東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy./
作者:	Barajas, Carlos Alexander.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	113 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
Contained By:	Dissertations Abstracts International83-12B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29161153
ISBN:	9798802714744

Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy.
Barajas, Carlos Alexander.

Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 113 p.

Source: Dissertations Abstracts International, Volume: 83-12, Section: B.

Thesis (Ph.D.)--University of Maryland, Baltimore County, 2022.

This item must not be sold to any third party vendors.

Proton beam radiotherapy is a method of cancer treatment that uses proton beams to irradiate cancerous tissue, while simultaneously sparing doses to healthy tissue. In order to optimize radiation doses to the tumor and ensure that healthy tissue is spared, many researchers have suggested verifying the treatment delivery through the use of real-time imaging. One promising method of real-time imaging is the use of a Compton camera, which can image prompt gamma rays or simply "prompt gammas", that are emitted along the beam's path through the patient. However, because of limitations in the Compton camera's ability to detect prompt gammas, the reconstructed images are often noisy and unusable for verifying proton treatment delivery. Machine learning is able to automatically learn patterns that exist in numerical data, making it a promising method to analyze Compton camera data for the purpose of reducing noise in the reconstructed images.In this thesis we demonstrate a supervised deep residual fully connected neural net-work's ability to perform on three different, and increasingly complex, data scenarios: true triples, true triples/double-to-triples (DtoT), true triples/DtoT/false triples. The jump from true triples/DtoT to true triples/DtoT/false triples is surprisingly difficult despite only gaining a single class. This single additional class requires significantly more configuration and training time than one might expect because false triples are so similar to doubles-to-triples which themselves are similar to triples. We test all of our networks on 20 different Monte-Carlo with Detector Effect (MCDE) simulation datasets which consist of varying dose rates. The neural networks showed acceptable accuracy as the number of classes grew from 6, to 12, to 13. When classifying the 13classes the neural network had an average rough accuracy of 76% across all classes and datasets. This level of classification accuracy translates to a large measurable improvement in the amount of data that is viable for reconstruction. When doing an image reconstruction from Compton camera data on 20kMU/min, 100kMU/min, and 180kMU/min dose rates, only 7.9%, 1.8%, and 0.9%, respectively, of the all data collected can be used. When we use the neural network to sanitize the data we see that the amount of total data usable increases to 78.0%, 73.8%, and 59.6%, respectively. The neural network's ability to make such drastic changes to data quality is a huge boon for improving the viability using the Compton camera for prompt gamma image reconstruction, but improvements to the neural network accuracy should be made for potential clinical usage.

ISBN: 9798802714744Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Compton camera

Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy.
LDR:03888nmm a2200385 4500 001 2352231
005 20221118093850.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798802714744
035 $a (MiAaPQ)AAI29161153
035 $a AAI29161153
040 $a MiAaPQ $c MiAaPQ
100 1 $a Barajas, Carlos Alexander. $3 3691851
245 1 0 $a Neural Networks for the Sanitization of Compton Camera Based Prompt Gamma Imaging Data for Proton Radiotherapy.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 113 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
500 $a Advisor: Gobbert, Matthias K.
502 $a Thesis (Ph.D.)--University of Maryland, Baltimore County, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Proton beam radiotherapy is a method of cancer treatment that uses proton beams to irradiate cancerous tissue, while simultaneously sparing doses to healthy tissue. In order to optimize radiation doses to the tumor and ensure that healthy tissue is spared, many researchers have suggested verifying the treatment delivery through the use of real-time imaging. One promising method of real-time imaging is the use of a Compton camera, which can image prompt gamma rays or simply "prompt gammas", that are emitted along the beam's path through the patient. However, because of limitations in the Compton camera's ability to detect prompt gammas, the reconstructed images are often noisy and unusable for verifying proton treatment delivery. Machine learning is able to automatically learn patterns that exist in numerical data, making it a promising method to analyze Compton camera data for the purpose of reducing noise in the reconstructed images.In this thesis we demonstrate a supervised deep residual fully connected neural net-work's ability to perform on three different, and increasingly complex, data scenarios: true triples, true triples/double-to-triples (DtoT), true triples/DtoT/false triples. The jump from true triples/DtoT to true triples/DtoT/false triples is surprisingly difficult despite only gaining a single class. This single additional class requires significantly more configuration and training time than one might expect because false triples are so similar to doubles-to-triples which themselves are similar to triples. We test all of our networks on 20 different Monte-Carlo with Detector Effect (MCDE) simulation datasets which consist of varying dose rates. The neural networks showed acceptable accuracy as the number of classes grew from 6, to 12, to 13. When classifying the 13classes the neural network had an average rough accuracy of 76% across all classes and datasets. This level of classification accuracy translates to a large measurable improvement in the amount of data that is viable for reconstruction. When doing an image reconstruction from Compton camera data on 20kMU/min, 100kMU/min, and 180kMU/min dose rates, only 7.9%, 1.8%, and 0.9%, respectively, of the all data collected can be used. When we use the neural network to sanitize the data we see that the amount of total data usable increases to 78.0%, 73.8%, and 59.6%, respectively. The neural network's ability to make such drastic changes to data quality is a huge boon for improving the viability using the Compton camera for prompt gamma image reconstruction, but improvements to the neural network accuracy should be made for potential clinical usage.
590 $a School code: 0434.
650 4 $a Computer science. $3 523869
650 4 $a Medical imaging. $3 3172799
650 4 $a Nuclear physics. $3 517741
653 $a Compton camera
653 $a Data
653 $a Deep learning
653 $a Neural networks
653 $a Prompt gamma
653 $a Radiotherapy
690 $a 0984
690 $a 0574
690 $a 0756
710 2 $a University of Maryland, Baltimore County. $b Mathematics, Applied. $3 1026717
773 0 $t Dissertations Abstracts International $g 83-12B.
790 $a 0434
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29161153