Transfer-Learning Deep Radiomics and Hand-Crafted Radiomics for Classifying Lymph Nodes from Contrast-Enhanced Computed Tomography in Lung Cancer

Abstract

Objectives: Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies. Methods: In this study, 100 lung cancer patients underwent a contrast-enhanced 18F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional “hand-crafted” radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii). Results: In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865–0.878), SBS 35.8 (34.2–37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively). Conclusion: Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.

Machine learning and radiomics for segmentation and classification of adnexal masses on ultrasound

“…To contextualise the ODS model’s performance, deep learning and radiomics have shown similar success in other pathologies, achieving AUCs of 0.90 32 , 0.72 33 , 0.83 34 , 0.76 35 and 0.72 36 in differentiating lung metastases, predicting lymph node metastasis in breast cancer, classifying lymph nodes in lung cancer, predicting human epidermal growth factor receptor 2 (HER2) status in breast cancer and improving lung cancer diagnosis, respectively. The ODS model’s performance (F1-score 0.83, AUC 0.90) is aligned with these applications, underscoring its potential in adnexal mass classification.…”

Application of radiomics in diagnosis and treatment of lung cancer

“…Yang et al (Yang et al, 2018) combined preoperative venous phase enhanced CT images' radiomics features with clinical features, achieving AUC values of 0.911 and 0.871 for predicting lymph node metastasis. Ferreira Junior et al (Ferreira-Junior et al, 2020) calculated various radiomic features significantly associated with distant metastasis, nodal metastasis, and histology, yielding AUC values of 0.92 and using the random forest model (Laqua et al, 2023). The PET/ CT-based radiomics nomogram exhibited predictive ability for occult lymph node metastasis in NSCLC, with AUCs of 0.884 in the training set and 0.881 in the testing set (Qiao et al, 2022).…”