I am a fifth-year PhD student at Emory University in the Department of Computer Science. I currently work on Medical Image Processing using Deep Learning methods with Prof. Imon Banerjee and Prof. Ashish Sharma. Before this, I worked with Prof. Jun Kong during Aug.2017~Sep.2018. My expected graduation is December 2022. I'm actively seeking for full-time positions related to deep learning, machine learning, computer vision.
I'm broadly interested in computer vision and medical image processing. My research involves object detection, object segmentation, and medical image analysis(whole-slide microscopy image and radiology image) using deep neural networks.


Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Xiaoyuan Guo, Jiali Duan, C.-C. Jay Kuo, Judy Wawira Gichoya, Imon Banerjee.
ICPR 2022
OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
Xiaoyuan Guo, Jiali Duan, Saptarshi Purkayastha, Hari Trivedi, Judy Wawira Gichoya, Imon Banerjee.
ICMR 2022, oral presentation
MedShift: identifying shift data for medical dataset curation
Xiaoyuan Guo, Judy Wawira Gichoya, Hari Trivedi, Saptarshi Purkayastha, Imon Banerjee.
CVAD: A generic medical anomaly detector based on Cascade VAE
Xiaoyuan Guo, Judy Wawira Gichoya, Saptarshi Purkayastha, Imon Banerjee.
Margin-Aware Intra-Class Novelty Identification for Medical Images
Xiaoyuan Guo, Judy Wawira Gichoya, Saptarshi Purkayastha, Imon Banerjee.
SPIE 2022
TilGAN: GAN for Facilitating Tumor-Infiltrating Lymphocyte Pathology Image Synthesis with Improved Image Classification
Monjoy Saha, Xiaoyuan Guo, Ashish Sharma.
IEEE Access 2021
SCU-Net: A Deep Learning Method for Segmentation and Quantification of Breast Arterial Calcifications on Mammograms
Xiaoyuan Guo, William C O’Neill, Brianna Vey, Tianen Christopher Yang, Thomas J Kim, Maryzeh Ghassemi, Ian Pan, Judy Wawira Gichoya, Hari Trivedi, Imon Banerjee.
Medical Physics 2021
Deeper Thinner UNet (DT-UNet) for Fine Vessel Segmentation of Breast Arterial Calcification (BAC)
Xiaoyuan Guo, Judy Wawira Gichoya, Hari Trivedi, William C O’Neill, Rhakur Priya, Weijia Sun, Manisha Singh, Kathiravelu Pradeeban, Kim Thomas, Chris Yang, Imon Banerjee.
CMIMI 2020
Liver Steatosis Segmentation With Deep Learning Methods
Xiaoyuan Guo, Fusheng Wang, George Teodoro, Alton B. Farris, Jun Kong.
2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape based Intensity Analysis for Overlapped Nuclei in Fluorescence In-Situ Hybridization Images
Xiaoyuan Guo, Hanyi Yu, Blair Rossetti, George Teodoro, Daniel Brat, Jun Kong
EMBC 2018
A unified framework for multi-modal isolated gesture recognition
Jiali Duan, Jun Wan, Shuai Zhou,Xiaoyuan Guo, Stan Z Li
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)2017
PortraitGAN for Flexible Portrait Manipulation
Jiali Duan, Xiaoyuan Guo , Yuhang Song, Chao Yang, C-C Jay Kuo
Arxiv Preprint
A survey on algorithms of hole filling in 3D surface reconstruction
Xiaoyuan Guo, Jun Xiao, Ying Wang
The Visual Computer, 2016
Multi-modality fusion based on consensus-voting and 3d convolution for isolated gesture recognition
Jiali Duan, Shuai Zhou, Jun Wan, Xiaoyuan Guo, Stan Z Li
ArXiv Preprint
Face detection by aggregating visible components
Jiali Duan, Shengcai Liao, Xiaoyuan Guo, Stan Z Li
ACCV Workshop 2016 (Oral)

Other Projects

Lung Nodule Detection

Developing a Pytorch-based neural network to locate nodules in input 3D image CT volumes. Results will be seen soon!

Finding, Counting and Listing Triangles and Quadrilaterals in Large Graphs

Develop parallel algorithms for finding, counting and listing triangles and quadrilaterals in large graphs, OpenMP-based, MPI-based ans Spark-based parallel algorithms are implemented.

Hemorrhage Classification

Train a classifer to identify acute intracranial hemorrhage and its subtypes. Project is still ongoing.

Fibrosis Detection

Detect fibrosis area from the input tiff images.

Note: The background image is from internet, please contact me if you are the author of the image.