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.

Feasibility of automatic IMRT planning for cervical cancer based on a database of previously-treated patients / 中华放射肿瘤学杂志

Objective@#To develop and evaluate an automatic intensity-modulated radiation therapy (IMRT) program for cervical cancer based on a database of overlap volume histogram (OVH) and high-quality cervical IMRT plans for previously-treated patients.@*Methods@#A database consisting of high-quality IMRT plans and OVHs from 200 cervical cancer patients was established. OVHs of another 26 cervical cancer patients were converted into gray level images to calculate the image similarity compared with those from the database. The planning optimization function of the patients from the database with the highest image similarity was selected and inherent Pinnacle3 scripts were utilized to automatically generate IMRT plan. Finally, the dosimetric parameters, plan quality and design time were statistically compared between the automatic and manual plans.@*Results@#The target coverage, conformity index and homogeneity index did not significantly differ between two plans (all P>0.05). The V40, V45 and mean dose for the rectum in the automatic plans were significantly decreased by 6.1%, 1.3% and 50.7 cGy than those in the manual plans (all P<0.05). Compared with the manual plans, the mean dose for the intestine and femur in the automatic plans were significantly reduced by 31.7 cGy and 188.9 cGy (both P<0.05), whereas the mean dose for the ilium was slightly decreased by 92.3 cGy in the automatic plans (P>0.05). The plan design time was shortened by 71% in the automatic plans.@*Conclusions@#The automatic IMRT plans based on a database of OVH and high-quality IMRT plans can not only significantly shorten the plan design time, but also reduce the irradiated dose of normal tissues without compromising the target coverage and conformity index.

Feasibility of automatic IMRT planning for cervical cancer based on a database of previously-treated patients / 中华放射肿瘤学杂志

Objective To develop and evaluate an automatic intensity-modulated radiation therapy (IMRT) program for cervical cancer based on a database of overlap volume histogram (OVH) and high-quality cervical IMRT plans for previously-treated patients.Methods A database consisting of high-quality IMRT plans and OVHs from 200 cervical cancer patients was established.OVHs of another 26 cervical cancer patients were converted into gray level images to calculate the image similarity compared with those from the database.The planning optimization function of the patients from the database with the highest image similarity was selected and inherent Pinnacle3 scripts were utilized to automatically generate IMRT plan.Finally,the dosimetric parameters,plan quality and design time were statistically compared between the automatic and manual plans.Results The target coverage,conformity index and homogeneity index did not significantly differ between two plans (all P＞0.05).The V40,V45 and mean dose for the rectum in the automatic plans were significantly decreased by 6.1％,1.3％ and 50.7 cGy than those in the manual plans (all P＜0.05).Compared with the manual plans,the mean dose for the intestine and femur in the automatic plans were significantly reduced by 31.7 cGy and 188.9 cGy (both P＜0.05),whereas the mean dose for the ilium was slightly decreased by 92.3 cGy in the automatic plans (P＞ 0.05).The plan design time was shortened by 71％ in the automatic plans.Conclusions The automatic IMRT plans based on a database of OVH and high-quality IMRT plans can not only significantly shorten the plan design time,but also reduce the irradiated dose of normal tissues without compromising the target coverage and conformity index.