Machine Learning-Based Radiomics Signatures for EGFR and KRAS Mutations Prediction in Non-Small-Cell Lung Cancer
| Autor: | Yung-Chieh Chen, Van Hiep Nguyen, Cheng Yu Chen, Nguyen Quoc Khanh Le, Sho-Jen Cheng, Quang Hien Kha |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Male
Lung Neoplasms Rat Sarcoma computer.software_genre medicine.disease_cause feature selection Radiomics Carcinoma Non-Small-Cell Lung genetic algorithm Medicine Epidermal growth factor receptor Biology (General) Spectroscopy Aged 80 and over biology General Medicine Middle Aged Computer Science Applications ErbB Receptors Chemistry machine learning non-small-cell lung carcinoma Female Non small cell KRAS Supervised Machine Learning Algorithms QH301-705.5 radiogenomics Radiogenomics Feature selection Machine learning Catalysis Article Inorganic Chemistry Proto-Oncogene Proteins p21(ras) Humans Physical and Theoretical Chemistry Lung cancer Molecular Biology QD1-999 neoplasms Aged Neoplasm Staging eXtreme Gradient Boosting business.industry Organic Chemistry Reproducibility of Results KRAS mutation medicine.disease respiratory tract diseases ROC Curve Mutation biology.protein Artificial intelligence EGFR mutation business Tomography X-Ray Computed low-dose computed tomography computer Biomarkers |
| Zdroj: | International Journal of Molecular Sciences Volume 22 Issue 17 International Journal of Molecular Sciences, Vol 22, Iss 9254, p 9254 (2021) |
| ISSN: | 1422-0067 |
| DOI: | 10.3390/ijms22179254 |
| Popis: | Early identification of epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations is crucial for selecting a therapeutic strategy for patients with non-small-cell lung cancer (NSCLC). We proposed a machine learning-based model for feature selection and prediction of EGFR and KRAS mutations in patients with NSCLC by including the least number of the most semantic radiomics features. We included a cohort of 161 patients from 211 patients with NSCLC from The Cancer Imaging Archive (TCIA) and analyzed 161 low-dose computed tomography (LDCT) images for detecting EGFR and KRAS mutations. A total of 851 radiomics features, which were classified into 9 categories, were obtained through manual segmentation and radiomics feature extraction from LDCT. We evaluated our models using a validation set consisting of 18 patients derived from the same TCIA dataset. The results showed that the genetic algorithm plus XGBoost classifier exhibited the most favorable performance, with an accuracy of 0.836 and 0.86 for detecting EGFR and KRAS mutations, respectively. We demonstrated that a noninvasive machine learning-based model including the least number of the most semantic radiomics signatures could robustly predict EGFR and KRAS mutations in patients with NSCLC. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|