A Comparative Study of Radiomics and Deep-Learning Approaches for Predicting Surgery Outcomes in Early-Stage Non-Small Cell Lung Cancer (NSCLC)
H Zhang1, Z Yang2, B Ackerson2, Z Hu1, M Khazaieli2, C Kelsey2, F Yin2, C Wang2*, (1) Duke Kunshan University, Kunshan, Jiangsu, China, (2) Duke University, Durham, NC
Presentations
SU-H400-IePD-F5-3 (Sunday, 7/10/2022) 4:00 PM - 4:30 PM [Eastern Time (GMT-4)]
Exhibit Hall | Forum 5
Purpose: To compare radiomics and deep-learning (DL) methods for predicting NSCLC surgical treatment failure.
Methods: A cohort of 83 patients undergoing lobectomy or wedge resection for early-stage NSCLC from our institution was studied. There were 7 local failures and 16 non-local failures (regional and/or distant). Gross tumor volumes (GTV) were contoured on pre-surgery CT datasets after 1mm3 isotropic resolution resampling. For the radiomics analysis, 92 radiomics features were extracted from the GTV and z-score normalizations were performed. The multivariate association between the extracted features and clinical endpoints were investigated using a random forest model following 70%-30% training-test split. For the DL analysis, both 2D and 3D model designs were executed using two different deep neural networks as transfer learning problems: in 2D-based design, 8x8cm2 axial fields-of-view(FOVs) centered within the GTV were adopted for VGG-16 training; in 3D-based design, 8x8x8 cm3 FOVs centered within the GTV were adopted for U-Net’s encoder path training. In both designs, data augmentation (rotation, translation, flip, noise) was included to overcome potential training convergence problems due to the imbalanced dataset, and the same 70%-30% training-test split was used. The performances of the 3 models (Radiomics, 2D-DL, 3D-DL) were tested to predict outcomes including local failure, non-local failure, and disease-free survival. Sensitivity/specificity/accuracy/ROC results were obtained from their 20 trained versions.
Results: The radiomics models showed limited performances in all three outcome prediction tasks. The 2D-DL design showed significant improvement compared to the radiomics results in predicting local failure (ROC AUC = 0.546±0.056). The 3D-DL design achieved the best performance for all three outcomes (local failure ROC AUC = 0.768 ± 0.051, non-local failure ROC AUC = 0.683±0.027, disease-free ROC AUC = 0.694±0.042) with statistically significant improvements from radiomics/2D-DL results.
Conclusion: 3D-DL execution outperformed the classic radiomics approach in predicting clinical outcomes after surgery for early-stage NSCLC.
Keywords
Taxonomy
TH- Response Assessment: Modeling: Machine Learning
Contact Email