Quantitative radiomic analysis of computed tomography scans using machine and deep learning techniques accurately predicts histological subtypes of non-small cell lung cancer: A retrospective analysis
European Journal of Surgical Oncology · 2025
DOI: 10.1016/j.ejso.2025.110376 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Surgical Oncology, 2025. Verfasst von Suhrud Panchawagh und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Mayo Clinic, Scottsdale, AZ, USA. Electronic address: panchawagh.suhrud@mayo.edu. Hauptthemen laut MEDLINE: Carcinoma, Non-Small-Cell Lung, Lung Neoplasms, Tomography, X-Ray Computed, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Non-small cell lung cancer (NSCLC) histological subtypes impact treatment decisions. While pre-surgical histopathological examination is ideal, it's not always possible. CT radiomic analysis shows promise in predicting NSCLC histological subtypes. OBJECTIVE: To predict NSCLC histological subtypes using machine learning and deep learning models using Radiomic features. METHODS: 422 lung CT scans from The Cancer Imaging Archive (TCIA) were analyzed. Primary neoplasms were segmented by expert radiologists. Using PyRadiomics, 2446 radiomic features were extracted; post-selection, 179 features remained. Machine learning models like logistic regression (LR), Support vector machine (SVM), Random Forest (RF), XGBoost, LightGBM, and CatBoost were employed, alongside a deep neural network (DNN) model. RESULTS: RF demonstrated the highest accuracy at 78 % (95 % CI: 70 %-84 %) and AUC-ROC at 94 % (95 % CI: 90 %-96 %). LightGBM, XGBoost, and CatBoost had AUC-ROC values of 95 %, 93 %, and 93 % respectively. The DNN's AUC was 94.4 % (95 % CI: 94.1 %-94.6 %). Logistic regression had the least efficacy. For histological subtype prediction, random forest, boosting models, and DNN were superior. CONCLUSIONS: Quantitative radiomic analysis with machine learning can accurately determine NSCLC histological subtypes. Random forest, ensemble models, and DNNs show significant promise for pre-operative NSCLC classification, which can streamline therapy decisions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology, Mayo Clinic, Scottsdale, AZ, USA. Electronic address: panchawagh.suhrud@mayo.edu.
- Indian Institute of Technology, Kharagpur, India.
- Byramjee Jeejeebhoy Government Medical College and Sassoon General Hospitals, Pune, India.
- Department of Neurosurgery, Stanford University, CA, USA.
- Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, India.
- Tata Memorial Hospital, Mumbai, India.
Zitieren
APA
Panchawagh, S., Halder, A., Haldule, S., Sanker, V., Lalwani, D., Sequeria, R., Naik, H., & Desai, A. (2025). Quantitative radiomic analysis of computed tomography scans using machine and deep learning techniques accurately predicts histological subtypes of non-small cell lung cancer: A retrospective analysis. European Journal of Surgical Oncology. https://doi.org/10.1016/j.ejso.2025.110376
Vancouver
Panchawagh S, Halder A, Haldule S, Sanker V, Lalwani D, Sequeria R, et al. Quantitative radiomic analysis of computed tomography scans using machine and deep learning techniques accurately predicts histological subtypes of non-small cell lung cancer: A retrospective analysis. European Journal of Surgical Oncology. 2025. doi:10.1016/j.ejso.2025.110376
BibTeX
@article{Panchawagh2025,
author = {Panchawagh, Suhrud and Halder, Arita and Haldule, Saloni and Sanker, Vivek and Lalwani, Devansh and Sequeria, Rachel and Naik, Harshika and Desai, Atman},
title = {Quantitative radiomic analysis of computed tomography scans using machine and deep learning techniques accurately predicts histological subtypes of non-small cell lung cancer: A retrospective analysis},
journal = {European Journal of Surgical Oncology},
year = {2025},
doi = {10.1016/j.ejso.2025.110376}
}
EUVIMED