Yang Lei, PhD

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...

While 30% of lung cancer patients cannot tolerate breath-hold, free-breathing(FB) proton pencil-beam-scanning(PBS) deliveries compromise target coverage from the interplay effects of large motion. This study presents a novel FB-gated spirometer-based respirat...

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.

Commercial treatment planning systems (TPS), such as Varian Eclipse, cannot perform dose calculations on CBCTs acquired with 6DoF couch corrections. This limitation prevents direct dosimetric re-evaluation of verification scans. This study presents an offline...

Proton LATTICE radiotherapy (LRT), a spatially fractionated radiotherapy (SFRT), delivers high dose to intratumoral vertices while maintaining low valley dose. Single-field optimization (SFO) is robust in preserving peak-to-valley patterns but may increase en...

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...

This work aims to develop a physics-aware deep learning framework for radiotherapy dose prediction that improves accuracy and clinical efficiency. The proposed Physics-Aware Multimodal UNet (PhysMM-UNet) integrates CT images, fluence maps, organ masks, and mu...

Ultrasound-guided high-dose-rate (UGHDR) brachytherapy for prostate cancer depends on real-time transrectal ultrasound (TRUS) imaging for catheter guidance. However, the limited ability of TRUS to depict critical bony anatomy, such as the pubic arch, poses ch...

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...

Intensity-modulated proton therapy (IMPT) plan optimization is time-intensive due to its high dimensionality and the inherent non-convexity of clinical dosimetric constraints. Conventional algorithms like projected gradient descent (PGD) often require extensi...

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...

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 quantify the dosimetric consequences of physiology-composed abdominal motion on pancreatic cancer SBRT.

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...

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.