A Machine-Learning Approach Using PET-Based Radiomics to Predict the Histological Subtypes of Lung Cancer

Abstract

Purpose We sought to distinguish lung adenocarcinoma (ADC) from squamous cell carcinoma using a machine-learning algorithm with PET-based radiomic features. Methods A total of 396 patients with 210 ADCs and 186 squamous cell carcinomas who underwent FDG PET/CT prior to treatment were retrospectively analyzed. 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. The clinical and radiomic features were ranked, and a subset of useful features was selected based on Gini coefficient scores in terms of associations with histological class. The areas under the receiver operating characteristic curves (AUCs) of classifications afforded by several machine-learning algorithms (random forest, neural network, naive Bayes, logistic regression, and a support vector machine) were compared and validated via random sampling. Results We developed and validated a PET-based radiomic model 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). Conclusions A machine-learning approach successfully identified the histological subtypes of lung cancer. A PET-based radiomic features may help clinicians improve the histopathologic diagnosis in a noninvasive manner.

Machine learning based on clinico-biological features integrated 18F-FDG PET/CT radiomics for distinguishing squamous cell carcinoma from adenocarcinoma of lung

“…This study also explored whether the prediction performance based on radiomics could be further improved by combining with clinical factors and tumor marker levels. The Combined Model established in the present study not only significantly improved the prediction efficiency for subtype compared to these factors alone in both the training and validation sets (AUCs = 0.932 (training set), 0.901 (validation set), respectively) but also had higher performance than previous researches [14][15][16][17]. This discrepancy may be related to the complete and standard preoperative baseline data and postoperative pathological reports from a single center, as well as the appropriate algorithm [37].…”

“…18 F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT)-based radiomics have been shown to have potential in differentiating ADC from SCC [14,15]. Further studies have revealed that the discrimination performance could be further improved by combining with clinical features, like sex and smoking history (area under curve (AUC) = 0.859), which are higher than that of radiomic alone [16,17]. However, only PET radiomic parameters were extracted and analyzed in the above studies.…”

Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines

“…The complexity of the non-imaging data in multimodal fusion work was limited, particularly in the context of available featurerich and time-series data in the EHR. Instead, most studies focused primarily on basic demographic information such as age and gender 25,27,39 , a limited range of categorical clinical history such as hypertension or smoking status 32,34 or disease-specific clinical features known to be strongly associated with the disease of interest such as APOE4 for Alzheimer's 25,28,33,36 or PSA blood test for prediction of prostate cancer 40 . While selecting features known to be associated with disease is meaningful, future work may further benefit from utilizing large volumes of feature-rich data, as seen in fields outside medicine such as autonomous driving 44,45 .…”

“…Out of these five studies, two applied feature selection strategies to reduce the feature dimension and improve predictive performance. The employed feature selection strategies included a rank-based method using Gini coefficients 32 , a filter-based method based on mutual information of the features 35 , and a genetic-algorithm based method 35 . Seven of the early fusion studies compared the performance of their fusion models against single modality models ( Table 1).…”

Clinical Trials for Artificial Intelligence in Cancer Diagnosis: A Cross-Sectional Study of Registered Trials in ClinicalTrials.gov

“…Ten trials were designed to diagnose lung cancer. In terms of the imaging diagnosis of lung cancer, it was reported that machine learning could predict the histological type of lung cancer through the imaging characteristics of PET/CT (18).…”