Pathobiology最新文献

{"title":"Immune Scenario Identification Combining Multiplexed, Quantitative, and Advanced Imaging Analysis Could Be Relevant in Immunotherapy against Glioblastoma and Grade 4 Astrocytoma.","authors":"Miguel A Idoate, Mikel Ariz-Galilea, Ainhoa Urbiola-Casales, Miriam Alonso-García, Jesús Machuca-Aguado, Carlos Ortiz de Solórzano, Eloy Rivas-Infante, Rainiero Avila-Polo, Michele Biscuola","doi":"10.1159/000545488","DOIUrl":"10.1159/000545488","url":null,"abstract":"<p><strong>Introduction: </strong>In our research on understanding glioblastoma's resistance mechanisms to immunotherapy, we extensively investigated through an innovative technology that enables the simultaneous assessment of multiple biomarkers. With this approach, we aim to gain deeper insights into the interplay between immunosuppressive cells (ICs) and effector cells (ECs).</p><p><strong>Methods: </strong>One hundred twenty-six cases of glioblastoma were studied employing tissue microarrays stained with a panel of immune infiltrate validated via multiplex immunofluorescence and quantified by advanced image analysis. All cases were categorized according to an EC/IC ratio and their respective medians. Statistical correlations between cell populations and with survival were calculated.</p><p><strong>Results: </strong>M2 macrophages were the most abundant ICs, followed by a variable number of ECs and protumoral activated microglia, and a scant quantity of FoxP3 cells. EC showed a statistically significant direct positive correlation with ICs. The patients with tumors exhibiting an EC/IC ratio ≤0.063 displayed a significantly poorer outcome. Furthermore, in the context of incomplete surgical resection, significant differences were evident considering immune scenarios.</p><p><strong>Conclusions: </strong>By integrating multiplex technology with advanced imaging analysis, we successfully identified 4 distinct immune scenarios in glioblastoma. We observed a favorable immune scenario characterized by a relatively high EC/IC ratio, which is especially evident in the clinical setting of incomplete tumor resection. This promising immune scenario holds significant potential for selecting suitable candidates for immunotherapy in glioblastoma.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"315-334"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144094237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computer-Aided Diagnostics Helps Accurately Determine Different Expression Levels of Claudin-18.2 in Gastric Cancer.","authors":"Sabina Köfler, Sabina Köfler, Katharina Mühlberger, Verena Girkinger, Drolaiz H W Liu, Bastian Dislich, Beat Gloor, Rupert Langer","doi":"10.1159/000545769","DOIUrl":"10.1159/000545769","url":null,"abstract":"<p><strong>Introduction: </strong>Determination of claudin-18.2 expression by immunohistochemistry (IHC) is a prerequisite for targeted treatment of gastric cancers (GCs) with zolbetuximab. Precise assessment of IHC expression categories, however, may be challenging and prone to interobserver variability. Computer-aided diagnosis has a high potential of improving diagnostic accuracy and reproducibility. We established a computer-aided analysis tool for claudin-18.2 positivity scoring.</p><p><strong>Methods: </strong>Analysis steps included the identification of tumour tissue on haematoxylin-3,3'-diaminobenzidine-stained tissue microarray (TMA) slides, cell segmentation, and membranous staining intensity estimation of claudin-18.2 (clone 43-14A). We analysed 2,248 cores from 417 primary resected GCs with detailed pathological data available.</p><p><strong>Results: </strong>In 51.6% (1,159/2,248) of TMA cores, no stained tumour cells were detected. Among cases with claudin-18.2 expression, predominantly 1+ and 2+ cells, a minority of 3+ stained cells were found, and 2+ to 3+ staining was unevenly distributed. Utilizing the SPOTLIGHT claudin-18.2 positivity threshold, we identified 12% (187/1,555) positive cores corresponding to 2.5% (9/365) positive cases. Lower staining intensities in tumour centre cores point to intratumoural heterogeneity.</p><p><strong>Conclusion: </strong>Computer-aided diagnostics helps accurately measure claudin-18.2 expression levels, allowing to precisely determine claudin-18.2 status in GC patients. Previously uncaptured categorization of staining intensities may enhance the understanding of claudin-18.2 threshold for patient stratification.