Yunzhi Huang

I am an Assistant Professor at School of Artificial Intelligence, Nanjing University of Information Science and Technology, also a memeber in AIM.

I received my Ph.D at the College of Biomedical Engineering, Sichuan University. Before that, I recieved my Bacholar's and Master's degree at the College of Eletronic Engineering, Sichuan Univerisity. During my PhD. period, I was offered the chance to visit at YAP Lab and IDEA Lab at the Department of Radiology, University of North Carolina at Chapel Hill, supervised by Prof. Pew-Tian YAP and Prof. Dinggang Shen.

Email  /  Google Scholar  /  GitHub  /  ResearchGate  /  LinkedIn

profile photo
Research

My research interest lies in the intersection deep learning in medical image analysis. Specifically, I am dedicated to applications in 1) fast registration models, 2) neurosurgery planning.

Please be free to contact me if you would like to collaborate with me!

News

[06/2023] Our paper on Longitudinal Prediction was accepted in PR.

[08/2022] Our paper on Learn2Reg was accepted in TMI.

[06/2022] Two papers were accepted by MICCAI 2022:

"Weakly Supervised MR-TRUS Image Synthesis for Brachytherapy of Prostate Cancer"

"Localizing the Recurrent Laryngeal Nerve via Ultrasound with a Bayesian Shape Framework"

[09/2021] Our study on deformable registration of brain MR images via a hybrid loss were invited to an oral presentation in MICCAI 2021 Learn2Reg challenge.

[06/2021] One paper was accepted by MICCAI 2021.

[01/2021] Our study on difficulty-aware hierarchical convolutional neural networks for deformable registration of brain MR images was accepted by MedIA.

[12/2020] I successfully defended my Ph.D thesis.

[09/2020] I completed my internship at Departement of Radiology, UNC-CH.

[06/2020] Our study on semi-supervised segmentation of lesion from breast ultrasound images with attentional generative adversarial network was accepted by CMPB.

[12/2019] Our study on automatic detection on intracranial aneurysm from digital subtraction angiography with cascade convolutional neural networks was accepted by Biomedical Engineering Online.

[12/2019] Our study on two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images was accepted by Biomedical Engineering Online.

[05/2018] Our study on sensor level functional connectivity topography comparison between different references based EEG and MEG was accepted by Frontiers in behavioral neuroscience.

[07/2017] Our study on how different EEG references influence sensor level functional connectivity graphs was accepted by Frontiers in neuroscience.

Representative Publications
Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network

Prediction of infant brain MRI is challenging owing to the rapid contrast and structural changes particularly during the first year of life. We introduce a trustworthy metamorphic generative adversarial network (MGAN) for translating infant brain MRI from one time-point to another.

Pattern Recognition, 2023
Localizing the Recurrent Laryngeal Nerve via Ultrasound with a Bayesian Shape Framework

We propose the first learning-based framework to identify the RLN from a US image for pre-operative assessment of contraindication for robotic thyroidectomy.

MICCAI, 2022 (Early Acceptance)
Deformable registration of brain MR images via a hybrid loss

Considering that well-designed loss functions can facilitate a learning model into a desirable convergence, we learn a deformable registration model for T1-weighted MR images by integrating multiple image characteristics via a hybrid loss.

MICCAI Challenge, 2021
Difficulty-aware hierarchical convolutional neural networks for deformable registration of brain MR images

we present a difficulty-aware model based on an attention mechanism to automatically identify hard-to-register regions, allowing better estimation of large complex deformations. The difficulty-aware model is incorporated into a cascaded neural network consisting of three sub-networks to fully leverage both global and local contextual information for effective registration.

arXiv / code

Medical Image Analysis, 2021
Experience

Departement of Radiology, Univerisity of North Carolina at Chapel Hill
Student Intern
Advisor: Prof. Pew-Tian YAP and Prof. Dinggang Shen

Sep. 2018 - Sep. 2020

Grants

"Research on Intraoperative Trajectory Optimization for Brain Tumor Resection based on Multi-modal Images", NSFC, 2022-2024, No. 62101365

Startup Research Foundation, Nanjing University of Information Science and Technology, 2022-2024

Professional Activities

Review Service

IEEE Transactions on Medical Imaging

Pattern Recognition

Medical Image Analysis

MICCAI 2022

Teaching

University of Nanjing Univerisity of Information Science and Technology, 22/23(1) Artificial Intelligence and Machine Learning

University of Nanjing Univerisity of Information Science and Technology, 22/23(1) Machine Learning



Template is adapted from here.