Automated Radiation Target Contouring and Treatment Planning Via RATA: A Multi-Center RCT
Automated Target Volume Contouring and Intelligent Treatment Planning Based on a Multi-Agent Collaborative Radiotherapy Large Model (RATA): A Multi-Center Validation and Prospective Randomized Controlled Trial
Radiotherapy, a cornerstone of comprehensive cancer treatment, relies heavily on clinician expertise for target volume contouring and treatment planning. Consequently, clinical practice is often constrained by procedural bottlenecks, inter-observer variability, and prolonged iterative feedback cycles. Although current artificial intelligence (AI) models have demonstrated progress in automated contouring, key limitations persist, including insufficient integration of multimodal clinical text, a lack of closed-loop dosimetric feedback, and limited generalizability across complex cancer types.
This study aims to develop and validate RATA (Radiotherapy Treatment Multi-Agent Assistant), a novel large model system powered by a collaborative multi-agent architecture. Driven by Large Language Model (LLM) decision engines, RATA processes pathological imaging, electronic health records (EHR), and multimodal medical data to construct a end-to-end, fully automated closed-loop pipeline encompassing "target contouring, plan design, dosimetric evaluation, and reflective refinement." Innovatively breaking through traditional unidirectional radiotherapy workflows, the system establishes a dosimetric feedback-driven adaptive iteration mechanism, leveraging dose distribution outcomes to guide multi-agent dynamic fine-tuning of target volumes, thereby mimicking the collaborative clinical logic between senior radiation oncologists and medical physicists.
For validation, this study adopts a multi-center, three-stage clinical validation framework-comprising multi-center retrospective validation, human-AI collaborative efficacy assessment, and a prospective randomized controlled trial (RCT)-to comprehensively evaluate the system's performance in improving contouring precision, mitigating experience-dependent disparities across clinician seniority, and reducing total workflow processing time. Implementation of the RATA platform holds potential to eliminate redundant operational steps, enabling a minute-level "scan-to-treat" response. Furthermore, its natural language interaction interface optimizes human-AI collaboration and substantially reduces clinical workload. Overall, this study not only establishes a standardized, intelligent assistance paradigm for precision radiation oncology but also provides essential evidence-based support and technological foundations for the clinical translation of multimodal AI in complex cancer management.
Studieöversikt
Status
Status
Betingelser
Betingelser
Intervention / Behandling
Intervention / Behandling
Studietyp
Studietyp
Inskrivning (Beräknad)
Inskrivning
Fas
Fas
- Inte tillämpbar
Kontakter och platser
Studiekontakt
Studiekontakt
- Namn: Xiaohui Zhao, MD
- Telefonnummer: +86-13828491190
- E-post: zhaoxh27@mail.sysu.edu.cn
Studieorter
-
-
Guangdong
-
Guangzhou, Guangdong, Kina, 510120
- Sun Yat-sen Memorial Hospital, Sun Yat-sen University
-
Kontakt:
- Xiaohui Zhao, MD
- Telefonnummer: +86-13828491190
- E-post: zhaoxh27@mail.sysu.edu.cn
-
Huvudutredare:
- Xiaohui Zhao, MD
-
-
Deltagandekriterier
Urvalskriterier
Urvalskriterier
Åldrar som är berättigade till studier
- Barn
- Vuxen
- Äldre vuxen
Tar emot friska volontärer
Kön som är behöriga för studier
Beskrivning
Inclusion Criteria:
- Pathologically confirmed malignant neoplasm requiring definitive or adjuvant radiotherapy.
- Availability of verified pathology report.
- Availability of baseline imaging examinations and diagnostic reports.
- Availability of standardized and complete clinical electronic health records.
Exclusion Criteria:
- Incomplete clinical, imaging, or follow-up data.
- Presence of multiple primary malignancies.
- Patients scheduled for salvage or palliative radiotherapy.
Studieplan
Hur är studien utformad?
Designdetaljer
- Primärt syfte: Hälsovårdsforskning
- Tilldelning: Randomiserad
- Interventionsmodell: Parallellt uppdrag
- Maskning: Enda
Antal vapen
Vapen och interventioner
Deltagargrupp / ArmDeltagargrupp / Arm |
Intervention / BehandlingIntervention / Behandling |
|---|---|
|
Experimentell: RATA-Assisted Workflow Arm
Patients in this arm receive radiotherapy using the RATA-assisted "scan-to-treat" model. Patients remain in position on the couch while the Multi-Agent Collaborative Radiotherapy Large Model (RATA) executes target volume contouring, treatment planning, dosimetric evaluation, and reflective refinement in a closed-loop automated workflow, enabling rapid delivery of the first fraction. |
An AI-driven multi-agent platform utilizing large language model decision engines to automatically perform target volume contouring, dosimetric plan generation, evaluation, and adaptive refinement for cancer radiotherapy. |
|
Aktiv komparator: Standard Offline Workflow Arm
Patients in this arm follow the traditional offline clinical workflow. After initial simulation CT scanning, patients leave the treatment room while radiation oncologists and medical physicists manually perform target contouring and treatment planning according to standard practice. Patients return to the clinic at a later scheduled time for their first radiation fraction. |
Conventional offline radiation therapy planning workflow, where target volume contouring and treatment planning are manually performed by radiation oncologists and medical physicists according to routine institutional protocols. |
Vad mäter studien?
