Shanhui Sun is currently the head of AI and medical imaging at UII America, Inc., Cambridge, MA 02140, where he works in medical imaging, computer vision, machine learning & deep learning. Before joining UII America, he was Principal Scientist at CuraCloud, Princeton, NJ 08540 and a staff scientist at Siemens Corporate Research at Princeton, NJ 08540.
He received his Ph.D. at the Department of Electrical and Computer Engineering (ECE), the University of Iowa, in December 2012 under the supervision of Prof. Reinhard Beichel. He was a researcher in The Iowa Institute for Biomedical Imaging (IIBI) from year 2008 to year 2013 under the supervision of Prof. Reinhard Beichel and Prof. Milan Sonka. His Ph.D. thesis is about medical image analysis using a proposed hybrid virtual reality (VR) and desktop environment. The thesis can be found at "Automated and interactive approaches for optimal surface finding based segmentation of medical image data".
Google Scholar / LinkedIn / Email
Our paper "An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal " has been accepted by IPMI 2023.
Our paper "Invertible Sharpening Network for MRI Reconstruction Enhancement " has been accepted by MICCAI 2022.
Our paper "Pyramid Convolutional RNN for MRI Image Reconstruction" has been accepted by TMI.
We will present a new multi-modal image registration framework using a multi-scale neural ODE network in MICCAI 2021.
We got 3 papers accepted in MICCAI 2020.
We proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation for cardiac MRI motion tracking. This work: "FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation" will be presented in CVPR 2020.
We won multi-coil 4x track in the first fastMRI challenge which was co-organized by Facebook AI and NYU Langone Health. Our AI method is summarized in this paper. Please check it.
My work of automated Ultrasound Transesophageal Echocardiography (TEE) Transducer Detection (6 Degree of Freedom) in X-ray Fluoroscopy Videos using Machine Learning and Computer Vision Technology is now in a new Siemens product (TrueFusion, FDA clearance), and is featured on Siemens' Website. This technology is explained in our MICAAI 2016 paper (S. Sun et al. Towards Automated Ultrasound Transesophageal Echocardiography and X-Ray Fluoroscopy Fusion using an Image-based Co-registration Method, MICCAI 2016).
Selected Papers (More on publication page):
J. Xu, E. Chen, X. Chen, T. Chen, S. Sun Multi-scale Neural ODEs for 3D Medical Image Registration (MICCAI 2021)
H. Yu, X. Chen, H. Shi, T. Chen, T. Huang, S. Sun, Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation (MICCAI 2020)
K. Xuan, S. Sun, Z. Xue, L. Chen, Q. Wang, D. Shen, and S. Liao, Learning MRI k-Space Subsampling Pattern Using Progressive Weight Pruning (accepted by MICCAI 2020)
E. Z. Chen, T. Chen, S. Sun, MRI Image Reconstruction via Learning Optimization Using Neural ODEs (MICCAI 2020)
H. Yu, S. Sun, H. Yu, X Chen, H. Shi, T. Huang, T. Chen, FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation (CVPR 2020)
E. Z. Chen, X. Chen, J. Lv, Y. Zheng, T. Chen, J. Xu, and S. Sun, Real-Time Cardiac Cine MRI with Residual Convolutional Recurrent Neural Network (ISMRM 2020)
S. Sun*, J. Hu*, M. Yao, J. Hu, X. Yang, Q. Song and X. Wu, Robust Multimodal Image Registration using Deep Recurrent Reinforcement Learning, Accepted by ACCV 2018 (*co-first author)
B. Kong, S. Sun*, X. Wang, Q. Song, S. Zhang* Invasive Cancer Detection Utilizing Compressed Convolutional Neural Network and Transfer Learning. MICCAI 2018 (Early Accept, *co-advisor)
S. Sun et al. Towards Automated Ultrasound Transesophageal Echocardiography and X-Ray Fluoroscopy Fusion using an Image-based Co-registration Method, MICCAI 2016
S. Sun, J. Ernst, A. Sapkota, E. Ritzhaupt-Kleissl, R. Wiles, J. Bamberger and T. Chen. Short Term Cloud Coverage Prediction using Ground Based All Sky Imager, IEEE Smart Grid Comm, 2014
S. Sun, M. Sonka and R. Beichel. Graph-Based IVUS Segmentation with Efficient Computer-Aided Refinement. IEEE Transaction on Medical Imaging, 32(8):1536-1549, August 2013.
S. Sun, M. Sonka and R. Beichel. Lung Segmentation Refinement based on Optimal Surface Finding Utilizing a Hybrid Desktop/Virtual Reality User Interface. Computerized Medical Imaging and Graphics., 31(1): 15-27 (2013)
S. Sun, M. Sonka and R. Beichel. Graph-based 4D Lung Segmentation in CT Images with Expert-Guided Computer-Aided Refinement. 2013 International Symposium on Biomedical Imaging (ISBI).
S. Sun, C. Bauer, and R. Beichel. Automated 3D Segmentation of Lungs with Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach. IEEE Trans. Med. Imag., 31(2): 449–460, February 2012.