Weiguo Lu, PhD

To develop a WEb-Accessible comprehensiVE (WEAVE) platform, that combines AI-driven segmentation with a user-friendly interface to automatically segment Vestibular Schwannomas (VS) and track longitudinal volumes for disease assessment, planning, and monitorin...

To address fragmentation and variability in longitudinal brain lesion assessment, we developed Brain-Dynamics, a vendor-neutral platform integrating auto‑segmentation, multimodal co‑registration, lesion labeling/tracking, and quantitative analytics for resear...

Cone-beam CT (CBCT) acquired on the linear accelerator is being increasingly used beyond image guidance to support simulation and treatment planning workflows. This work reports the clinical implementation, challenges, and solutions associated with CBCT-based...

In MR-only radiotherapy planning (MROP), limited field-of-view (LFOV) acquisition and imaging artifacts can introduce truncated anatomy and density inaccuracies, reducing the reliability of dose calculation and preventing comprehensive plan evaluation due to...

Simulation-omitted prostate SBRT (SO-PRO) has potential to reduce treatment delays and expand access to care but presents unique challenges for SBRT workflows that require careful management of target and organ-at-risk (OAR) dose. A major barrier is diagnosti...

DeepTuning is a deep learning–based dose prediction framework that generates multiple dose distributions with different trade-offs, analogous to multi-criteria optimization. Leveraging historical cases with varying trade-offs, DeepTuning extracts semantic tra...

To develop an AI agent framework leveraging large language models (LLMs) for intelligent data extraction and reasoning over radiation oncology data from oncology information systems (OIS) and electronic medical records (EMR), enabling patient-specific queries...

Online adaptive prostate MR-guided radiotherapy (MRgRT) is time-sensitive, and contouring with structure preparation can require upwards of 15 minutes per fraction. While vendor-TPS provided contours can be useful, performance and consistency vary by site, pr...

Proton arc therapy (PAT) holds promise for enhancing plan conformity while minimizing dose sparing. However, PAT faces practical barriers related to delivery inefficiency, and its effectiveness can be compromised by beam range and radiobiological uncertaintie...

MRI–only radiotherapy planning requires accurate synthetic CT (sCT) generation to enable dose calculation and patient positioning without a planning CT in Linac-based treatment delivery settings. While prior studies have demonstrated promising results for ind...

Adaptive radiotherapy (ART) and personalized ultra‑fractionated stereotactic adaptive radiotherapy (PULSAR) require longitudinal anatomical modeling, deformable image registration (DIR), and dose recalculation and accumulation. While these capabilities are we...

Accurately modeling how organs move is essential in modern medical imaging and radiotherapy. Tasks such as deformable image registration (DIR), dose accumulation, motion tracking, and treatment adaptation all depend on reliable representations of anatomical d...

Deep learning–based glioma segmentation models are commonly developed under the assumption that the standard glioma MRI protocol—T1-weighted, contrast-enhanced T1 (T1ce), T2-weighted, and FLAIR—is available; however, this assumption may not hold in time-const...

FLASH radiotherapy delivers curative dose to tumor at ultra-high dose rates (UHDR,>40Gy/s) while mitigating normal tissue toxicity. However, data on late-responding tissues are limited, halting its safe clinical translation. Owing to its steep dose–response a...

The goal of this study is to accurately estimate 3D deformation and generate real-time volumetric images using only one or two X-ray projections, overcoming the limitations of ultra-sparse conditions in conventional deformable image registration (DIR) and vol...

Accurate lesion segmentation is fundamental to medical image analysis, yet most methods are tailored to specific anatomical sites or modalities, limiting their generalizability in diverse clinical settings. While recent vision-language foundation models enabl...

Motion estimation naturally requires two time points, making it inherently a relational quantity. This constrains how motion can be learned during training, as the entanglement of paired data makes cross-modality and cross-dimensional scenarios particularly c...

Accurate tumor segmentation is essential for adaptive radiation therapy (ART) but remains time-consuming, labor-intensive, and subject to considerable inter-user variations. Recent advances in foundation models, such as Segment Anything Model 2 (SAM2), show s...