Multimodal LLM for Breast Cancer Radiotherapy Target Auto-Contouring and Planning
Multimodal Data Fusion-Based Artificial Intelligence Large Language Model for Automated Target Volume Contouring and Intelligent Treatment Planning in Breast Cancer Radiotherapy: A Multicenter Ambidirectional Cohort Study
Breast cancer remains the most prevalent malignancy among women worldwide, with a continuously increasing incidence. As a crucial component of comprehensive cancer treatment, radiotherapy plays a key role in reducing local recurrence rates and improving overall survival outcomes. However, traditional radiotherapy target volume contouring and treatment planning design rely heavily on clinician expertise, presenting challenges such as prolonged processing time, significant inter-observer variability, and high subjectivity in dose optimization. Although artificial intelligence has made substantial progress in automated contouring and planning, conventional single-modal models still face major limitations. These models struggle to effectively integrate clinical text, tumor biological characteristics, and dose distribution factors, resulting in restricted generalizability. Therefore, developing an intelligent radiotherapy assistance system capable of multimodal data fusion is of high clinical significance to enhance precision and efficiency in breast cancer radiotherapy.
This study aims to develop an innovative breast cancer radiotherapy assistance system based on a multimodal large language model. By integrating multimodal imaging data (including CT, MRI, and ultrasound), pathology reports, and structured electronic health record text, the system realizes end-to-end intelligence from target volume contouring to treatment plan generation. Employing a multicenter, ambidirectional cohort design, the study collects comprehensive clinical data from breast cancer patients who have undergone breast-conserving surgery or mastectomy. Technologically, the system innovatively combines the natural language processing capabilities of large language models with the image analysis strengths of deep learning, utilizing attention mechanisms to achieve deep fusion and interactive comprehension of heterogeneous medical data. Notably, the system breaks through traditional radiotherapy planning workflows by jointly optimizing target contouring and dose planning as a unified pipeline, applying reinforcement learning algorithms to dynamically balance target volume coverage with organ-at-risk protection. The outcomes of this study will provide an important paradigm for the clinical application of AI in radiation oncology and advance the field of precision radiotherapy.
Study Overview
Status
Status
Conditions
Conditions
Intervention / Treatment
Intervention / Treatment
Study Type
Study Type
Enrollment (Estimated)
Enrollment
Contacts and Locations
Study Contact
Study Contact
- Name: Xiaohui Zhao, MD
- Phone Number: +86-13828491190
- Email: zhaoxh27@mail.sysu.edu.cn
Study Locations
-
-
Guangdong
-
Guangzhou, Guangdong, China, 510120
- Sun Yat-sen Memorial Hospital, Sun Yat-sen University
-
Contact:
- Xiaohui Zhao, MD
- Phone Number: +86-13828491190
- Email: zhaoxh27@mail.sysu.edu.cn
-
Principal Investigator:
- Xiaohui Zhao, MD
-
-
Participation Criteria
Eligibility Criteria
Eligibility Criteria
Ages Eligible for Study
- Child
- Adult
- Older Adult
Accepts Healthy Volunteers
Genders Eligible for Study
Sampling Method
Study Population
The study population includes patients with breast cancer from multiple medical centers. The retrospective cohort comprises patients treated at Sun Yat-sen Memorial Hospital (n=35,000) and external collaborating centers (Shenshan Medical Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Zhoukou Central Hospital, and Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, n=15,000) between January 1, 2002, and October 31, 2025. The prospective test cohort comprises patients prospectively enrolled at Sun Yat-sen Memorial Hospital starting from January 1, 2026 (n=1,000).
Description
Inclusion Criteria:
- Patients with pathologically confirmed breast malignant tumors who require postoperative adjuvant radiotherapy following radical surgery.
- Availability of complete pathology reports.
- Availability of complete imaging examinations and reports (such as CT, MRI, ultrasound, X-ray).
- Availability of standardized clinical medical records.
Exclusion Criteria:
- Patients with missing data.
- Patients with primary multiple cancers.
- Patients receiving salvage or palliative radiotherapy.
- Patients receiving accelerated partial breast irradiation (APBI).
Study Plan
How is the study designed?
