Author profile
Department of Radiation Oncology, University of Maryland School of Medicine
Brachytherapy is a standard component in cervical cancer treatment. Venezia applicators allow addition of limited needle positions to tandem and ovoid procedures, but needle selection and insertion depth largely rely on physician judgement, requiring some lev...
To develop prognostic models integrating delta radiomics from prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA-PET/CT) and dosiomics with clinical variables to predict metastasis-free survival (MFS) in patients with lo...
Four-dimensional cone-beam computed tomography (4D-CBCT) enables visualization of respiration-induced anatomical motion but suffers from degraded image quality due to sparse-view acquisition. This study proposes a deep learning-based approach combining interp...
To integrate the first nozzle-mounted, quad-camera prompt gamma imaging (PGI) system on a clinical proton therapy gantry and to evaluate its efficacy for proton range verification under realistic treatment delivery conditions.
Artificial Intelligence (AI) has undergone transformative advancements, revolutionizing medical imaging and radiation therapy with unprecedented precision and efficiency. Breakthroughs in agentic AI, foundation models, and interpretable AI have significantly...
Therapy Physics
To introduce a conditional Wavelet Diffusion framework incorporating depth-wise convolution for efficient high-resolution 3D medical image synthesis, and to evaluate its performance on MRI cross-modality translation and CT texture generation for realistic dig...
Deep learning–based three‑dimensional (3D) dose prediction models are increasingly becoming viable for radiotherapy workflows. However, their sensitivity to small variations in input data remains insufficiently characterized. This study presents a framework t...
Pulmonary fluid changes often necessitate treatment replanning; however, associated mass variations compromise deformable dose accumulation (DDA) and complicate its evaluation. Accurate estimation of cumulative dose and its associated uncertainty is therefore...
Radiomic survival models often have substantial class imbalance, which can distort patient ranking and reduce the reliability of predicted survival probabilities. This study evaluated commonly used imbalance-handling strategies and whether their effects chang...
Daily cone-beam CT (CBCT) is widely used in adaptive proton therapy; however, scatter artifacts can degrade image quality and introduce proton dose calculation inaccuracies. We developed a region-of-interest (ROI)–guided Swin-Transformer deep learning (DL) ne...
Model the therapeutic effects of chemotherapy, radiotherapy, and chemoradiotherapy to study the heterogeneous responses of pancreatic cancer patient-derived tumor organoids (PDTOs).
Accurate radiotherapy delivery requires precise knowledge of soft-tissue anatomy at the time of treatment, particularly for abdominal targets affected by respiration, peristalsis, and inter-fractional anatomical changes. Current clinical systems provide limit...
Ultrafast ultrasound (UFUS) enables imaging of blood flow, functional dynamics, cardiac motion, and real-time treatment verification. UFUS is often acquired using high frame-rate single plane-wave imaging (SPWI), which has limited image quality due to the sin...
With recent shifts in the federal funding landscape, many investigators are facing new challenges in supporting their research. An analysis of 2025 NIH data reveals a steep decline year-over-year in new grants awarded to AAPM members, raising serious concerns...
With recent shifts in the federal funding landscape, many investigators are facing new challenges in supporting their research. An analysis of 2025 NIH data reveals a steep decline year-over-year in new grants awarded to AAPM members, raising serious concerns...
Protoacoustic (PA) imaging enables real-time verification of proton dose deposition by reconstructing 3D initial pressure maps from acoustic signals generated during proton delivery. However, in practical treatment settings, detectors cannot fully surround th...
Radiomics models often exhibit unreliable performance and substantial variation across institutions. One aspect that has not been examined thoroughly is how parameter settings—such as normalization scale, outlier handling, and bin width—affect downstream resu...