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"265-275"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence-Driven Quantification of Tumor-Stroma Ratio and Fibroblasts Enables Precise Classification of Stroma Quality and Quantity in Predicting Colorectal Cancer Recurrence.","authors":"Minsun Jung, Jun Yong Kim, Hoein Jeong, Aaron Valero Puche, Sanghoon Song, Soo Ick Cho, Minsun Jung","doi":"10.1159/000546021","DOIUrl":"10.1159/000546021","url":null,"abstract":"<p><strong>Introduction: </strong>The tumor microenvironment plays a crucial role in the progression and prognosis of colorectal cancer (CRC). Among its components, the tumor-stroma ratio (TSR) and cancer-associated fibroblasts (CAFs) have emerged as significant prognostic markers. However, conventional assessments of TSR and CAF density remain subjective and labor-intensive, limiting their clinical applicability.</p><p><strong>Methods: </strong>We utilized an artificial intelligence (AI)-based whole slide image analysis platform, Lunit SCOPE IO, to objectively quantify TSR and CAF density in tissue samples from 207 treatment-naïve patients with stage II and III CRC.</p><p><strong>Results: </strong>Our analysis demonstrated that both TSR (log-rank p < 0.0001) and CAF density (log-rank p = 0.017) were independently associated with disease-free survival (DFS). These AI-derived markers outperformed conventional prognostic factors. Furthermore, integrating TSR and CAF density with existing high-risk criteria enabled reclassification of additional patients as high risk, enhancing DFS prediction and reducing false-negative rates.</p><p><strong>Conclusion: </strong>AI-powered histopathological quantification of TSR and CAF density improves prognostic accuracy in CRC and offers a promising approach for refining risk stratification. These findings support the integration of AI-based pathology into clinical practice to enhance diagnostic precision and patient management.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"276-287"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneity of Lung Cancer: The Histopathological Diversity and Tumour Classification in the Artificial Intelligence Era.","authors":"Raquel Ramos, Conceição Souto Moura, Mariana Costa, Nuno Jorge Lamas, Lígia Prado E Castro, Renato Correia, Diogo Garcez, José Miguel Pereira, Carlos Sousa, Nuno Vale","doi":"10.1159/000544892","DOIUrl":"10.1159/000544892","url":null,"abstract":"<p><strong>Background: </strong>Lung cancer is the most common cancer worldwide and is also the leading cause of cancer-related mortality. Its poor prognosis is primarily attributed to unspecific symptoms that result in late diagnosis, and its heterogeneous nature that further complicates treatment. This heterogeneity is largely driven by the diversity in histological subtypes, significantly impacting the clinical course of patients. Therefore, tumour subtyping using haematoxylin and eosin staining and immunohistochemistry is crucial for predicting patients' outcomes, making an accurate diagnosis, and choosing the appropriate treatment approach. Small-cell lung cancer and non-small cell lung cancer are the two major types, and subclassifying non-small cell lung cancer is essential to identify genetic alterations and, consequently, choose an adequate targeted therapy.</p><p><strong>Summary: </strong>This article reviews all these lung tumour characteristics, specifying histological types and subtypes, and presenting their distinct features. To aid understanding, complementary images from Unilabs illustrate various lung tumour subtypes. Additionally, alternative approaches using artificial intelligence to improve tumour classification are reviewed, along with a discussion of their limitations.</p><p><strong>Key messages: </strong>Thus, lung tumour classification is crucial for cancer treatment; nonetheless, it can be a subjective process, reliant on the pathologist's interpretation. In the era of artificial intelligence and deep/machine learning, the classification of lung cancer subtypes has the potential to become more efficient, accurate, and consistent. These advancements could lead to faster diagnosis and treatment decisions, ultimately improving patient survival and quality of care. Harnessing AI tools may address the limitations of subjective interpretation, offering a promising avenue for enhancing precision in lung cancer diagnostics.