Modern Pathology最新文献

{"title":"Low-Grade Fibro-Osseous Lesions With Isolated Chromosome 12 Chromothripsis: A Distinct Entity Or a Low-Grade Central Osteosarcoma With a Novel Driver?","authors":"Carla Saoud ,&nbsp;Yanming Zhang ,&nbsp;Jamal Benhamida ,&nbsp;Liliana Villafania ,&nbsp;Gunes Gundem ,&nbsp;Robert Cimera ,&nbsp;Sinchun Hwang ,&nbsp;Neerav N. Shukla ,&nbsp;Damon Reed ,&nbsp;Elli Papaemmanouil ,&nbsp;Narasimhan P. Agaram ,&nbsp;Konstantinos Linos ,&nbsp;Marc Ladanyi ,&nbsp;Carol D. Morris ,&nbsp;Meera R. Hameed","doi":"10.1016/j.modpat.2025.100931","DOIUrl":"10.1016/j.modpat.2025.100931","url":null,"abstract":"<div><div>Chromothripsis, a catastrophic genomic event causing extensive chromosomal fragmentation and rearrangement, has been identified in conventional osteosarcoma, contributing to karyotypic heterogeneity. Chromothripsis was also detected in a subset of parosteal osteosarcomas, primarily involving chromosome 12, but not well documented in low-grade central osteosarcoma (LGCOS). Here, we report 2 cases of low-grade fibro-osseous lesions with isolated chromosome 12 chromothripsis, aiming to characterize them by comparing their genomic and epigenetic profiles to those of other bone neoplasms. Case 1 was a 12-year-old male with a destructive lesion involving the proximal left tibia, and case 2 was a 13-year-old female with an expansile lucent bone lesion involving the distal tibia with cortical breakthrough. Both cases consisted of hypocellular bland fibroblastic proliferation. Areas of thin trabeculae of woven bone surrounded by osteoblasts were present. In addition, case 1 showed areas of atypical cartilaginous islands and areas reminiscent of LGCOS. By single-nucleotide polymorphism array, both cases showed extremely complex and numerous genomic alterations involving chromosome 12. Whole-genome sequencing and optical genome sequencing confirmed the chromothriptic event involving chromosome 12. Using the Heidelberg Epignostix sarcoma methylation classifier (v12.3), both cases matched to fibrous dysplasia methylation class. Dimensionality reduction using Uniform Manifold Approximation and Projection demonstrated that the 2 index cases clustered primarily with low-grade osteosarcomas lacking <em>MDM2</em> amplification and with fibrous dysplasia, whereas remaining separate from parosteal osteosarcomas and <em>MDM2</em>-amplified low-grade osteosarcomas. Our findings suggest that chromothripsis of chromosome 12 may represent an early and/or an alternate mechanism in fibro-osseous lesions progressing to LGCOS instead of or before the development of the well-recognized <em>CDK4/MDM2</em> amplification. Larger cohorts with long-term follow-ups and integrative molecular studies are needed to clarify the biological significance and clinical implications, including recurrence, dedifferentiation, and survival.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"39 1","pages":"Article 100931"},"PeriodicalIF":5.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145471545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing Interpretive and Diagnostic Competency Development in Pathology Training","authors":"Tad T. Brunyé ,&nbsp;Hannah Shucard ,&nbsp;Megan M. Eguchi ,&nbsp;Trafton Drew ,&nbsp;Jonathan Marotti ,&nbsp;Lesley C. Lomo ,&nbsp;Mark R. Kilgore ,&nbsp;Kimberly H. Allison ,&nbsp;Kathleen F. Kerr ,&nbsp;Joann G. Elmore ,&nbsp;Donald L. Weaver","doi":"10.1016/j.modpat.2025.100802","DOIUrl":"10.1016/j.modpat.2025.100802","url":null,"abstract":"<div><div>Accurate disease diagnosis is the cornerstone of patient care, directly impacting the quality of health care delivery and patient outcomes. Developing diagnostic competence is a critical goal of pathology residency training. This study uses longitudinal data from trainees during pathology residency to examine the association between years of training and performance in 4 key interpretive phases: detecting critical regions, recognizing their relevance, describing histopathological features, and rendering an accurate diagnosis. Using a study set of 32 digital whole slide images of breast biopsies, 155 pathology residents from 10 US academic medical centers each reviewed 14 cases across multiple