Primära resultatmått
Primära resultatmått
Resultatmått |
Åtgärdsbeskrivning |
Tidsram |
|---|---|---|
|
Total Closed-Loop Workflow Duration
Tidsram: At the time of simulation and treatment planning for each participant (up to 1 day)
|
Total time (in minutes) required for the complete end-to-end radiotherapy planning closed-loop workflow, measured from initial CT simulation scan completion to final clinical treatment plan approval and readiness for first fraction delivery. |
At the time of simulation and treatment planning for each participant (up to 1 day)
|
Sekundära resultatmått
Sekundära resultatmått
Resultatmått |
Åtgärdsbeskrivning |
Tidsram |
|---|---|---|
|
Clinical Acceptance Rate of Treatment Plans
Tidsram: At plan evaluation prior to treatment delivery (up to 1 day)
|
Percentage of treatment plans rated as clinically acceptable (score ≥3 on a 5-point Likert scale) by senior radiation oncologists without substantial manual re-planning. |
At plan evaluation prior to treatment delivery (up to 1 day)
|
|
Planning Time and Workload Reduction Rate
Tidsram: At plan evaluation prior to treatment delivery (up to 1 day)
|
Total clinician active manual intervention time (contour editing and plan optimization duration in minutes) and percentage of labor time saved compared to the standard manual workflow. |
At plan evaluation prior to treatment delivery (up to 1 day)
|
|
Contouring Accuracy Metrics and Dosimetric Parameters
Tidsram: At plan evaluation prior to treatment delivery (up to 1 day)
|
Geometric similarity metrics including Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and Average Surface Distance (ASD); dosimetric indicators including Target Coverage (V95%), Conformity Index (CI), Homogeneity Index (HI), and Organs-at-Risk (OAR) dose constraints. |
At plan evaluation prior to treatment delivery (up to 1 day)
|
|
First Setup Verification Pass Rate
Tidsram: At the first fraction of radiotherapy delivery (Day 1 of treatment)
|
Proportion of participants passing the initial positional setup and position verification check (e.g., CBCT/IGRT alignment) prior to the first fraction delivery on the treatment couch. |
At the first fraction of radiotherapy delivery (Day 1 of treatment)
|
Samarbetspartners och utredare
Sponsor
Sponsor
Samarbetspartners
Samarbetspartners
Utredare
Utredare
- Huvudutredare: Xiaohui Zhao, MD, Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
Studieavstämningsdatum
Studera stora datum
Studiestart (Beräknad)
Studiestart
Primärt slutförande (Beräknad)
Primärt slutförande
Avslutad studie (Beräknad)
Avslutad studie
Studieregistreringsdatum
Först inskickad
Först inskickad
Först inskickad som uppfyllde QC-kriterierna
Först inskickad som uppfyllde QC-kriterierna
Första postat (Faktisk)
Första postat
Uppdateringar av studier
Senaste uppdatering publicerad (Faktisk)
Senaste uppdatering publicerad
Senaste inskickade uppdateringen som uppfyllde QC-kriterierna
Senaste inskickade uppdateringen som uppfyllde QC-kriterierna
Senast verifierad
Senast verifierad
Mer information
Termer relaterade till denna studie
Ytterligare relevanta MeSH-villkor
Andra studie-ID-nummer
Andra studie-ID-nummer
- SYSKY-2026-406-03
Plan för individuella deltagardata (IPD)
Planerar du att dela individuella deltagardata (IPD)?
Läkemedels- och apparatinformation, studiedokument
Studerar en amerikansk FDA-reglerad läkemedelsprodukt
Studerar en amerikansk FDA-reglerad produktprodukt
Denna information hämtades direkt från webbplatsen clinicaltrials.gov utan några ändringar. Om du har några önskemål om att ändra, ta bort eller uppdatera dina studieuppgifter, vänligen kontakta register@clinicaltrials.gov. Så snart en ändring har implementerats på clinicaltrials.gov, kommer denna att uppdateras automatiskt även på vår webbplats .