University of Twente Student Theses

Login

Fully automated machine learning based VMAT planning for oropharyngeal cancer

Bruggen, I.G. van (2019) Fully automated machine learning based VMAT planning for oropharyngeal cancer.

Full text not available from this repository.

Full Text Status:Access to this publication is restricted
Abstract:Objective To demonstrate that fully automated Volumetric Modulated Arc Therapy (VMAT) dose distributions for oropharyngeal cancer patients can be generated, with similar quality as the clinical ‘dosimetrists-optimized’ dose distributions, further indicated as reference plans. Method MLO planning involved training of a model, which was used to predict the voxel dose for novel patients. CT scans, structures and dose distributions of 155 consecutive primary Head and Neck Cancer (HNC) patients, previously treated with dual arc VMAT, were retrieved from our clinical database. In the final step, the predicted dose distribution was input to a mimicking optimization to generate a deliverable dose distribution. The main goal of this study, generating clinical acceptable MLO plans, was investigated with a model containing 60 oropharyngeal cancer plans. Validation was performed with 39 oropharyngeal cancer patients to tune prediction and mimicking settings using both target and Organ At Risk (OAR) quality measures on models with 60 oropharyngeal cancer plans. The dose distributions of the validation plans were compared against the reference plans. Results The predicted dose was in accordance with reference dose for all plans. Plan quality was highly dependent on prediction and mimicking settings. In the final settings, the mimicked plans of the model with 60 oropharyngeal cancer plans had adequate target coverage, acceptable OARs dose and sum NTCP lower or within 2% increase compared to reference plans in 26/39 (67%) plans. Conclusion In this study, we have demonstrated that clinical acceptable MLO VMAT plan quality can be reached in the majority of oropharyngeal cancer patients.
Item Type:Essay (Master)
Faculty:TNW: Science and Technology
Subject:44 medicine
Programme:Technical Medicine MSc (60033)
Link to this item:http://purl.utwente.nl/essays/79371
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page