years of residency training. Image-viewing behavior, annotation accuracy, and diagnostic decisions were recorded and analyzed. Generalized estimating equations were used to assess the relationship between residency year and metrics capturing the 4 interpretive phases. Year of residency training was not significantly associated with the detection of critical regions or recognizing their importance. However, each year of residency training was associated with 2% less time spent viewing critical regions (<em>P</em> = 0.025) and 1% more attentional coverage of the image space (<em>P</em> = 0.01), suggesting that residents adopt broader scanning strategies over time. Further, each year of residency training was associated with 19% higher odds of writing an accurate annotation (odds ratio = 1.19, <em>P</em> &lt; 0.001) and 18% higher odds of making an accurate diagnosis (odds ratio = 1.18, <em>P</em> &lt; 0.001). Exploratory analyses indicated that accurate feature annotation was the key predictor of diagnostic accuracy, highlighting its importance as a foundational skill in clinical decision-making. Both the ability to describe histopathological features and diagnostic accuracy increase with years of residency training, and the former appears to be a key component of the latter. Competency-based training in pathology should incorporate targeted interventions to improve histopathological feature recognition and description, which appears most likely to improve overall diagnostic performance.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100802"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144180881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Histopathologic Insights Into Curvularia-Induced Chronic Granulomatous Fungal Sinusitis: A Guide for Surgical Pathologists","authors":"Ashleigh N. Riegler ,&nbsp;Jessica W. Grayson ,&nbsp;Jacob W. Greenway ,&nbsp;Bradford A. Woodworth ,&nbsp;Todd P. McCarty ,&nbsp;Peter G. Pappas ,&nbsp;Sixto M. Leal Jr.","doi":"10.1016/j.modpat.2025.100898","DOIUrl":"10.1016/j.modpat.2025.100898","url":null,"abstract":"<div><div>Chronic granulomatous fungal sinusitis is a rare, debilitating infection characterized by an enlarging mass affecting the orbit, nose, palate, and paranasal sinuses, with occasional intraorbital and intracranial extension. Most cases are reported in subtropical regions, with rare reports from the United States and Europe. Globally, <em>Aspergillus flavus</em> is the primary causative agent in &gt;60% of cases, followed by other <em>Aspergillus</em> species and dematiaceous molds. This study highlights the histopathologic, microbiologic, and molecular diagnostic features of 6 cases with chronic granulomatous fungal sinusitis caused by the emerging pathogen <em>Curvularia</em>, predominantly affecting healthy African Americans in the Southeastern United States. Histopathological examination revealed multinucleated giant cells and noncaseating granulomatous inflammation. Short septate hyphae with bulbous swelling predominated, but there was significant variation in size, shape, and color, with half the cases lacking hyphal pigmentation. Lack of awareness of this emerging entity and variable morphology led to initial misidentification in 3 cases as hyaline septate hyphae <em>(Fusarium</em>), yeasts, and <em>Blastomyces</em>. All cases showed extracellular and intracellular (within multinucleated giant cells) hyphae and round forms with thick refractile cell walls lacking intracellular contents, yielding a characteristic “ghost shell” morphology, indicating fungal nonviability. Consistent with this finding, only 1 culture yielded a live isolate of <em>Curvularia</em>. In addition, 28S rRNA gene sequencing of formalin-fixed paraffin-embedded tissue was required for identification and identified <em>Curvularia lunata</em> (n = 4), <em>Curvularia spicifera</em> (n = 1), and <em>Curvularia</em> spp. (n = 1). One case with 2 hyphal morphologies also grew <em>Aspergillus fumigatus</em>, indicating coinfection. Chronic granulomatous fungal sinusitis, caused by the understudied and persistent pathogen <em>Curvularia</em>, is an emerging threat in immunocompetent hosts, characterized by pathogen persistence in critical facial and cranial structures, despite a significant host response. To accurately diagnose and guide treatment, surgical pathologists must be aware of its expanded geographic range, affected populations, and key histopathologic features, as described herein.