Jun Zhou, PhD

Foundation models (FMs) have demonstrated strong performance on challenging radiation therapy tasks such as automatic delineation, deformable image registration, and multimodal visual question answering (VQA). However, they are typically task-specific and req...

Cone-beam CT (CBCT) is integral to modern radiotherapy workflows; however, limited soft-tissue contrast and imaging artifacts restrict its quantitative use, particularly for online auto-segmentation in CBCT-guided adaptive radiotherapy. Models pretrained on c...

Proton prostate SBRT is characterized by steep dose gradients and elevated linear energy transfer (LET) near the end of range, which may contribute to genitourinary (GU) toxicity. Prior work suggests that bladder neck (trigone) dose is a stronger predictor of...

Pin-ridge filters (pRFs) have emerged as a promising hardware-based approach for ultrafast proton beam delivery through upstream proton fluence modulation. While pRF-based planning techniques having been explored computationally, experimental implementation h...

Radiation-induced lymphopenia (RIL) is a prevalent and clinically significant toxicity in lung cancer radiotherapy. Circulating lymphocyte exposure is inherently time-dependent due to blood flow through irradiated volumes during beam delivery. Intensity-modul...

Post-mastectomy chest-wall (CW) irradiation is well suited for proton FLASH due to the predominance of normal tissue within the target and the feasibility of single-energy tangential transmission beam (TB) delivery. This study investigates optimization strate...

Adaptive replanning in head and neck (H&N) radiotherapy can be resource-intensive and can also disrupt clinical workflow. We developed and validated a machine learning model that combines dosiomics and clinical features to predict which patients are likely to...

With the number of proton centers increasing, each facing intermittent downtime or need for renovations. Developing optimal approaches to maintain uninterrupted treatment is essential to preserve clinical outcomes. This study outlines key risk factors, workfl...

Deformable image registration (DIR) in medical imaging remains inherently ill-conditioned due to structural ambiguities and weak anatomical constraints. Although foundation models (FMs) have shown strong promise for unsupervised DIR, existing approaches typic...

Ultra-fast imaging and delivery are rapidly transforming particle therapy, opening new directions for both FLASH and non-FLASH high-dose-rate treatments. This symposium aims to update the community on the accelerating progress in ultra-fast beam delivery, adv...

Online adaptive proton therapy is highly sensitive to interfractional anatomical variation, yet conventional online replanning workflows remain time‑intensive and limit routine clinical implementation, particularly for hypofractionated prostate stereotactic b...

Prostate MRI is increasingly used in modern radiotherapy, but compared with CT, large-scale MRI datasets remain limited for fine-tuning foundation models. This study investigates the cross-modality transferability of a CT–fine-tuned foundation model to prosta...