Author ORCID Identifier

0000-0003-1583-7121

Date of Graduation

5-2021

Document Type

Dissertation (PhD)

Program Affiliation

Medical Physics

Degree Name

Doctor of Philosophy (PhD)

Advisor/Committee Chair

Laurence Court

Committee Member

Peter Balter

Committee Member

Carlos Cardenas

Committee Member

Caroline Chung

Committee Member

Rebecca Howell

Committee Member

Ann Klopp

Committee Member

Christine Peterson

Abstract

Palliative radiotherapy is an effective treatment for the palliation of symptoms caused by vertebral metastases. Visible evidence of disease is localized on medical images as part of the treatment planning process. However, complicating factors such as time pressures, anatomic variants in the spine, and similarities in adjacent vertebrae are associated with wrong level treatments of the spine. In addition, erroneous manual contouring of anatomic structures is a major failure mode in radiotherapy treatment planning.

The purpose of this study is to mitigate the challenges associated with treatment planning of the spine by automating the treatment planning process for three-dimensional conformal radiotherapy. To accomplish this, deep and machine learning models will work in symphony within a multi-stage framework to perform image-based tasks in place of manual tasks. An automated solution that is efficient, effective, and safe would be especially valuable for clinics seeking to expedite their palliative radiotherapy planning services or optimize their use of diagnostic and simulation CT imaging for radiotherapy treatment planning.

The central hypothesis of this work is that that 90% of automated treatment plans for bony metastases of the spine are clinically acceptable and can be generated in less than 10 minutes. Additionally, that potential mistreatment can be flagged with 100% sensitivity and at least 75% specificity.

Keywords

segmentation, treatment planning, deep learning, palliative radiotherapy, spinal metastases

Download

Share

COinS