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100898"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145176820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-Based Tool.","authors":"Ziyu Su, Yongxin Guo, Robert Wesolowski, Gary Tozbikian, Nathaniel S O'Connell, Muhammad Khalid Khan Niazi, Metin N Gurcan","doi":"10.1016/j.modpat.2025.100847","DOIUrl":"10.1016/j.modpat.2025.100847","url":null,"abstract":"<p><p>Accurate recurrence risk stratification is crucial for optimizing treatment plans for breast cancer patients. Current prognostic tools like Oncotype DX offer valuable genomic insights into hormone receptor-positive and human epidermal growth factor receptor-negative patients but are limited by cost and accessibility, particularly in underserved populations. In this study, we present Deep-Breast-Cancer-Recurrence (BCR)-Auto, a deep learning-based computational pathology approach that predicts breast cancer recurrence risk from routine hematoxylin and eosin-stained whole slide images. Our methodology was validated on 2 independent cohorts: The Cancer Genome Atlas Program breast cancer data set and an in-house data set from The Ohio State University. Deep-BCR-Auto demonstrated robust performance in stratifying patients into low- and high-recurrence risk categories. On The Cancer Genome Atlas Program breast cancer data set, the model achieved an area under the receiver operating characteristic curve of 0.827, significantly outperforming the existing weakly supervised models (P = .041). In the independent The Ohio State University data set, Deep-BCR-Auto maintained strong generalizability, achieving an area under the receiver operating characteristic curve of 0.832, along with 82.0% accuracy, 85.0% specificity, and 67.7% sensitivity. These findings highlight the potential of computational pathology as a cost-effective alternative for recurrence risk assessment, broadening access to personalized treatment strategies. This study underscores the clinical utility of integrating deep learning-based computational pathology into routine pathological assessment for breast cancer prognosis across diverse clinical settings.</p>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":" ","pages":"100847"},"PeriodicalIF":6.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144668002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated Multiomics Analysis of Microsatellite Instability-High Colorectal Cancer Identifies a Subtype With Poor Outcome","authors":"Gangzhi Zhang ,&nbsp;Biting Zhou ,&nbsp;Xiaoxian Xu ,&nbsp;Yang Che ,&nbsp;Wenjie Hong ,&nbsp;Shu Zheng ,&nbsp;Suzhan Zhang ,&nbsp;Wangxiong Hu ,&nbsp;Yanmei Yang","doi":"10.1016/j.modpat.2025.100896","DOIUrl":"10.1016/j.modpat.2025.100896","url":null,"abstract":"<div><div>Up to 50% of patients with metastatic microsatellite instability-high (MSI-H) colorectal cancer (CRC) are resistant to immunotherapy and experience progression or recurrence after treatment. We integrated the genomic, epigenomic, transcriptomic, and proteomic data for 99 patients in a Chinese MSI-H CRC cohort. Proteomic profiling of primary tumors clearly classified MSI-H tumors into 2 subtypes. We found that the 2 subtypes have different mutational signatures, enriched pathways, gene fusion networks, and clinical outcomes. Notably, NCAM1 could serve as a potential biomarker for checkpoint inhibitor response in MSI-H CRC. Thus, there is an urgent need to stratify the MSI-H group into different subtypes and adopt more targeted therapies to prolong patient survival.