Tian Liu, PhD

Micro-ultrasound (microUS) provides high-resolution visualization of the prostate for interventional procedures; however, the scarcity of annotated datasets limits the development of robust automated segmentation methods. This study leverages a foundation-mod...

A persistent challenge in medical physics education is the lack of centralized, interactive, and easily accessible training tools that integrate into daily clinical workflows. Many existing resources are static, fragmented, and difficult to use consistently a...

To systematically assess whether commonly proposed architectural enhancements provide measurable benefits for deep learning-based radiotherapy dose prediction, using controlled comparisons of 3D U-Net variants to support evidence-based model selection and est...

Objective assessment of radiotherapy plans is challenging because expert assessment relies on complex, multidimensional tradeoffs that are not fully captured by predefined dose-volume constraints. This study aims to quantitatively interpret expert treatment p...

To implement a full abdominal motion model that combines respiration with gastrointestinal (GI) motility and quantify its interplay impact in pencil-beam scanning (PBS) proton therapy.

Ultra-high-dose-rate (UHDR) proton irradiation may spare normal tissue (FLASH effect), but PBS proton dose rate is limited by machine constraints (minimum MU/spot and dwell time). Intra-field interruptions can leave sub-threshold MU for remaining delivery, de...

Accurate prediction of radiation-induced toxicity is crucial for optimizing radiotherapy outcomes, yet most existing models rely on supervised learning with clinician-graded toxicity scores that are susceptible to patient self-reporting errors and intra-obser...

Accurate prediction of radiation-induced toxicity is crucial for optimizing radiotherapy outcomes. However, most existing predictive models rely on uni-modal data and deterministic models that are vulnerable to label noise and uncertainty. This study aims to...

Accurate real-time tumor tracking is critical for MRI-guided radiotherapy, where geometric uncertainty can significantly increase dose to surrounding critical organs. Continuous cine-MRI enables motion-adaptive treatment. However, accurate tracking under larg...

Consistently automating clinically acceptable plans without human intervention remains a challenge in radiotherapy. While knowledge-based planning (KBP) predicts optimal achievable dose-volume metrics, it often fails to achieve these metrics without manual ad...

Diagnostic and Interventional Radiology Physics

Knowledge-based planning (KBP) improves plan quality and efficiency. However, training institution-specific models requires substantial clinical data and expertise, and publicly available models may not align with local clinical objectives. This study evaluat...

To evaluate whether a Large Language Model (LLM)–driven autonomous planning system can self-learn planning strategies from human planner logs and apply this knowledge to generate clinically compatible radiotherapy plans without manual refinements.

Existing deep learning-based dose prediction methods primarily learn empirical mappings between anatomy and dose, without modeling beam delivery physics. This gap may limit their robustness and accuracy, especially in heterogeneous regions where dose depositi...

In-vivo dosimetry requires compact dosimeters suitable for patient placement, with multiple detectors often deployed simultaneously for spatial sampling. The 2023 nanoDot OSLD recall left many clinics without accessible, low-cost alternatives. Our purpose is...

To quantify the impact of gastrointestinal (GI) motility on pencil-beam scanning (PBS) proton therapy for abdominal cancers, and assess how fractionation and motion amplitude mitigate motility-induced interplay effects.