Machine learning for differentiating lung squamous cell cancer from adenocarcinoma using Clinical-Metabolic characteristics and 18F-FDG PET/CT radiomics

• Published in: PloS one Vol. 19; no. 4; p. e0300170
• Main Authors: Zhang, Yalin, Liu, Huiling, Chang, Cheng, Yin, Yong, Wang, Ruozheng
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.04.2024; Public Library of Science (PLoS)
• Subjects: Adenocarcinoma; Adenocarcinoma - diagnostic imaging; Algorithms; Analysis; Biology and Life Sciences; Carcinoma, Non-Small-Cell Lung - diagnostic imaging; Carcinoma, Squamous Cell - diagnostic imaging; Care and treatment; Cell differentiation; Computer and Information Sciences; Diagnosis; Epithelial Cells; Fluorodeoxyglucose F18; Humans; Lung; Lung cancer; Lung cancer, Non-small cell; Lung Neoplasms - diagnostic imaging; Machine Learning; Medical imaging equipment; Medicine and Health Sciences; PET imaging; Physical Sciences; Positron Emission Tomography Computed Tomography; Radiomics; Research and Analysis Methods; Retrospective Studies; Squamous cell carcinoma; China
• DOI: 10.1371/journal.pone.0300170
• ISSN: 1932-6203

Noninvasive differentiation between the squamous cell carcinoma (SCC) and adenocarcinoma (ADC) subtypes of non-small cell lung cancer (NSCLC) could benefit patients who are unsuitable for invasive diagnostic procedures. Therefore, this study evaluates the predictive performance of a PET/CT-based radiomics model. It aims to distinguish between the histological subtypes of lung adenocarcinoma and squamous cell carcinoma, employing four different machine learning techniques. A total of 255 Non-Small Cell Lung Cancer (NSCLC) patients were retrospectively analyzed and randomly divided into the training (n = 177) and validation (n = 78) sets, respectively. Radiomics features were extracted, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was employed for feature selection. Subsequently, models were constructed using four distinct machine learning techniques, with the top-performing algorithm determined by evaluating metrics such as accuracy, sensitivity, specificity, and the area under the curve (AUC). The efficacy of the various models was appraised and compared using the DeLong test. A nomogram was developed based on the model with the best predictive efficiency and clinical utility, and it was validated using calibration curves. Results indicated that the logistic regression classifier had better predictive power in the validation cohort of the radiomic model. The combined model (AUC 0.870) exhibited superior predictive power compared to the clinical model (AUC 0.848) and the radiomics model (AUC 0.774). In this study, we discovered that the combined model, refined by the logistic regression classifier, exhibited the most effective performance in classifying the histological subtypes of NSCLC.