns improved the triaging of NTRK molecular testing of BRAF p.V600E-negative PTCs when a stepwise approach is undertaken. This study also demonstrated that TRK protein localization may vary with tumor progression and dedifferentiation.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"7"},"PeriodicalIF":11.3,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methylation Profiles Differ According to Clinical Characteristics in Well-Differentiated Neuroendocrine Tumors of the Lung.","authors":"Philipp Melhorn, Erwin Tomasich, Alissa Blessing, Luka Brcic, Angelika Kogler, Alexander Draschl, Peter Mazal, Anna Sophie Berghoff, Markus Raderer, Matthias Preusser, Gerwin Heller, Barbara Kiesewetter","doi":"10.1007/s12022-025-09847-2","DOIUrl":"10.1007/s12022-025-09847-2","url":null,"abstract":"<p><p>Neuroendocrine tumors (NET) of the lung constitute a rare entity of primary lung malignancies that often exhibit an indolent clinical course. Epigenetics-related differences have been described previously for lung NET, but the clinical significance remains unclear. In this study, we performed genome-wide methylation analysis using the Infinium MethylationEPIC BeadChip technology on FFPE tissues from lung NET treated at two academic centers. We aimed to investigate the methylation profiles of known prognostic subgroups. In total, 54 tissue samples from primary lung NET were analyzed, of which 37 were typical carcinoids (TC) and 17 atypical carcinoids (AC). Overall, 25/53 patients (47.2%) developed metastases throughout the disease course, 14/26 (53.8%) had a positive somatostatin receptor (SSTR) scan, and 7/28 patients (25.0%) had documented endocrine activity. Analysis of the DNA methylation data showed substantial differences between TC and AC samples and revealed three distinct clusters (C1-C3): C3 (n = 29) with 100% TC and 89.7% non-metastasized, C2 (n = 22) with 63.6% AC and 95.5% metastasized, and C1 with three AC samples (2/3 metastasized). In subgroup analyses, distinct methylation patterns were observed based on histology, metastases, SSTR status, and endocrine activity. In the functional gene classification, the genes affected by differential methylation were mainly involved in cell signaling. DNA methylation could potentially aid in the diagnostic process of lung NET. The differences in methylation observed with respect to clinical features like SSTR expression and endocrine activity could translate into improved management of lung NET.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"6"},"PeriodicalIF":11.3,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11903570/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143617856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Gene Expression Analysis in Papillary Thyroid Carcinoma Reveals a Transcriptional Profile Associated with Reduced Radioiodine Avidity.","authors":"Vincenzo Condello, Carlotta Marchettini, Catharina Ihre-Lundgren, Joachim N Nilsson, C Christofer Juhlin","doi":"10.1007/s12022-025-09849-0","DOIUrl":"10.1007/s12022-025-09849-0","url":null,"abstract":"<p><p>Papillary thyroid carcinoma (PTC) is the most common form of well-differentiated thyroid cancer (WDTC) and generally has a favorable prognosis. However, subsets of these tumors can metastasize, leading to aggressive disease progression and poorer clinical outcomes. Radioactive iodine (RAI) therapy is routinely given in the adjuvant setting following thyroidectomy and lymph node dissection for WDTC. Nevertheless, its therapeutic efficacy is limited to tumors with high iodine avidity. Early post-surgical classification of thyroid cancers as either iodine-avid or refractory is crucial for enabling more personalized and effective treatment strategies. In this study, we aimed to identify transcriptomic determinants associated with RAI refractoriness (RAI-R) to improve prognostication. We collected clinicopathologic data and conducted RNA-seq on 36 tissue samples (18 high-avidity and 18 low-avidity), each uniquely characterized by ex vivo iodine concentration measurements taken directly from surgical specimens. Whole-transcriptomic analysis identified 63 differentially expressed genes, with six (S100A4, CRTC2, ANO1, WWTR1, DEPTOR, MT1G) showing consistent deregulation. The expression of ANO1, an established iodine transporter at the apical membrane of the thyroid follicular cells, correlated significantly with iodine avidity (r = 0.54). Validation via RT-qPCR confirmed differential expression trends. Gene ontology and pathway enrichment analyses highlighted thyroid hormone synthesis, PI3K-AKT, and MAPK signaling pathways as key regulators of RAI avidity. A refined multivariate predictive model incorporating ANO1 mRNA expression, histological subtypes, and sample type demonstrated strong predictive performance (adjusted R² = 0.55). These findings suggest ANO1 as a promising biomarker for predicting iodine avidity in thyroid cancer.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"4"},"PeriodicalIF":11.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11845550/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identification of Oncogenic Alterations in 124 Cases of Pediatric Papillary Thyroid Carcinoma: BEND7::ALK, DLG5::RET, and CCDC30::ROS1 Fusions Induce MAPK Pathway Activation.","authors":"Yixuan Liu, Longnv Bao, Guangqi Li, Weimao Kong, Xueqing Li, Jingnan Wang, Xingzhu Pan, Zhen Zhang, Jigang Wang","doi":"10.1007/s12022-025-09850-7","DOIUrl":"10.1007/s12022-025-09850-7","url":null,"abstract":"<p><p>Pediatric papillary thyroid carcinoma (PPTC; under age 18 at the time of diagnosis) is relatively uncommon. There are few studies concerning the genetic background of PPTC in Asian countries. In this study, we reviewed 124 cases of PPTC from a single medical center in China. DNA-based next-generation sequencing (NGS) was performed to identify genetic alterations, with receptor tyrosine kinase (RTK) fusions further validated by RNA-based NGS. DICER1 mutations and TERT