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100896"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145138299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ovarian Sex Cord Tumor With Annular Tubules (SCTAT) Harbor Recurrent Copy Number Alterations, Including Monosomy 22","authors":"Andrew M. Leader ,&nbsp;Alexander Neil ,&nbsp;Stephanie Siegmund ,&nbsp;Amir Dehghani ,&nbsp;Azra Ligon ,&nbsp;Ursula A. Matulonis ,&nbsp;Marisa R. Nucci ,&nbsp;W. Glenn McCluggage ,&nbsp;Brooke E. Howitt ,&nbsp;David L. Kolin","doi":"10.1016/j.modpat.2025.100891","DOIUrl":"10.1016/j.modpat.2025.100891","url":null,"abstract":"<div><div>Sex cord tumor with annular tubules (SCTAT) is a rare ovarian sex cord–stromal neoplasm of low or intermediate malignant potential. Although some SCTATs are associated with Peutz-Jeghers syndrome (PJS), the majority arise in the nonsyndromic setting and typically lack <em>STK11</em> mutations. As molecular alterations other than <em>STK11</em> in SCTAT are largely unknown, we sought characterize the genomic landscape in these neoplasms better. SCTATs (n = 22) from 20 patients (5 with PJS, 1 with Prader-Willi syndrome, and 14 with no known syndromic status) were retrospectively identified. STK11 (LKB1) immunohistochemistry (IHC) was performed. Panel-based DNA sequencing was used to detect copy number variations and point mutations in 447 genes in 12 tumors from patients with no history of PJS, with 1 additional non-PJS tumor undergoing only targeted <em>STK11</em> sequencing. Molecular profiles were compared with other ovarian sex cord–stromal tumors (n = 67). An <em>STK11</em> mutation and concurrent loss of heterozygosity was in 1 of 13 sporadic tumors. STK11 IHC was intact (n = 14) or equivocal (n = 2) for <em>STK11</em> wild-type tumors and lost in 1 sporadic tumor with <em>STK11</em> mutation and 5 tumors from patients with known PJS. <em>TERT</em> promoter mutations were present in 6 of 12 tumors. Recurrent copy number alterations included monosomy 22 (8/12), as well as low-level copy number gains of <em>FOXL2</em> (10/12; median, 4.3 estimated copies in <em>FOXL2</em>-gained tumors; range, 2.6-7.9), <em>WT1</em> (9/12), and <em>GATA4</em> (8/12). One tumor demonstrated biallelic inactivation of <em>TP53</em> in a region of high-grade transformation characterized by significant cytologic atypia, mitotic activity, and necrosis. In conclusion, nonsyndromic SCTATs are molecularly characterized by <em>FOXL2, WT1</em>, and <em>GATA4</em> gains, monosomy 22, and <em>TERT</em> promoter mutations. High-grade transformation may rarely occur, a phenomenon not previously described, and is associated with <em>TP53</em> mutation. STK11 IHC appears to be a reliable surrogate for <em>STK11</em> mutations and may be useful in suggesting a PJS-related tumor.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100891"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145064988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Spatial Profiling Demonstrates Differences Between Fibrosarcomatous Transformation of Dermatofibrosarcoma Protuberans and Its Conventional Counterparts","authors":"Nicholas Frazzette ,&nbsp;Suvrajit Maji ,&nbsp;Nada Mohamed ,&nbsp;Austin Jones ,&nbsp;Ata S. Moshiri ,&nbsp;Robert W. Ricciotti ,&nbsp;Shreeram Akilesh ,&nbsp;Jose G. Mantilla","doi":"10.1016/j.modpat.2025.100879","DOIUrl":"10.1016/j.modpat.2025.100879","url":null,"abstract":"<div><div>Dermatofibrosarcoma protuberans (DFSP) is a neoplasm of the dermis with a tendency for aggressive local growth and recurrence. A minority of DFSP cases may transform into higher-grade sarcoma (fibrosarcomatous transformation [FST]) (DFSP-FST), which is associated with more aggressive behavior and risk of metastasis. The histologic diagnosis of DFSP-FST may be challenging, particularly in small biopsies. Currently, there are no specific markers to reliably support the diagnosis of DFSP-FST. We identified 33 DFSP from 32 patients, including 9 patients with FST and 1 distant metastasis. Tissue microarrays (TMAs) were created using representative areas of all cases, including DFSP-FST, conventional regions from DFSP-FST, and pure conventional DFSP. Digital spatial profiling of the entire transcriptome was performed on the TMAs using the Nanostring GeoMx platform. Expression data were queried to identify differentially expressed genes specific to the regions of transformation in DFSP. Immunohistochemistry for PReferentially expressed Antigen in MElanoma (PRAME) was subsequently performed using a clinically validated protocol. Digital spatial profiling demonstrated