Computer Science ETDs

Publication Date

Spring 5-16-2026

Abstract

Commissioning and routine quality assurance (QA) in radiotherapy require extensive measurements using bulky water tank systems, making the process time-consuming and costly. This research proposes an efficient framework for radiotherapy commissioning and QA by generating complete LINAC physics data from sparse measurements and developing a portable solid-water detector with embedded diodes for high-resolution dosimetry.

At the core of the framework is a Wavelet-based Implicit Neural Network (WINN) that reconstructs full measurement datasets from limited inputs while maintaining clinical accuracy. The model achieves gamma passing rates above 95% (1%/1 mm) and mean absolute errors below 0.5%, while reducing parameters by 99.46% compared to SIREN and maintaining a compact size under 1 MB. Combined with the proposed detector, the framework enables fast, accurate, and cost-effective dosimetry for next-generation radiotherapy systems.

Language

English

Keywords

deep learning, coordinate network, deep learning, wavelet function, LINAC, commissioning, radotherapy

Document Type

Dissertation

Degree Name

Computer Science

Level of Degree

Doctoral

Department Name

Department of Computer Science

First Committee Member (Chair)

Shuang Luan

Second Committee Member

Bruna Jacobson

Third Committee Member

Yi He

Fourth Committee Member

Richard Shaw

Download

Share

COinS