東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Machine Learning Techniques for Synt...

Tang, Derek,

Linked to FindBook

Google Book

Amazon

博客來

Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows // Derek Tang.
Author:	Tang, Derek,
Description:	1 electronic resource (68 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
Contained By:	Dissertations Abstracts International86-12B.
Subject:	Medical imaging. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31933881
ISBN:	9798280723283

Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows /
Tang, Derek,

Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows /Derek Tang. - 1 electronic resource (68 pages)

Source: Dissertations Abstracts International, Volume: 86-12, Section: B.

Infrastructure expenses and capital costs of systems are the most significant hurdles to expanding global access to proton therapy for cancer treatment. Systemic democratization requires the development of new, cost-effective technologies. One possible approach is the evolution of compact proton systems with fixed or limited-angle beamlines, which rely on image guidance and online adaptive radiotherapy to minimize irradiation of healthy tissue. Cone-beam CT (CBCT) images acquired during treatment setup are prone to scatter and beam-hardening artifacts that result in inaccurate Hounsfield unit (HU) values compared to standard CT, compromising the ability to perform precise dose calculations directly on them. To address this challenge, the use of machine learning (ML) algorithms to create HU-corrected synthetic CTs (sCT) from CBCT images is investigated to optimize adaptive workflows for ensuring safe and effective use in compact proton systems.ML models have shown great promise in quickly generating sCT images but are prone to hallucinations and can distort anatomical features, leading to errors in proton planning. This work investigates four approaches to improve the training of ML models for sCT generation. The first uses modified loss functions to focus the training of generators along the path of a proton beam, in addition to the regions of interest that are contoured by physicians. The second involves the development of a cycle-consistent multi-task automated segmentation and sCT generation model for adaptive workflow acceleration and geometric constraint enforcement to preserve the structure during image translation. Next, a framework using a proton dose-based loss is proposed to directly optimize the training of sCT generators to improve overall treatment planning outcomes. Finally, a method is developed using encoders and StyleGAN to investigate the use of latent vector manipulation, providing users with more input in AI medical image generation.Model training, validation, and testing was performed using CBCT and CT images with physician contours from 186 patients treated for prostate cancer on an Elekta Agility linear accelerator. Image quality metrics such as the mean absolute error, root-mean-squared error, and structural similarity index metric were used along with DICE scores to determine segmentation performance. Transfer learning on inter- and intra-institutional datasets was also used to assess generalizability across various imaging systems. sCT images were evaluated dosimetrically for proton radiotherapy using RayStation.Loss-based optimizations proposed in these studies indicate significant improvements in image quality of sCT as compared to established ML models like CycleGAN, though these lead to marginal improvements in treatment planning outcomes. Furthermore, the proposed multi-task network optimizes adaptive radiotherapy workflows by successfully implementing simultaneous segmentation and unsupervised image translation, reducing the amount of time a patient is on the treatment table to minimize uncertainties in adaptive treatments. Additionally, while the results of preliminary StyleGAN training suggest underperformance relative to CycleGAN, it is paramount to highlight the unprecedented model control latent space manipulation provides users. Going forward, this work can inform further development of reliable and efficient models through more targeted approaches to training for sCT generation and the broader use of ML in radiation oncology for improved patient care.

English

ISBN: 9798280723283Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Synthetic CTs

Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows /
LDR:05001nmm a22004453i 4500 001 2432663
005 20250731101907.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798280723283
035 $a (MiAaPQD)AAI31933881
035 $a AAI31933881
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tang, Derek, $e author. $3 3821971
245 1 0 $a Machine Learning Techniques for Synthetic CT Generation in Online Adaptive Proton Therapy Workflows / $c Derek Tang.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (68 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
500 $a Advisors: Yan, Susu Committee members: Sajo, Erno; Desgranges, Caroline.
502 $b Ph.D. $c University of Massachusetts Lowell $d 2025.
520 $a Infrastructure expenses and capital costs of systems are the most significant hurdles to expanding global access to proton therapy for cancer treatment. Systemic democratization requires the development of new, cost-effective technologies. One possible approach is the evolution of compact proton systems with fixed or limited-angle beamlines, which rely on image guidance and online adaptive radiotherapy to minimize irradiation of healthy tissue. Cone-beam CT (CBCT) images acquired during treatment setup are prone to scatter and beam-hardening artifacts that result in inaccurate Hounsfield unit (HU) values compared to standard CT, compromising the ability to perform precise dose calculations directly on them. To address this challenge, the use of machine learning (ML) algorithms to create HU-corrected synthetic CTs (sCT) from CBCT images is investigated to optimize adaptive workflows for ensuring safe and effective use in compact proton systems.ML models have shown great promise in quickly generating sCT images but are prone to hallucinations and can distort anatomical features, leading to errors in proton planning. This work investigates four approaches to improve the training of ML models for sCT generation. The first uses modified loss functions to focus the training of generators along the path of a proton beam, in addition to the regions of interest that are contoured by physicians. The second involves the development of a cycle-consistent multi-task automated segmentation and sCT generation model for adaptive workflow acceleration and geometric constraint enforcement to preserve the structure during image translation. Next, a framework using a proton dose-based loss is proposed to directly optimize the training of sCT generators to improve overall treatment planning outcomes. Finally, a method is developed using encoders and StyleGAN to investigate the use of latent vector manipulation, providing users with more input in AI medical image generation.Model training, validation, and testing was performed using CBCT and CT images with physician contours from 186 patients treated for prostate cancer on an Elekta Agility linear accelerator. Image quality metrics such as the mean absolute error, root-mean-squared error, and structural similarity index metric were used along with DICE scores to determine segmentation performance. Transfer learning on inter- and intra-institutional datasets was also used to assess generalizability across various imaging systems. sCT images were evaluated dosimetrically for proton radiotherapy using RayStation.Loss-based optimizations proposed in these studies indicate significant improvements in image quality of sCT as compared to established ML models like CycleGAN, though these lead to marginal improvements in treatment planning outcomes. Furthermore, the proposed multi-task network optimizes adaptive radiotherapy workflows by successfully implementing simultaneous segmentation and unsupervised image translation, reducing the amount of time a patient is on the treatment table to minimize uncertainties in adaptive treatments. Additionally, while the results of preliminary StyleGAN training suggest underperformance relative to CycleGAN, it is paramount to highlight the unprecedented model control latent space manipulation provides users. Going forward, this work can inform further development of reliable and efficient models through more targeted approaches to training for sCT generation and the broader use of ML in radiation oncology for improved patient care.
546 $a English
590 $a School code: 0111
650 4 $a Medical imaging. $3 3172799
650 4 $a Biomedical engineering. $3 535387
650 4 $a Oncology. $3 751006
650 4 $a Biophysics. $3 518360
653 $a Synthetic CTs
653 $a Radiotherapy
653 $a StyleGAN
653 $a Image quality
653 $a Cone-beam CT
690 $a 0574
690 $a 0786
690 $a 0992
690 $a 0541
710 2 $a University of Massachusetts Lowell. $b Physics. $e degree granting institution. $3 3820701
720 1 $a Yan, Susu $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-12B.
790 $a 0111
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31933881