significant gene expression differences between DFSP-FST and conventional DFSP. Genes that were overexpressed in DFSP-FST include <em>PRAME</em>, <em>CTAG1B</em>, and <em>MMP11</em>. Immunohistochemical analysis for PRAME showed positive expression in 7 of 10 DFSP-FST (70%) and 1 of 23 conventional DFSP (4%) (<em>P</em> &lt; .0001). Gene expression profiling shows significant upregulation of <em>PRAME</em> and <em>CTAG1B</em> in DFSP-FST compared with conventional DFSP, a finding that was validated by immunohistochemistry for PRAME. Therefore, immunohistochemistry for PRAME may be useful to support the diagnosis of FST, especially in small biopsies. Increased expression of CTAG1B (NY-ESO-1) in DFSP-FST may also offer future therapeutic potential.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100879"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144992943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flat Cell Variant of Lung Adenocarcinoma In Situ","authors":"Naoyuki Oka ,&nbsp;Satsuki Kishikawa ,&nbsp;Jumpei Kashima ,&nbsp;Hirokazu Watanabe ,&nbsp;Masahiko Kusumoto ,&nbsp;Keisuke Asakura ,&nbsp;Shun-Ichi Watanabe ,&nbsp;Yasushi Yatabe","doi":"10.1016/j.modpat.2025.100876","DOIUrl":"10.1016/j.modpat.2025.100876","url":null,"abstract":"<div><div>Adenocarcinoma in situ (AIS) of the lungs has been increasingly diagnosed worldwide following the establishment of its diagnostic criteria along with advances in computed tomography imaging technology. We encountered a series of AISs with a peculiar flat cell morphology that were challenging to diagnose using the current diagnostic criteria. Histologically, all 5 tumors showed a lepidic pattern consisting of flat tumor cells with minimal nuclear atypia. Intra-alveolar mucin was identified in 4 cases, although cytoplasmic mucin of the tumor cells was inconspicuous. All tumors harbored genetic or immunohistochemical features of neoplasms identical to those of conventional AIS. Driver mutations were detected in 3 tumors (2 <em>EGFR</em> mutations and 1 <em>ERBB2</em> mutation), and 4 tumors were positive for hepatocyte nuclear factor 4 alpha, although the intensity was very low. We also identified a flat cell variant of minimally invasive adenocarcinoma, suggesting a stepwise progression similar to that in conventional AIS. These findings suggest that AIS with flat cellular features is a morphologic variant of AIS and may be challenging to diagnose if pathologists are unaware of this atypical feature of lung neoplasm.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100876"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144961655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning–Based Segmentation of Lung Adenocarcinoma Whole-Slide Images for Objective Grading, Tumor Spread Through Air Spaces Identification, and Mutation Prediction","authors":"David Joon Ho ,&nbsp;Jason C. Chang ,&nbsp;Rania G. Aly ,&nbsp;Hai Cao Truong Nguyen ,&nbsp;Prasad S. Adusumilli ,&nbsp;Thomas J. Fuchs ,&nbsp;William D. Travis ,&nbsp;Chad M. Vanderbilt","doi":"10.1016/j.modpat.2025.100907","DOIUrl":"10.1016/j.modpat.2025.100907","url":null,"abstract":"<div><div>Manual quantification of morphologic patterns in lung adenocarcinoma is subject to reproducibility issues due to interpathologist variability. In this study, we developed a deep learning–based multiclass segmentation model providing a modality for objective and quantitative grading of digitized lung adenocarcinoma images from resected specimens. Additionally, the model can detect tumor spread through air spaces and show enrichment of specific morphologic patterns in tumors with different genomic alterations. The study was based on 766 resected nonmucinous lung adenocarcinomas. Deep Multi-Magnification Network was trained to segment 14 tissue subtypes based on annotations of 108 internal whole-slide images at pixel level by thoracic pathologists (J.C.C. and W.D.T.). The trained model was validated on an external cohort of 130 cases for determining predominant patterns and on the remaining 528 internal cases for the 3 clinical tasks. The model graded nonmucinous lung adenocarcinomas based on the International Association for the Study of Lung Cancer Pathology