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.

Download Full-text

A dummy-run evaluation of postoperative hypofractionated intensity-modulated radiation therapy (POHIM-RT) trials for cervical cancer

Journal of Radiation Research ◽

10.1093/jrr/rraa085 ◽

2020 ◽

Vol 62 (1) ◽

pp. 149-154

Author(s):

Won Kyung Cho ◽

Heejung Kim ◽

Won Park ◽

Sang-Won Kim ◽

Jongwon Kim ◽

...

Keyword(s):

Cervical Cancer ◽

Quality Assurance ◽

Radiation Therapy ◽

Organs At Risk ◽

Treatment Plan ◽

Intensity Modulated Radiation Therapy ◽

Target Volume ◽

Similarity Coefficients ◽

Intensity Modulated ◽

And Performance

Abstract The postoperative hypofractionated intensity-modulated radiation therapy (POHIM-RT) trial is a phase II study to evaluate toxicity following hypofractionated intensity modulated radiation therapy (IMRT) for cervical cancer. This study describes the results of a benchmark procedure for RT quality assurance of the POHIM-RT trial. Six participating institutions were provided computed tomography for RT planning and an IMRT plan for a sample and were instructed to delineate volumes, create a treatment plan and quality assurance (QA) plan, and submit the results of all procedures. The inter-institutional agreements on RT volume and plan results were evaluated using the kappa value and dice similarity coefficients. The simultaneous truth and performance level estimation (STAPLE) method was employed to generate a consensus target volume. The treatment volumes, organs-at-risk volumes, and results of the RT plan and QA reported by the institutions were acceptable and adhered well to the protocol. In terms of clinical target volume (CTV) delineation, there were differences between the institutions, particularly in vaginal cuff and paracolpium subsites. Consensus CTV was generated from the collected CTVs with the STAPLE method. The participating institutions showed considerable agreement regarding volume, dose and QA results. To improve CTV agreement in CTV, we provided feedback with images of the consensus target volume and detailed written guidelines for specific subsites that were the most heterogeneous.

Download Full-text

Decreased Radiation Dose to Swallowing Organs at Risk (Pharyngeal, Laryngeal, and Oral Cavity Structures) by “Tongue-Out” Compared to Tongue-In Position During Intensity-Modulated Radiation Therapy for Base of Tongue Cancer

International Journal of Radiation Oncology*Biology*Physics ◽

10.1016/j.ijrobp.2017.06.1431 ◽

2017 ◽

Vol 99 (2) ◽

pp. E347

Author(s):

W.J. Kil ◽

C. Kulasekere ◽

C. Hatch ◽

J. Bugno ◽

R. Derrwaldt

Keyword(s):

At Risk ◽

Radiation Therapy ◽

Radiation Dose ◽

Oral Cavity ◽

Tongue Cancer ◽

Organs At Risk ◽

Intensity Modulated Radiation Therapy ◽

Intensity Modulated ◽

Base Of Tongue

Download Full-text

Dosimetric comparison between 3D conformal and intensity-modulated radiation therapy for prostate cancer

Journal of Radiotherapy in Practice ◽

10.1017/s1460396909990343 ◽

2010 ◽

Vol 9 (2) ◽

pp. 77-85 ◽

Cited By ~ 2

Author(s):

Courtney Buckey ◽

Gregory Swanson ◽

Sotirios Stathakis ◽

Nikos Papanikolaou

Keyword(s):

Radiation Therapy ◽

Organs At Risk ◽

External Beam Radiotherapy ◽

Radiation Therapy Oncology Group ◽

Intensity Modulated Radiation Therapy ◽

Standard Of Care ◽

Target Volume ◽

Conformal Radiation Therapy ◽

Intensity Modulated ◽

3D Crt

AbstractBackground and Purpose: Intensity-modulated radiation therapy (IMRT) is considered by many to be the standard of care in the delivery of external-beam radiotherapy treatments to the prostate. The purpose of this study is to assess the validity of the purported benefits of IMRT.Materials and Methods: Treatment plans were produced for 10 patients using both 3D conformal radiation therapy (3D-CRT) and IMRT, utilising the dose constraints recommended by the Radiation Therapy Oncology Group (RTOG) 0415 protocol. Three IMRT modalities used in this study were linear accelerator based IMRT, helical tomotherapy, and serial tomotherapy. The prescription to the target, 76 Gy, was the same for all plans.Results: In general the 3D-CRT plans satisfied the RTOG criteria for planning target volume (PTV) coverage, and met or bettered the dose criteria for the organs at risk. PTV coverage was more homogeneous for the IMRT plans than the 3D-CRT plans but not significantly improved.Conclusions: Technically, because the IMRT plans required greater effort for the optimisation, longer treatment times and higher monitor units, the use of IMRT for the fulfilment of the protocol’s dosimetric goals was not justified using these constraints.

Download Full-text