Adaptive radiotherapy adjusts treatment to the anatomy seen on the day. But before a plan can adapt, a person has to decide where the treatment target begins and ends. This work examines how those decisions vary across clinical specialties.
A treatment-target name is a small piece of text with a large job: it has to preserve clinical intent while fitting a shared naming convention. This project explores where local language models can help, and where a clinician still needs to look closely.
Preview images load from this site. YouTube connects only after you press play.
For people with multiple brain metastases, a radiation plan needs to cover the targets while limiting dose outside them. This study asks how high-fidelity planning and control rings change that balance on Ethos 2.0.
Preview images load from this site. YouTube connects only after you press play.
Good overlap scores are useful, but they do not tell the whole story of an automatically drawn organ. This head-to-head study pairs quantitative evaluation with blinded physician review.
Preview images load from this site. YouTube connects only after you press play.
Follow-up imaging asks clinicians to understand what has changed since treatment. This project brings earlier treatment contours into the follow-up magnetic-resonance image so that history is easier to review.
Beam energy affects more than delivery speed. This planning-and-phantom study asks how the choice between two flattening-filter-free photon beams changes lung-treatment dosimetry and efficiency.
Preview images load from this site. YouTube connects only after you press play.
Before the clinical-AI projects, biophysics offered a way to study complex biological questions through a controlled model system. This paper investigates interactions between selected compounds, synthetic membranes, and amyloid aggregates.
Preview images load from this site. YouTube connects only after you press play.
A short collaboration showcase about Udi’s visiting-scholar experience, AI research and student exchange between UAB and McMaster.
Uploaded September 11, 2024
A recorded presentation on optimizing dose delivery during fractionated radiotherapy, associated with CUPC 2023.
Uploaded October 29, 2023
Event: October 28, 2023
My TG-263 work exposed a useful safety distinction. Explore the three checks below; no patient data or clinical recommendation is shown.
The candidate uses the expected character set, structure, and permitted anatomy label.
Illustrative logic only. The published poster evaluated a reviewed naming workflow; it did not validate autonomous clinical use.
See the methods, results, and limitations →The research record also includes optical brain measurement, smartphone gel-electrophoresis analysis, augmented reality for surgical models, genomic radiation-dose modelling, and early biophysics.