promoter mutations were detected by Sanger sequencing. We also explored the relationship between these genetic alterations and the clinicopathologic features, as well as the prognostic factors. Three recombinant plasmids expressing V5/HIS-tagged RTK fusion proteins (BEND7::ALK, DLG5::RET, CCDC30::ROS1) were constructed to investigate the in vitro effects. We found that the two most common subtypes were the classic subtype (77.4%) and the diffuse sclerosing subtype (17.7%). Hashimoto's thyroiditis was observed in 42.3% of cases, and regional lymph node metastasis was present in 82.9% of patients. The most frequent genetic alteration was the BRAF c.1799 T > A (p.V600E) mutation (63 patients, 50.8%), followed by RTK fusions (31 patients, 25.0%). A DICER1 mutation was detected in two cases, and TERT promoter mutations were not observed in any of the patients. RTK fusions were associated with the diffuse sclerosing subtype, Hashimoto's thyroiditis, and extrathyroidal extension. Adverse prognostic factors identified included RTK fusion, age under 14 years, and tumor size over 2 cm. Additionally, a significant proportion of these patients had actionable molecular alterations. Three rare kinase fusions, BEND7::ALK, DLG5::RET, and CCDC30::ROS1, were shown to induce phosphorylation of the MAPK pathway and promote cell proliferation in vitro. The specific RTK inhibitors could counteract the fusion-induced cell proliferation. Our data highlights the genetic landscape of Chinese PPTC patients, with RTK fusions being associated with aggressive clinicopathologic features. The rare fusions BEND7::ALK, DLG5::RET, and CCDC30::ROS1 may contribute to PPTC development with a BRAF-like effect.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"5"},"PeriodicalIF":11.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Relevance of ATRX/DAXX Gene Mutations and ALT in Functioning Pancreatic Neuroendocrine Tumors.","authors":"Brenna R van T Veld, Wenzel M Hackeng, Claudio Luchini, Lodewijk A A Brosens, Koen M A Dreijerink","doi":"10.1007/s12022-025-09848-1","DOIUrl":"10.1007/s12022-025-09848-1","url":null,"abstract":"<p><p>Functioning pancreatic neuroendocrine tumors (PanNETs) represent a subset of PanNETs that cause symptoms due to hormonal activity. Insulinoma is the most common functioning PanNET type. Mutations in the alpha thalassemia/mental retardation X-linked (ATRX) and death domain-associated protein (DAXX) genes result in genomic instability. ATRX/DAXX mutations and associated alternative lengthening of telomeres (ALT) are common in non-functioning PanNETs and associated with aggressive tumor behavior. Recent reports have shown that ATRX/DAXX mutations and ALT are also present in functioning PanNETs. In this review, we summarize the literature addressing ATRX/DAXX mutations and ALT in functioning PanNETs and discuss the clinical relevance with regard to distinguishing aggressive and indolent functioning tumors. ATRX/DAXX gene mutations and/or ALT have been reported in insulinoma, glucagonoma, gastrinoma, VIPoma and calcitoninoma. In insulinoma, the presence of ATRX/DAXX mutations and ALT are associated with aggressive behavior and could therefore be used as prognostic biomarkers. Although ATRX/DAXX mutation and ALT assessment may currently not be the standard of care in routine diagnostic pathology practice, the use of DAXX/ATRX immunohistochemistry at least can be encouraged not only for non-functioning but also for functioning PanNETs.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"3"},"PeriodicalIF":11.3,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11829919/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Enabled Scoring of Pancreatic Neuroendocrine Tumors Based on Cancer Infiltration Patterns.","authors":"Soner Koc, Ozgur Can Eren, Rohat Esmer, Fatma Ulkem Kasapoglu, Burcu Saka, Orhun Cig Taskin, Pelin Bagci, Nazmi Volkan Adsay, Cigdem Gunduz-Demir","doi":"10.1007/s12022-025-09846-3","DOIUrl":"10.1007/s12022-025-09846-3","url":null,"abstract":"<p><p>Pancreatic neuroendocrine tumors (PanNETs) are a heterogeneous group of neoplasms that include tumors with different histomorphologic characteristics that can be correlated to sub-categories with different prognoses. In addition to the WHO grading scheme based on tumor proliferative activity, a new parameter based on the scoring of infiltration patterns at the interface of tumor and non-neoplastic parenchyma (tumor-NNP interface) has recently been proposed for PanNET categorization. Despite the known correlations, these categorizations can still be problematic due to the need for human judgment, which may involve intra- and inter-observer variability. Although there is a great need for automated systems working on quantitative metrics to reduce observer variability, there are no such systems for PanNET categorization. Addressing this gap, this study presents a computational pipeline that uses deep learning models to automatically categorize PanNETs for the first time. This pipeline proposes to quantitatively characterize PanNETs by constructing entity-graphs on the cells, and to learn the PanNET categorization using a graph neural network (GNN) trained on these graphs. Different than the previous studies, the proposed model integrates pathology domain knowledge into the GNN construction and training for the purpose of a deeper utilization of the tumor microenvironment and its architectural changes for PanNET categorization. We tested our model on 105 HE stained whole slide images of PanNET tissues. The experiments revealed that this domain knowledge integrated pipeline led to a 76.70% test set F1-score, resulting in significant improvements over its counterparts.</p>","PeriodicalId":55167,"journal":{"name":"Endocrine Pathology","volume":"36 1","pages":"2"},"PeriodicalIF":11.3,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11757657/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143025754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}