Jihong Chen

Dosimetric divergence in ICBT vs. IC/ISBT configurations: Comparative analysis of three optimization algorithms for cervical cancer brachytherapy

Objective To compare dosimetric differences among graphical-based manual planning (MA), simulated annealing inverse optimization (IPSA), and hybrid inverse optimization (HIPO) for cervical cancer in both intra-cavitary brachytherapy (ICBT) and interstitial brachytherapy combined with ICBT (IC/ISBT) settings, providing evidence for clinical optimization method selection. Methods This study consisted of 60 cervical cancer patients undergoing CT-guided three-dimensional brachytherapy, including 30 ICBT patients and 30 IC/ISBT patients. Plans were generated using MA, IPSA, and HIPO. The dosimetric parameters for the high-risk clinical target volume (HRCTV) including D 100% , V 150% , V 200% , conformity index (CI), homogeneity index (HI) were compared. Meanwhile, the dosimetric parameters D 1cc , D 2cc for the bladder, rectum, sigmoid, and total treatment time were evaluated. Results Compared with MA, both IPSA and HIPO delivered lower doses to organs at risk (OARs). The total treatment time was significantly shorter for HIPO compared to IPSA and MA (P < 0.05). In ICBT patients, the D 1cc and D 2cc of OARs were lower for IPSA compared to HIPO (P > 0.05), while the CI was significantly better for HIPO (P < 0.05). Nevertheless, in IC/ISBT patients, D 2cc of rectum for HIPO was significantly lower compared to IPSA (P < 0.05), with better CI. Conclusion Inverse optimization effectively reduces doses to OARs while maintaining target coverage. HIPO appears to be the preferred choice for IC/ISBT, due to shortened treatment time, superior CI and rectal protection compared with IPSA.

Automated Intensity Modulated Radiation Therapy Treatment Planning for Cervical Cancer Based on Convolution Neural Network

Purpose: To develop and evaluate an automatic intensity-modulated radiation therapy (IMRT) program for cervical cancer, including a Convolution Neural Network (CNN)-based prediction model and an automated optimization strategy. Methods: A CNN deep learning model was trained to predict a patient-specify set of IMRT objectives based on overlap volume histograms (OVH) and high-quality plan of previous patients. A total of 140 cervical cancer patients were enrolled in this study, including 100 patients in the training set, 20 patients in the validation set and 20 patients in the testing set. The input of this model was OVH data and the output were values of IMRT plan objectives. For patients in the testing set, the set of planning objectives were predicted by the CNN model and used to automatically generate IMRT plans. Meanwhile, manual plans of these patients were generated by 1 beginner planner and 1 senior planner respectively. Finally, dose distribution, dosimetric parameters and planning time were analyzed. In addition, the 3 types of plans were blinded compared and ranked by an experienced oncologist. Results: There were almost no statistically differences among these 3 types of plans in target coverage and dose conformity. Dose homogeneity were slightly decreased while the average dose and parameters for most organs-at-risk (OARs) were decreased in automatic plans. Especially in comparison with manual plans by the beginner planner, V40 of bladder and rectum decreased 6.3% and 12.3%, while mean dose of rectum and marrow were 1.1 Gy and 1.8 Gy lower with automatic plans (either P < 0.017). In the blinded comparison, automatic plans were chosen as best plan in 14 cases. Conclusions: For cervical cancer, automatic IMRT plans optimized from the CNN generated objectives have superior dose sparing without compromising of target dose. It significantly reduced the planning time.