This month's Editor's Favorite article is "A Machine-Learning Approach Using PET-Based Radiomics to Predict the Histological Subtypes of Lung Cancer" by SH Hyun. Authors propose to retrospectively distinguish lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC) using a machine-learning algorithm with PET-based radiomic features in 396 patients (210 ADCs and 186 SCCs) with FDG PET/CT performed prior to treatment. Four clinical features (age, sex, tumor size, and smoking status) and 40 radiomic features were investigated in terms of lung ADC subtype prediction. Radiomic features were extracted from the PET images of segmented tumors using the LIFEx package. Clinical and radiomic features were ranked, and a subset of useful features was extracted based on Gini coefficient scores in terms of associations with histological class.
Area under the receiver operating characteristic curves (AUCs) of classifications were analyzed by five machine-learning algorithms (random forest, neural network, naive Bayes, logistic regression, and a support vector machine) were compared and validated via random sampling.
Authors developed and validated a PET-based radiomic model capable of predicting the histological subtypes of lung cancer. Sex, SUVmax, gray-level zone length nonuniformity, gray-level nonuniformity for zone, and total lesion glycolysis were the 5 best predictors of lung ADC. The logistic regression model outperformed all other classifiers (AUC = 0.859, accuracy = 0.769, F1 score = 0.774, precision = 0.804, recall = 0.746) followed by the neural network model (AUC = 0.854, accuracy = 0.772, F1 score = 0.777, precision = 0.807, recall = 0.750).
Authors conclude that a machine-learning approach successfully identified the histological subtypes of lung cancer. PET-based radiomic features may help clinicians improve the histopathologic diagnosis in a noninvasive manner.