Research Interests
Deep learning, computer vision, multimodal large language models, and medical image analysis/computing
Biography
Xuzhe's research interests primarily lie in the intersection of deep learning, computer vision, multimodal large language models, and medical image analysis/computing, with a focus on model robustness and generalist AI. He was/is focusing on the following problems and techniques:
Problems: semantic segmentation, model robustness, image generation/synthesis, image classification, reasoning segmentation, multimodal learning
Techniques: self-supervised learning, domain adaptation, vision-language models, self-attention, generative models
Select Publications
1. Xuzhe Zhang, Xinzi He, Jia Guo, Nabil Ettehadi, et al., “PTNet3D: A 3D High-Resolution Longitudinal Infant Brain MRI Synthesizer Based on Transformers”, IEEE Transactions on Medical Imaging, 2022
2. Xuzhe Zhang, Elsa D Angelini, Fateme S Haghpanah, Andrew F Laine, et al., “Quantification of lung ventilation defects on hyperpolarized MRI: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD study”, Magnetic Resonance Imaging, 2022
3. Xuzhe Zhang, Christopher B. Cooper, Martin R. Prince, et al., “MRI Assessed Dynamic Hyperinflation Induced by Tachypnea in Chronic Obstructive Pulmonary Disease: The SPIROMICS-HF Study”, Radiology: Cardiothoracic Imaging, 2024
4. Xuzhe Zhang, Yuhao Wu, Elsa Angelini, et al., “MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling”, IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024