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"239-250"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144027709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trop2 Expression in Correlation to the Molecular Subtype in Vulvar Squamous Cell Carcinomas.","authors":"Anne Kathrin Höhn, Benjamin Wolf, Mirjam Forberger, Christine E Brambs, Blake Gilks, Lien Hoang, Grit Gesine Ruth Hiller, Jessica N McAlpine, Amy Jamieson, Yvette Drew, Lars-Christian Horn","doi":"10.1159/000543554","DOIUrl":"10.1159/000543554","url":null,"abstract":"<p><strong>Introduction: </strong>Targeted therapy with antibody-drug conjugates (ADCs) has achieved promising results in the treatment of different solid tumors. Sacituzumab-Govitecan (SG), a humanized anti-Trop2 monoclonal antibody linked with the cytotoxic topoisomerase I inhibitor SN-38, has been approved for the treatment of metastatic triple-negative breast cancer. The treatment approach with SG requires the expression of Trop2 within the tumor cells. Trop2 is overexpressed in many other cancer types, suggesting a broader therapeutic application beyond breast cancer to these ADCs. We explore expression of Trop2 vulvar squamous cell carcinomas (VSCCs) and how this relates to molecular classification.</p><p><strong>Methods: </strong>Immunohistochemical Trop2 expression was evaluated on diagnostic biopsies of VSCC using an immunoreactive score. Staining results were compared to the molecular subtype of VSCC.</p><p><strong>Results: </strong>Fifty-seven cases were included in the study. 63.2% of VSCC were p16-ve/p53abn (HPV-independent (p53abn)) molecular subtype, 29.8% p16+ve/p53wt (HPV-associated) and 1.4% p16-ve/p53wt (HPV-independent (p53wt)) tumors. All diagnostic biopsies (N = 57) showed at least a weak Trop2 expression. Moderate and strong expression was seen in 15/17 (88.2%) of the p16-ve/p53abn, 32/36 (88.8%) of the p16+ve/p53wt and 3/4 (75%) of the p16-ve/p53wt molecular subtype. Expression was significantly higher, as assessed by H score, in the HPV-associated VSCC, compared to HPV-independent.</p><p><strong>Conclusion: </strong>VSCCs have high expression of Trop2 and represents a promising therapeutic target. Clinical trials exploring Trop2-directed ADCs such as SG are warranted in this rare cancer type, including in the prognostically poor HPV-independent VSCC with a TP53-mutation (p16-ve/p53abn molecular subtype). The targetable molecule, Trop2, can be easily assessed by immunohistochemistry on diagnostic biopsies from VSCC.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"150-156"},"PeriodicalIF":3.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12136508/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143009448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"KRT18 as a Novel Biomarker of Urothelial Papilloma while Evaluating Low-Grade Papillary Urothelial Neoplasms: Bi-Center Analysis.","authors":"Minsun Jung, Bohyun Kim, Jae Seok Lee, Jun Yong Kim, Dohyun Han, Kwangsoo Kim, Sunah Yang, Eun Na Kim, Hyeyooon Kim, Ilias P Nikas, Sohyeon Yang, Kyung Chul Moon, Hyebin Lee, Han Suk Ryu","doi":"10.1159/000540926","DOIUrl":"10.1159/000540926","url":null,"abstract":"<p><strong>Introduction: </strong>Although urothelial papilloma (UP) is an indolent papillary neoplasm that can mimic the morphology of low-grade papillary urothelial carcinoma (PUC), there is no immunomarker to differentiate reliably these two entities. In addition, the molecular characteristics of UP are not fully understood.</p><p><strong>Methods: </strong>We conducted an in-depth proteomic analysis of papillary urothelial lesions (n = 31), including UP and PUC along with normal urothelium. Protein markers distinguishing UP and PUC were selected with machine learning analysis, followed by internal and external validation using immunohistochemistry.</p><p><strong>Results: </strong>In the proteomic analysis, UP and PUC showed overlapping proteomic profiles. We identified EHD4 and KRT18 as candidate diagnostic biomarkers of UP. Through immunohistochemical validation in two independent cohorts (n = 120), KRT18 was suggested as a novel UP diagnostic marker, able to differentiate UP from low-grade PUC. We also found that 3.5% of patients with UP developed urothelial carcinoma in subsequent resections, supporting the malignant potential of UP. KRT18 downregulation was significantly associated with UPs subsequently progressing to urothelial carcinoma, following their initial diagnosis.