Committee recommendation and successfully stratified patients into well, moderately, and poorly differentiated morphologies (<em>P</em> &lt; 1 × 10⁻⁴). Pixels categorized as spread through air spaces significantly correlated with pathologists’ interpretations. For molecular analysis, solid pattern was enriched with <em>TP53</em> mutations and depleted of <em>EGFR</em> kinase domain mutations. Lepidic pattern was inversely associated with <em>TP53</em> mutations. Acinar was enriched with <em>EGFR</em> mutations, whereas papillary was associated with <em>RET</em> fusions. Our study demonstrated that deep learning–based segmentation can accurately quantify histologic patterns in lung adenocarcinoma and identify additional prognostic features. By simultaneously providing an objective assessment of various tasks, our comprehensive methodology in lung adenocarcinoma paves way for deep learning–assisted pathologic diagnosis and treatment guidance.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100907"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145275333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Magnetic Resonance Imaging (MRI)–Adapted Prostate Cancer Risk Tool Incorporating Cribriform and Intraductal Carcinoma","authors":"Ngoc-Nhu Jennifer Nguyen ,&nbsp;Kristen Liu ,&nbsp;Katherine Lajkosz ,&nbsp;Rui Bernardino ,&nbsp;Leyi Bellinda Yin ,&nbsp;Eva Hollemans ,&nbsp;Lisa J. Kroon ,&nbsp;Neil Fleshner ,&nbsp;Geert J.L.H. van Leenders ,&nbsp;Kenneth A. Iczkowski ,&nbsp;Theodorus H. van der Kwast ,&nbsp;Michelle R. Downes","doi":"10.1016/j.modpat.2025.100852","DOIUrl":"10.1016/j.modpat.2025.100852","url":null,"abstract":"<div><div>Current prostate cancer risk stratification tools are not adapted for magnetic resonance imaging (MRI)–targeted biopsies and do not include the presence of cribriform carcinoma/intraductal carcinoma (CC/IDC), an independent predictor of adverse clinical outcomes. We developed an MRI-adapted prostate cancer risk tool (MAPCaRT), which incorporates CC/IDC presence to the Cancer of the Prostate Risk Assessment (CAPRA) tool. We compared the prognostic power of MAPCaRT with that of CAPRA in MRI-targeted biopsies (n = 266, 2015-2023) and systematic-only biopsies (n = 1291, 2010-2018) that had matched radical prostatectomy. MAPCaRT employs the aggregate core count method for MRI-targeted lesions to calculate percent positive biopsy cores and uses the radiological stage when assessing MRI-targeted biopsies. Point attribution for CC/IDC presence and Gleason score was determined using a Cox proportional hazards model that included the CAPRA score, Gleason score, and CC/IDC status. Based on calculated MAPCaRT and CAPRA scores, patients were classified into the low-risk (0-2), intermediate-risk (3-5), or high-risk (6+) group. Model performance was assessed via the Kaplan-Meier curves, Harrell C-indices, and decision curve analysis for biochemical recurrence–free survival (BCR-FS) and event-free survival (EFS) (metastasis/cancer-specific death). CC/IDC was present in 84 of 266 (32%) MRI-targeted biopsies and 293 of 1291 systematic-only biopsies (23%). The median follow-up time was 3.4 years (IQR, 2.3-5.5 years) for the MRI-targeted biopsy cohort and 5.9 years (IQR, 3.4-8.1 years) for the systematic biopsy cohort. In the MRI-targeted biopsy cohort, MAPCaRT showed substantial improvement of the C-index compared with CAPRA (0.635 vs 0.574, <em>P</em> = .045) and greater net clinical benefit for 4-year BCR-FS. In the systematic biopsy cohort, MAPCaRT demonstrated improved C-index for BCR-FS (0.696 vs 0.655, <em>P</em> &lt; .001) and greater net clinical benefit for 5-year BCR-FS and EFS. Other model performance metrics were marginally better with MAPCaRT. In summary, we developed MAPCaRT (prostatecancercalculator.lmp.utoronto.ca), a modified version of CAPRA incorporating CC/IDC presence, which demonstrated improved BCR-FS and EFS predictions. This may result in better clinical guidance for disease management decisions.</div></div>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":"38 12","pages":"Article 100852"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144732310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}