Design Details
- Observational Models: COHORT
- Time Perspectives: OTHER
Number of groups / cohorts
Cohorts and Interventions
Group / CohortGroup / Cohort |
Intervention / TreatmentIntervention / Treatment |
|---|---|
|
Retrospective Training and Internal Validation Cohort
Retrospective collection of clinical data, multimodal images (MRI, CT, ultrasound, X-ray), pathology reports, and radiotherapy plans from patients with breast cancer treated at Sun Yat-sen Memorial Hospital between January 1, 2002, and October 31, 2025. This cohort (n=35,000) is used for model training and internal validation of the multimodal LLM-assisted automated contouring and radiotherapy planning system. |
The study evaluates an innovative multimodal large language model (LLM) system designed for automated target volume delineation and intelligent treatment planning in post-operative breast cancer radiotherapy. The system integrates clinical text, multimodal imaging (CT, MRI, ultrasound, X-ray), and pathology data to joint-optimize contouring and dose planning without direct patient intervention. |
|
Retrospective External Validation Cohort
Retrospective collection of data from external collaborative centers (Sun Yat-sen Memorial Hospital Shenzhen Hospital, Zhoukou Central Hospital, and Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology) between January 1, 2002, and October 31, 2025 (total n=15,000). This cohort is used to evaluate the external generalizability and robustness of the multimodal AI model. |
The study evaluates an innovative multimodal large language model (LLM) system designed for automated target volume delineation and intelligent treatment planning in post-operative breast cancer radiotherapy. The system integrates clinical text, multimodal imaging (CT, MRI, ultrasound, X-ray), and pathology data to joint-optimize contouring and dose planning without direct patient intervention. |
|
Prospective Test Cohort
Prospective collection of data from patients with breast cancer treated at Sun Yat-sen Memorial Hospital starting from January 1, 2026 (n=1,000). This cohort undergoes double-blind evaluation to prospectively test the performance of the multimodal LLM-driven target volume auto-segmentation and intelligent radiotherapy planning system in clinical practice. |
The study evaluates an innovative multimodal large language model (LLM) system designed for automated target volume delineation and intelligent treatment planning in post-operative breast cancer radiotherapy. The system integrates clinical text, multimodal imaging (CT, MRI, ultrasound, X-ray), and pathology data to joint-optimize contouring and dose planning without direct patient intervention. |
What is the study measuring?
Primary Outcome Measures
Primary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
Dice Similarity Coefficient (DSC) of Target Volume Auto-Segmentation
Time Frame: Baseline
|
Evaluation of the Dice Similarity Coefficient (DSC) between AI-generated automatic breast cancer target volume contours and expert manual contours. |
Baseline
|
Secondary Outcome Measures
Secondary Outcome Measures
Outcome Measure |
Measure Description |
Time Frame |
|---|---|---|
|
95% Hausdorff Distance (95HD) of Target Volume Auto-Segmentation
Time Frame: Baseline
|
Evaluation of the 95% Hausdorff Distance (95HD) between AI-generated automatic breast cancer target volume contours and expert manual contours. |
Baseline
|
|
Intersection over Union (IoU) of Target Volume Auto-Segmentation
Time Frame: Baseline
|
Evaluation of the Intersection over Union (IoU) between AI-generated automatic breast cancer target volume contours and expert manual contours. |
Baseline
|
|
Clinical Evaluation Score of Target Volume Auto-Segmentation
Time Frame: Baseline
|
Blinded evaluation by radiation oncology experts using the Investigator-Developed Cancer Target Volume Contouring Performance Evaluation Scale, a structured 5-point clinical evaluation scale. The scale assesses five dimensions: laterality accuracy (0 to 1 point), radiotherapy type suitability (0 to 1 point), target volume definition (0 to 1.5 points), coverage (0 to 1 point), and structural integrity (0 to 0.5 points). The total score ranges from a minimum of 0 to a maximum of 5, where higher scores indicate better target volume contouring quality and clinical acceptability. |
Baseline
|
Collaborators and Investigators
Sponsor
Sponsor
Collaborators
Collaborators
Investigators
Investigators
- Principal Investigator: Xiaohui Zhao, MD, Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
Study record dates
Study Major Dates
Study Start (Estimated)
Study Start
Primary Completion (Estimated)
Primary Completion
Study Completion (Estimated)
Study Completion
Study Registration Dates
First Submitted
First Submitted
First Submitted That Met QC Criteria
First Submitted That Met QC Criteria
First Posted (Actual)
First Posted
Study Record Updates
Last Update Posted (Actual)
Last Update Posted
Last Update Submitted That Met QC Criteria
Last Update Submitted That Met QC Criteria
Last Verified
Last Verified
More Information
Terms related to this study
Additional Relevant MeSH Terms
Other Study ID Numbers
Other Study ID Numbers
- SYSKY-2026-014-01
Plan for Individual participant data (IPD)
Plan to Share Individual Participant Data (IPD)?
Drug and device information, study documents
Studies a U.S. FDA-regulated drug product
Studies a U.S. FDA-regulated device product
This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.