</p><p><strong>Conclusion: </strong>This is the first study that successfully revealed UPs comprehensive proteomic landscape, while it also identified KRT18 as a potential diagnostic biomarker of UP.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"28-39"},"PeriodicalIF":3.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142081176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cytological Features of the Emerging Entity Papillary Renal Neoplasm with Reverse Polarity: A Case Report Highlighting the Relevance of Fine-Needle Aspiration in Renal Masses.","authors":"João Lobo, João Castro, Júlia Azevedo, Cláudia Lobo, Ângelo Rodrigues, Isaac Braga, Rui Freitas, Rui Silva-Santos, Ana Peixoto, Rui Henrique, Luís Leça, João Lobo","doi":"10.1159/000545894","DOIUrl":"10.1159/000545894","url":null,"abstract":"<p><strong>Introduction: </strong>Papillary renal neoplasm with reverse polarity (PRNRP) is an emerging entity characterized by distinctive histomorphological and molecular features. Often identified incidentally in imaging studies, its accurate diagnosis is essential considering its favorable prognosis. However, its cytological features need further characterization, since only one single publication with 2 cases diagnosed in fine-needle aspiration biopsies have been reported to date.</p><p><strong>Case presentation: </strong>We report the case of a 70-year-old man recently diagnosed with primary lung adenocarcinoma. Fine-needle aspiration biopsy of a 15-mm nodule in the left kidney revealed cytological features consistent with a papillary neoplasm with eosinophilic features. Immunocytochemistry showed positivity for PAX-8, CK7, and GATA3 and negativity for TTF-1. Next-generation sequencing (NGS) identified a KRAS G12V mutation. Altogether, these findings enabled the diagnosis of PRNRP. The patient underwent conservative management of the renal tumor, which did not recur at 8 months since diagnosis.</p><p><strong>Conclusion: </strong>PRNRP is a recently described tumor which can be managed conservatively. We describe the third case of PRNRP diagnosed on fine-needle aspiration biopsy, which enabled several diagnostic studies, including immunocytochemistry and NGS confirmation. With this case, we highlight the increasing role of fine-needle aspiration biopsy in the clinical management of a subset of patients with small renal masses.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"288-293"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transdifferentiation of Multiple Myeloma into Histiocytic Sarcoma: Case Report of a Highly Unusual Phenomenon.","authors":"Neha Seth, Phyu Thin Naing, Ram Singh, Saroja Geetha, Kalpana Reddy, Xinmin Zhang, Tianyu Yang, Jessica Caro, Wayne Tam","doi":"10.1159/000546669","DOIUrl":"10.1159/000546669","url":null,"abstract":"<p><p><p>Introduction: Transdifferentiation of multiple myeloma (MM) into histiocytic sarcoma (HS) is exceptionally rare. We report a unique case, confirming this phenomenon through cytogenetics and molecular analyses. Case Presentation: A 46-year-old woman with high-risk light chain MM developed extramedullary disease despite multiple lines of therapy. Biopsies revealed atypical histiocytic proliferation consistent with HS. Shared immunoglobulin gene rearrangements, cytogenetic alterations, and gene mutations, including a rare BRAF L485F, confirmed clonal relatedness between the two neoplasms. IGH::MAF translocation specific to MM and IGVH somatic hypermutation in HS suggests divergent evolution from a putative germinal center B-cell (GCB) precursor. Conclusions: This case highlights lineage plasticity of MM to undergo HS transdifferentiation, potentially mediated through a mutated common GCB precursor antecedent to the plasma cell stage, and the subsequent development of HS and MM through acquisition of additional genetic events. Recognition of this exceptional phenomenon and understanding its underlying mechanism have implications for diagnosis, classification, and personalized treatment. </p>.