Area of research
Radiology, Nuclear Medicine and Imaging · Biomedical Engineering
Research interest
Research interests include Medical Imaging Techniques and Applications, Radiomics and Machine Learning in Medical Imaging, Advanced MRI Techniques and Applications, and Advanced X-ray and CT Imaging.
LeqMod: Adaptable Lesion-Quantification-Consistent Modulation for Deep Learning Low-Count PET Image Denoising.
GM-ABS: Promptable Generalist Model Drives Active Barely Supervised Training in Specialist Model for 3D Medical Image Segmentation.
SAM-driven cross prompting with adaptive sampling consistency for semi-supervised medical image segmentation.
AugGPT: Leveraging ChatGPT for Text Data Augmentation
Artificial General Intelligence for Medical Imaging Analysis
EchoFM: Foundation Model for Generalizable Echocardiogram Analysis
Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task
MediViSTA: Medical Video Segmentation Via Temporal Fusion SAM Adaptation for Echocardiography.
Nuclear Medicine AI in Action: The Bethesda Report (AI Summit 2024)
MA-SAM: Modality-agnostic SAM adaptation for 3D medical image segmentation
Zero shot health trajectory prediction using transformer
LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models
Artificial General Intelligence for Medical Imaging Analysis
Spach Transformer: Spatial and Channel-Wise Transformer Based on Local and Global Self-Attentions for PET Image Denoising.
Hallucination Index: An Image Quality Metric for Generative Reconstruction Models.
Anatomically Guided PET Image Reconstruction Using Conditional Weakly-Supervised Multi-Task Learning Integrating Self-Attention.
Volumetric Conditional Score-Based Residual Diffusion Model for PET/MR Denoising
Zero Shot Health Trajectory Prediction Using Transformer
Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study.
Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study (Preprint)
Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops
Nuclear Medicine and Artificial Intelligence: Best Practices for Algorithm Development.
Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior.
Penalized-Likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding.
Connectivity-based Cortical Parcellation via Contrastive Learning on Spatial-Graph Convolution.
Multiscale Multimodal Medical Imaging
Resting-State Electroencephalography for Continuous, Passive Prediction of Coma Recovery After Acute Brain Injury
Federated learning for predicting clinical outcomes in patients with COVID-19
A Graph Gaussian Embedding Method for Predicting Alzheimer's Disease Progression With MEG Brain Networks
Self-Supervised Dynamic CT Perfusion Image Denoising With Deep Neural Networks