A GPU-based multi-criteria optimization algorithm for HDR brachytherapy.

08:00 EDT 10th April 2019 | BioPortfolio

Summary of "A GPU-based multi-criteria optimization algorithm for HDR brachytherapy."

Currently in HDR brachytherapy planning, a manual fine-tuning of an objective function is necessary to obtain case-specific valid plans. This study intends to facilitate this process by proposing two patient-specific inverse planning algorithms for HDR prostate brachytherapy: knowledge-based multi-criteria optimization (kMCO) and brute-force multi-criteria optimization (bMCO). Two GPU-based optimization engines including simulated annealing (gSA) and a quasi-Newton optimizer (gL-BFGS) were implemented to compute multiple plans in parallel. After evaluating the equivalence and the computation performance of these two optimization engines, gL-BFGS was selected for kMCO and bMCO algorithms. 578 previously treated prostate HDR cases were divided into training set, validation set and test set. In the training set, a set of polynomial regression models were extracted for kMCO algorithm to use prior knowledge and a small number of alternative plans were computed alongside the predicted solution space. On the other hand, a large number of alternative plans were computed for bMCO algorithm to represent the complete Pareto surface. In the test set, kMCO and bMCO plans were compared with the physician-approved clinical plans. Our results indicated that the optimization process is equivalent between gL-BFGS and gSA. The number of clinically valid plans was 428 (92.6\%) for clinical plans and was 460 (99.6\%) for kMCO plans and was 461 (99.8\%) for bMCO plans. The number of valid plans with target $V_{100}$ coverage greater than 95\% was 288 (62.3\%) for clinical plans, 369 (79.9% for kMCO plans, and 404 (87.4\%) for bMCO plans. The mean plan generation time was 8.8s for kMCO, and 9.3s for bMCO. In conclusion, two ultra-fast and robust multi-criteria optimization algorithms were implemented for HDR prostate brachytherapy. A large-scale comparison against physician approved clinical plans showed that treatment plan quality could be improved and plan generation time could be significantly reduced with the proposed GPU-based MCO algorithms.


Journal Details

This article was published in the following journal.

Name: Physics in medicine and biology
ISSN: 1361-6560


DeepDyve research library

PubMed Articles [20139 Associated PubMed Articles listed on BioPortfolio]

A multi-criteria optimization approach for HDR prostate brachytherapy: I. Pareto surface approximation.

High dose rate (HDR) brachytherapy planning usually involves an iterative process of refining planning objectives until a clinically acceptable plan is produced. The purpose of this two-part study is ...

A multi-criteria optimization approach for HDR prostate brachytherapy: II. Benchmark against clinical plans.

The current iterative approach to inverse planning of high dose rate (HDR) treatment planning can be time consuming. The purpose of this two-part study is to streamline the planning process while main...

Comparison of the IPSA and HIPO algorithms for interstitial tongue high-dose-rate brachytherapy.

This study aimed to compare the inverse planning simulated annealing (IPSA) stochastic algorithm with the hybrid inverse planning and optimization (HIPO) algorithm for interstitial tongue high-dose-ra...

Radiobiological optimization comparison between pulse-dose-rate and high-dose-rate brachytherapy in patients with locally advanced cervical cancer.

Only scarce data are available on the possibility to include radiobiological optimization as part of the dosimetric process in cervical cancer treated with brachytherapy (BT). We compared dosimetric o...

Multi-agent hybrid particle swarm optimization (MAHPSO) for wastewater treatment network planning.

The planning of municipal wastewater treatment networks has been recognized as a valuable means for achieving the optimal use of resources and improving the cost-efficient operation of plants. In this...

Clinical Trials [9072 Associated Clinical Trials listed on BioPortfolio]

Continued Access Clinical Trial of the SonRtip Lead and Automatic AV-VV Optimization Algorithm in the PARADYM RF SonR CRT-D (CAS RESPOND CRT)

The objective of the Continued Access study is to gather confirmatory evidence on the safety of the SonRtip lead and performance of the automatic atrioventricular (AV) delay and interventr...

The Efficacy of MDI Treatment With an Optimization Algorithm Adjusting Basal-Bolus Parameters in Children and Adolescents With Type 1 Diabetes at a Diabetes Camp

Our lab at McGill University has developed an optimization algorithm for T1D MDI patients that estimates optimal basal-bolus parameters (basal injections and insulin-to-carbohydrate ratios...

Acute and Cronic Evaluation of AV/PV and VV Delay IEGM Based Optimisation Algorithm-QuickSept Study

AtrioVentricular (AV) and InterVentricular (VV) delay optimization can improve ventricular function in Cardiac Resynchronization Therapy (CRT) and is usually performed by means of echocard...

Prospective Treatment Algorithm Guiding Repair of Severe Ischemic Mitral Regurgitation

Ischemic mitral regurgitation is a disease where the mitral valve is regurgitant, or leaking, as a result of changes in the muscle of the heart caused by coronary artery disease Ischemic m...

Validation of a Quantra Supported Hemotherapy Algorithm in Cardiac Surgery

The aim of this study is to develop a coagulation algorithm based on Quantra POCT for the treatment of coagulopathic cardiac surgery patients.

Medical and Biotech [MESH] Definitions

An internationally recognized set of published rules used for evaluation of cancer treatment that define when tumors found in cancer patients improve, worsen, or remain stable during treatment. These criteria are based specifically on the response of the tumor(s) to treatment, and not on the overall health status of the patient resulting from treatment.

A multi- and interdisciplinary field concerned with improving health and achieving equity in health for all people. It transcends national boundaries, promotes cooperation and collaboration within and beyond health science fields, and combines population-based disease prevention with individually-based patient care.

Criteria and standards used for the determination of the appropriateness of the inclusion of patients with specific conditions in proposed treatment plans and the criteria used for the inclusion of subjects in various clinical trials and other research protocols.

A family of multisubunit cytoskeletal motor proteins that use the energy of ATP hydrolysis to power a variety of cellular functions. Dyneins fall into two major classes based upon structural and functional criteria.

Categorical classification of MENTAL DISORDERS based on criteria sets with defining features. It is produced by the American Psychiatric Association. (DSM-IV, page xxii)

Quick Search


DeepDyve research library

Relevant Topics

Prostate Cancer
Prostate cancer (cancer de prostata) Prostate cancer (cancer de prostata) is a form of cancer that develops in the prostate, a gland in the male reproductive system. Most prostate cancers are slow growing; however, there are cases of aggressive prostat...

Benign Prostatic Hyperplasia (BPH)
An enlarged prostate (benign prostatic enlargement (BPE) or benign prostatic hyperplasia (BPH)) is common in men after the age of about 50. Having an enlarged prostate does not mean you have cancer. In some cases, an enlarged prostate can cause the ...

Searches Linking to this Article