Development and clinical deployment of an automated planning tool for prostate only and male whole pelvis plans based on multi‐criteria optimization
Rattachement africain : us. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
BACKGROUND: Multi-criteria optimization (MCO) is an advanced optimization technique that can be applied to any problem with multiple objectives that may be conflicting. MCO has been available in commercial treatment planning systems (TPS) for several years now and has been applied to treatment planning of many anatomical locations in a variety of ways. The MCO optimization method is based on the Pareto plans generation and is very powerful, but there are significant hurdles in terms of clinical implementation due to long computing times, lack of dosimetrists training and plan degradation after the optimized fluence is converted to deliverable. While some authors have studied the use of MCO in automation, no clinical implementation of an MCO-based auto-planning technique has been reported. PURPOSE: This study aims to develop and clinically deploy an automated planning tool based on MCO for prostate and whole-pelvis radiotherapy. MATERIALS AND METHODS: A Python script based on a commercial treatment planning system was developed to automate MCO, including Pareto plan generation, fluence plan selection, dose conversion, and post-processing. The tool underwent retrospective validation on 10 prostate patients with the input of four dosimetrists and a 10-month prospective pilot involving another three senior dosimetrists across different community sites. Dosimetrists evaluated plan quality and provided quantitative and qualitative feedback for iterative improvements of the tool. The study reports on the plan comparisons between the clinical and the MCO generated plans for retrospective patients. The study also reports the prospective use cases and the qualitative and quantitative evaluations from dosimetrists. RESULTS: Retrospective evaluations showed 82.5% of MCO prostate plans were clinically acceptable. The tool generated prostate plans in approximately 10.1 min and whole pelvis plans in 27.2 min. Dosimetric analysis revealed comparable plan quality to clinical plans, with MCO plans achieving lower organ-at-risk doses. In the pilot phase, the MCO tool was used for 41 prospective patients, producing plans that dosimetrists could refine to achieve clinical acceptability within a median of 10 min. CONCLUSIONS: This study demonstrates the successful development and clinical implementation of an MCO-based automated planning tool for generating acceptable VMAT plans for prostate and whole pelvis radiotherapy. The extensive pilot phase showcases an effective strategy for integrating automated planning solutions into routine clinical practice.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Development and clinical deployment of an automated planning tool for prostate only and male whole pelvis plans based on multi‐criteria optimization
- Date Crossref
- 01/05/2026
- Éditeur
- Wiley
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
University of Maryland pays non établi dans la noticeUniversité ou école supérieure
-
University of Maryland Medical Center pays non établi dans la noticeÉtablissement de santé
-
University of Washington pays non établi dans la noticeUniversité ou école supérieure
-
Fred Hutch Cancer Center pays non établi dans la noticeOrganisation à but non lucratif
-
University of Colorado Denver pays non établi dans la noticeUniversité ou école supérieure
-
Maryland Oncology Hematology pays non établi dans la noticeÉtablissement de santé
-
University of Maryland Baltimore Washington Medical Center pays non établi dans la noticeÉtablissement de santé
-
University of Maryland Upper Chesapeake Health pays non établi dans la noticeÉtablissement de santé
-
Department of Radiation Oncology University of Colorado School of Medicine Aurora pays non établi dans la noticeUniversité ou école supérieure
-
Department Radiation Oncology Central Maryland Radiation Oncology Center Columbia Maryland USA pays non établi dans la noticeInstitution
-
Department Radiation Oncology Baltimore Washington Medical Center Radiation Oncology Glen Burnie Maryland USA pays non établi dans la noticeÉtablissement de santé
-
Department Radiation Oncology Kaufman Cancer Center Upper Chesapeake Medical Center Bel Air Maryland USA pays non établi dans la noticeÉtablissement de santé
University of Maryland, University of Maryland Medical Center et University of Washington, avec 9 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.