Sheng Liu

Sheng Liu

Auto-generated profile, based on publicly available information

Sheng Liu

Stanford University, Stanford, USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 July 2025 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
SLSheng Liu
Sheng Liu
OPOscar Pastor-Serrano
Oscar Pastor-Serrano
YCYizheng Chen
Yizheng Chen
MGMatthew Gopaulchan
Matthew Gopaulchan
WLWeixing Liang
Weixing Liang
Lei XingLei Xing
Lei Xing
Objective. Radiotherapy treatment planning is a time-consuming and potentially subjective process that requires iterative adjustment of model parameters to balance multiple conflicting objectives. Recent advancements in frontier artificial intelligence (AI) models offer promising avenues for addressing the challenges in planning and clinical decision-making. This study introduces GPT-RadPlan, an automated treatment planning framework that integrates radiation oncology knowledge with the reasoning capabilities of large multi-modal models, such as GPT-4Vision (GPT-4 V) from OpenAI. Approach. Via in-context learning, we incorporate clinical requirements and three approved clinical plans along with their optimization settings, enabling GPT-4 V to acquire treatment planning domain knowledge. The resulting GPT-RadPlan system is integrated into our in-house inverse treatment planning system through an application programming interface. For a given patient, GPT-RadPlan acts as both plan evaluator and planner, first assessing dose distributions and dose-volume histograms, and then providing ‘textual feedback’ on how to improve the plan to match the physician’s requirements. In this manner, GPT-RadPlan iteratively refines the plan by adjusting planning parameters, such as weights and dose objectives, based on its suggestions. Main results. The efficacy of the automated planning system is showcased across 17 prostate cancer and 13 head & neck cancer VMAT plans with prescribed doses of 70.2 Gy and 72 Gy, respectively, where we compared GPT-RadPlan results to clinical plans produced by human experts. In all cases, GPT-RadPlan either outperformed or matched the clinical plans, demonstrating superior target coverage and reducing organ-at-risk doses by 5 Gy on average (15% for prostate and 10%–15% for head & neck). Significance. Consistently satisfying the the dose-volume objectives in the clinical protocol, GPT-RadPlan represents the first multimodal large language model agent that mimics the behaviors of human planners in radiation oncology clinics, achieving promising results in automating the treatment planning process without the need for additional training.