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"361-371"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12270463/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144249117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel Role of Microtubule-Associated Serine/Threonine Kinase Like as a Good Prognostic Factor in Oral Squamous Cell Carcinoma and Evidences for a Link with Smad7.","authors":"Esperanza Pozo-Agundo, Miguel Álvarez-González, Paloma Lequerica-Fernández, Sergi Herrera I Nogués, Juan Pablo Rodrigo, Tania Rodríguez-Santamarta, Héctor E Torres-Rivas, Saúl Álvarez-Teijeiro, Juana María García-Pedrero, Mónica Álvarez-Fernández, Juan Carlos de Vicente","doi":"10.1159/000544183","DOIUrl":"10.1159/000544183","url":null,"abstract":"<p><strong>Introduction: </strong>Upregulated microtubule-associated serine/threonine kinase like (MASTL), a cell cycle kinase required for a progression through mitosis, expression has been associated to poor prognosis. This study aimed to investigate the clinical relevance of MASTL expression in oral squamous cell carcinoma (OSCC) and a possible mechanistic link with epithelial-mesenchymal transition (EMT).</p><p><strong>Methods: </strong>Immunohistochemical analysis of MASTL, E-cadherin, vimentin, and Smad7 was performed in paraffin-embedded tissue specimens from 148 OSCC patients.</p><p><strong>Results: </strong>Nuclear MASTL expression was detected in 115 (77.7%) OSCC specimens. High MASTL expression was significantly associated with the male gender, smoking habit, T stage, early clinical stage, and absence of vascular invasion. MASTL expression was inversely correlated with Smad7, whereas no association was observed with E-cadherin and vimentin. Patients harboring tumors with low MASTL expression exhibited a poorer overall survival. Smad7 expression was significantly related to reduced disease-specific and overall survival. High levels of MASTL expression were associated with better prognosis in T3 patients, N0 cases, and patients treated by surgery combined with radiotherapy and chemotherapy.</p><p><strong>Conclusion: </strong>The present study uncovers MASTL as a good prognostic factor in OSCC and a potential link with EMT via Smad7.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"189-201"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence Recognition Model Using Liquid-Based Cytology Images to Discriminate Malignancy and Histological Types of Non-Small-Cell Lung Cancer.","authors":"Ryota Tanaka, Yukihiro Tsuboshita, Mitsuaki Okodo, Rei Settsu, Kohei Hashimoto, Keisei Tachibana, Kazumasa Tanabe, Koji Kishimoto, Masachika Fujiwara, Junji Shibahara","doi":"10.1159/000541148","DOIUrl":"10.1159/000541148","url":null,"abstract":"<p><strong>Introduction: </strong>Artificial intelligence image recognition has applications in clinical practice. The purpose of this study was to develop an automated image classification model for lung cancer cytology using a deep learning convolutional neural network (DCNN).</p><p><strong>Methods: </strong>Liquid-based cytology samples from 8 normal parenchymal (N), 22 adenocarcinoma (ADC), and 15 squamous cell carcinoma (SQCC) surgical specimens were prepared, and 45 Papanicolaou-stained slides were scanned using whole-slide imaging. The final dataset of 9,141 patches consisted of 2,737 N, 4,756 ADC, and 1,648 SQCC samples. Densenet-121 was used as the DCNN to classify N versus malignant (ADC+SQCC) and ADC versus SQCC images. AdamW optimizer and 5-fold cross-validation were used in the training.</p><p><strong>Results: </strong>For malignancy prediction, the sensitivity, specificity, and accuracy were 0.97, 0.85, and 0.94, respectively, in the patch-level classification, and 0.92, 0.88, and 0.91, respectively, in the case-level classification. For SQCC prediction, the sensitivity, specificity, and accuracy were 0.86, 0.91, and 0.90, respectively, in the patch-level classification and 0.73, 0.82, and 0.78, respectively, in the case-level classification.</p><p><strong>Conclusion: </strong>The DCNN model performed excellently in predicting malignancy and histological types of lung cancer. This model may be useful for predicting cytopathological diagnosis in clinical situations by reinforcing training.</p>","PeriodicalId":19805,"journal":{"name":"Pathobiology","volume":" ","pages":"52-62"},"PeriodicalIF":3.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142093666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}