Author: Ke Colin Huang, Zirui Jiang, Joshua Low, Christopher F. Njeh, Oluwaseyi Oderinde, Yong Yue 👨🔬
Affiliation: Purdue University, Indiana University School of Medicine, Department of Radiation Oncology 🌍
Purpose: Enhancing the accuracy of tumor response predictions enables the development of tailored therapeutic strategies for patients with breast cancer (BCa). In this study, we developed deep-radiomic models to enhance the prediction of chemotherapy response after the first treatment cycle.
Methods: 18F- Fludeoxyglucose (FDG) PET/CT imaging data and clinical record from 60 BCa patients. PET/CT scans were performed at three treatment stages: before chemotherapy (T1), after the first cycle (T2), and post-second cycle or full regimen (T3). The patient's primary gross tumor volume (GTV) was delineated on PET images using a 40% threshold of SUVmax. Radiomic features were extracted from the GTV based on the PET/CT images. In addition, a Squeeze-and-Excitation Network (SENet) deep learning model was employed to generate additional features from the PET/CT images for combined analysis. A XGBoost machine learning model was developed and compared with the conventional machine learning (ML) algorithm (random forest [RF], logistic regression [LR] and support vector machine [SVM]). The performance of each model was assessed using receiver operating characteristics area under the curve (ROC AUC) analysis, and prediction accuracy in a validation cohort.
Results: The AUC values for the ML models using only radiomic features were 0.85(XGBoost, 95%CI: 0.73-0.97), 0.76 (RF, 95%CI: 0.61-0.91), 0.80 (LR, 95%CI: 0.66-0.94), and 0.59 (SVM, 95%CI: 0.41-0.77), with XGBoost showing the best performance. After incorporating additional deep-learning-derived features from SENet, the AUC values increased to 0.92 (95%CI: 0.85-1.00), 0.90 (95%CI: 0.82-0.98), 0.88 (95%CI: 0.79-0.97), and 0.61 (95%CI: 0.47-0.75), respectively, demonstrating significant improvements in predictive accuracy.
Conclusion: Integrating deep learning-derived features significantly enhanced the performance of predictive models for chemotherapy response in breast cancer patients. This study demonstrated the superior predictive capability of the XGBoost model, emphasizing its potential to optimize personalized therapeutic strategies by accurately identifying patients unlikely to respond to chemotherapy after the first treatment cycle.