Brief Bio

Currently, I am a senior applied research scientist at Nvidia Corporation, focusing on deep learning techniques and their application in medical imaging. Previously, I spent 3 years as a visiting fellow in Dr. Ronald Summers's CAD lab at National Institutes of Health Clinical Center. From Dec. 2013 to Jun. 2015, I was a product manager of post-processing workstations for multiple medical imaging modalities in Shanghai United Imaging Healthcare (UIH). Prior, I worked as an algorithm engineer and then dept. manager in Computer Aided Diagnosis (CAD) Department, Healthcare Software Unit, UIH, from Sep. 2011 to Nov. 2013. I received my PhD in Computer Vision under the supervision of Prof. Majid Mirmehdi at University of Bristol, UK in 2011. My research interests include computer vision, machine learning , deep learning and its application in medical imaging.

• My latest CV -- Google Scholar -- Linkedin Page

• Email： xiaosong.wang AT live.com ; xiaosongw AT nvidia.com

ChestX-ray Dataset

• Dataset download link: NIH Clinical Center Box.
• [Sep. 26, 2017] First Release of the ChestX-ray dataset
  
• [Dec. 16, 2017] Release data split files: train_val_list.txt and test_list.txt

Updates

• [Feb. 20th, 2018] News: Two of our papers are accepted in CVPR 2018, i.e. "TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays." and "Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Database."

• [Nov. 16^th, 2017] News: We are selected to recieve a prestigious NIH Clincial Center CEO Award for advancing radiology science and patient care by organizing and releasing a large dataset of radiology images to the public.
• [Sep. 26^th, 2017] News: the ChestX-ray14 dataset is finally available for public access via NIH Clinical Center Box. Find more details in the README file.
• [Jul. 26^th, 2017] I am invited to give an talk in Medical Computer Vision and Health Informatics Workshop CVPR 2017 about our recent work on "Big Data, Weak Label and True Clinical Impacts for Radiology Imaging Diagnosis" (slides).
• [Jul. 24^th, 2017] Our work “DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations” is accepted as a scientific poster in RSNA 2017
  
• [Mar. 07^th, 2017] Our work on “ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases” is accepted as a spotlight in CVPR 2017.
• [Dec. 20^th, 2016] Our work on “Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Annotation and Scene Recognition” is accepted in WACV 2017.
• [Nov. 26^th, 2016] Our work “Automated Annotation of a Large Scale Radiology Image Database using Deep Learning” wins the trainee research prize in RSNA 2016.
• [July 26^th, 2016] Our work “Automated Annotation of a Large Scale Radiology Image Database using Deep Learning” is accepted as a scientific poster in RSNA 2016.
• [July 25^th, 2016] Our medical image categorization work wins the NIH Fellows Award of Research Excellence (FARE) 2017 competition.
• [Apr. 29^th, 2016] Our paper “Automatic Lymph Node Cluster Segmentation using Holistically-Nested Networks and Structured Optimization in CT images” is early accepted in MICCAI 2016.
• [July 20^th, 2015] I start my postdoctoral fellowship in NIH.

X. Wang, Y. Peng, L. Lu, Z. Lu, R. M. Summers.

TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays. 

IEEE CVPR 2018;  arXiv:1801.04334, 2018 

[PDF]

K. Yan*, X. Wang*, L. Lu, R. M. Summers.

DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations 

arXiv:1710.01766; RSNA, 2017; IEEE CVPR 2018 

[PDF] [Data]

X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, R. M. Summers.

ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases. 

IEEE CVPR (spotlight);  arXiv:1705.02315, 2017 

[PDF] [Data]

X. Wang, L. Lu, H. Shin, L. Kim, M. Bagheri, I. Nogues, J. Yao, R. M. Summers.

Unsupervised Joint Mining of Deep Features and Image Labels for Large-scale Radiology Image Categorization and Scene Recognition.

IEEE WACV; arXiv:1701.06599; arXiv:1603.07965; RSNA 2016 
Winner of 2016 RSNA Trainee Research Award

[PDF] [Data]

I. Nogues, L. Lu, X. Wang, H. Roth, G. Bertasius, N. Lay, J. Shi, Y. Tsehay, R. M. Summers.

Automatic Lymph Node Cluster Segmentation using Holistically-Nested Networks and Structured Optimization.

MICCAI, 2016

[PDF]

X. Wang and M. Mirmehdi.

Archive Film Defect Detection and Removal: an Automatic Restoration Framework.

IEEE Transactions on Imaging Processing (T-IP), 2012

[PDF] [PhD Thesis]

X. Wang and M. Mirmehdi.

Archive Film Restoration based on Spatiotemporal Random Walks.

European Conference on Computer Vision (ECCV), 2010

[PDF]

X. Wang and M. Mirmehdi.

HMM based Archive Film Defect Detection with Spatial and Temporal constraints.

British Machine Vision Conference (BMVC), 2009
Winner of the Best Industrial Paper Prize

[PDF]

Last update: Sep. 2017