Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background: Rapid on-site evaluation (ROSE) plays an important role during transbronchial sampling, providing an intraoperative cytopathologic evaluation. However, the shortage of cytopathologists limits its wide application. This study aims to develop a deep learning model to automatically analyze ROSE cytological images.
Methods: The hierarchical multi-label lung cancer subtyping (HMLCS) model that combines whole slide images of ROSE slides and serum biological markers was proposed to discriminate between benign and malignant lesions and recognize different subtypes of lung cancer. A dataset of 811 ROSE slides and paired serum biological markers was retrospectively collected between July 2019 and November 2020, and randomly divided to train, validate, and test the HMLCS model. The area under the curve (AUC) and accuracy were calculated to assess the performance of the model, and Cohen's kappa (κ) was calculated to measure the agreement between the model and the annotation. The HMLCS model was also compared with professional staff.
Results: The HMLCS model achieved AUC values of 0.9540 (95% confidence interval [CI]: 0.9257-0.9823) in malignant/benign classification, 0.9126 (95% CI: 0.8756-0.9365) in malignancy subtyping (non-small cell lung cancer [NSCLC], small cell lung cancer [SCLC], or other malignancies), and 0.9297 (95% CI: 0.9026-0.9603) in NSCLC subtyping (lung adenocarcinoma [LUAD], lung squamous cell carcinoma [LUSC], or NSCLC not otherwise specified [NSCLC-NOS]), respectively. In total, the model achieved an AUC of 0.8721 (95% CI: 0.7714-0.9258) and an accuracy of 0.7184 in the six-class classification task (benign, LUAD, LUSC, NSCLC-NOS, SCLC, or other malignancies). In addition, the model demonstrated a κ value of 0.6183 with the annotation, which was comparable to cytopathologists and superior to trained bronchoscopists and technicians.
Conclusion: The HMLCS model showed promising performance in the multiclassification of lung lesions or intrathoracic lymphadenopathy, with potential application to provide real-time feedback regarding preliminary diagnoses of specimens during transbronchial sampling procedures.
Clinical Trial Number: Not applicable.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11523640 | PMC |
| http://dx.doi.org/10.1186/s12931-024-03021-8 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Mechanistic insights into MET exon 14 skipping mutations and their role in tumor progression.
Biochem Soc Trans
September 2025
Department of Biochemistry, McGill University, Montréal, QC, Canada.
The MET receptor tyrosine kinase is a pivotal regulator of cellular survival, motility, and proliferation. Mutations leading to skipping of exon 14 (METΔex14) within the juxtamembrane domain of MET impair receptor degradation and prolong oncogenic signaling, contributing significantly to tumor progression across multiple cancer types. METΔex14 mutations are associated with aggressive clinical behavior, therapeutic resistance, and poor outcomes.
View Article and Find Full Text PDFSTmiR: A Novel XGBoost-based framework for spatially resolved miRNA activity prediction in cancer transcriptomics.
PLoS One
September 2025
Institute of Computational Science and Technology, Guangzhou University, Guangzhou, China.
MicroRNAs (miRNAs) are critical regulators of gene expression in cancer biology, yet their spatial dynamics within tumor microenvironments (TMEs) remain underexplored due to technical limitations in current spatial transcriptomics (ST) technologies. To address this gap, we present STmiR, a novel XGBoost-based framework for spatially resolved miRNA activity prediction. STmiR integrates bulk RNA-seq data (TCGA and CCLE) with spatial transcriptomics profiles to model nonlinear miRNA-mRNA interactions, achieving high predictive accuracy (Spearman's ρ > 0.
View Article and Find Full Text PDF1p-Enh-regulated CYP4B1 alleviates NNK-induced heart failure and lung cancer via the STAT3 pathway.
PLoS One
September 2025
Biobank of Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research & The Affiliated Cancer Hospital of Nanjing Medical University, Nanjing, Jiangsu, PR China.
Heart failure (HF) and lung cancer (LC) often coexist, yet their shared molecular mechanisms are unclear. We analyzed transcriptome data from the NCBI Gene Expression Omnibus (GEO) database (GSE141910, GSE57338) to identify 346 HF‑related differentially expressed genes (DEGs), then combined weighted gene co-expression network analysis (WGCNA) pinpointed 70 hub candidates. Further screening of these 70 hub candidates in TCGA lung cancer cohorts via LASSO, Random Forest, and multivariate Cox regression suggested CYP4B1 as the only independent prognostic marker.
View Article and Find Full Text PDFA volumetric modulated arc therapy-based dynamic conformal arc technique with limited monitor units (VMATliMU) to reduce multileaf collimator interplay effects: A computational phantom study for stage I non-small-cell lung cancer.
PLoS One
September 2025
Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Korea.
Volumetric modulated arc therapy (VMAT) for lung cancer involves complex multileaf collimator (MLC) motion, which increases sensitivity to interplay effects with tumour motion. Current dynamic conformal arc methods address this issue but may limit the achievable dose distribution optimisation compared with standard VMAT. This study examined the clinical utility of a VMAT technique with monitor unit limits (VMATliMU) to mimic conformal arc delivery and reduce interplay effects while maintaining plan quality.
View Article and Find Full Text PDFBroad-Spectrum Antibiotic Use at the End of Life in Patients With Advanced Cancer.
JAMA Netw Open
September 2025
Department of Internal Medicine, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, South Korea.
Importance: Patients with advanced cancer frequently receive broad-spectrum antibiotics, but changing use patterns across the end-of-life trajectory remain poorly understood.
Objective: To describe the patterns of broad-spectrum antibiotic use across defined end-of-life intervals in patients with advanced cancer.
Design, Setting, And Participants: This nationwide, population-based, retrospective cohort study used data from the South Korean National Health Insurance Service database to examine broad-spectrum antibiotic use among patients with advanced cancer who died between July 1, 2002, and December 31, 2021.