Search Results for author: Xiaosong Wang

Found 29 papers, 9 papers with code

Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports

no code implementations6 Oct 2021 Riddhish Bhalodia, Ali Hatamizadeh, Leo Tam, Ziyue Xu, Xiaosong Wang, Evrim Turkbey, Daguang Xu

Both the classification and localization are trained in conjunction and once trained, the model can be utilized for both the localization and characterization of pneumonia using only the input image.

Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays

no code implementations30 Mar 2021 Xiaosong Wang, Ziyue Xu, Leo Tam, Dong Yang, Daguang Xu

In this work, we introduce an image-text pre-training framework that can learn from these raw data with mixed data inputs, i. e., paired image-text data, a mixture of paired and unpaired data.

Language Modelling Masked Language Modeling +1

Transformer Query-Target Knowledge Discovery (TEND): Drug Discovery from CORD-19

no code implementations28 Nov 2020 Leo K. Tam, Xiaosong Wang, Daguang Xu

To stimulate COVID-19 research, we release an influenza clinical trials and antiviral analogies dataset used in conjunction with the COVID-19 Open Research Dataset Challenge (CORD-19) literature dataset in the study.

Drug Discovery Language Modelling +1

Going to Extremes: Weakly Supervised Medical Image Segmentation

2 code implementations25 Sep 2020 Holger R. Roth, Dong Yang, Ziyue Xu, Xiaosong Wang, Daguang Xu

Here, we suggest using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation.

BIG-bench Machine Learning Image Segmentation +2

Learning Image Labels On-the-fly for Training Robust Classification Models

no code implementations22 Sep 2020 Xiaosong Wang, Ziyue Xu, Dong Yang, Leo Tam, Holger Roth, Daguang Xu

We apply the attention-on-label scheme on the classification task of a synthetic noisy CIFAR-10 dataset to prove the concept, and then demonstrate superior results (3-5% increase on average in multiple disease classification AUCs) on the chest x-ray images from a hospital-scale dataset (MIMIC-CXR) and hand-labeled dataset (OpenI) in comparison to regular training paradigms.

General Classification Robust classification

Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies

1 code implementation31 Jul 2020 Leo K. Tam, Xiaosong Wang, Evrim Turkbey, Kevin Lu, Yuhong Wen, Daguang Xu

The architectural modifications address three obstacles -- implementing a supervised vision and language detection method in a weakly supervised fashion, incorporating clinical referring expression natural language information, and generating high fidelity detections with map probabilities.

Head Detection Referring Expression

Multi-Domain Image Completion for Random Missing Input Data

no code implementations10 Jul 2020 Liyue Shen, Wentao Zhu, Xiaosong Wang, Lei Xing, John M. Pauly, Baris Turkbey, Stephanie Anne Harmon, Thomas Hogue Sanford, Sherif Mehralivand, Peter Choyke, Bradford Wood, Daguang Xu

Multi-domain data are widely leveraged in vision applications taking advantage of complementary information from different modalities, e. g., brain tumor segmentation from multi-parametric magnetic resonance imaging (MRI).

Brain Tumor Segmentation Disentanglement +1

Enhancing Foreground Boundaries for Medical Image Segmentation

no code implementations MIDL 2019 Dong Yang, Holger Roth, Xiaosong Wang, Ziyue Xu, Andriy Myronenko, Daguang Xu

Object segmentation plays an important role in the modern medical image analysis, which benefits clinical study, disease diagnosis, and surgery planning.

Image Segmentation Medical Image Segmentation +1

When Radiology Report Generation Meets Knowledge Graph

no code implementations19 Feb 2020 Yixiao Zhang, Xiaosong Wang, Ziyue Xu, Qihang Yu, Alan Yuille, Daguang Xu

In addition, we proposed a new evaluation metric for radiology image reporting with the assistance of the same composed graph.

Graph Embedding Image Captioning

Correlation via Synthesis: End-to-end Image Generation and Radiogenomic Learning Based on Generative Adversarial Network

no code implementations MIDL 2019 Ziyue Xu, Xiaosong Wang, Hoo-chang Shin, Dong Yang, Holger Roth, Fausto Milletari, Ling Zhang, Daguang Xu

In this work, we investigate the potential of an end-to-end method fusing gene code with image features to generate synthetic pathology image and learn radiogenomic map simultaneously.

Image Generation

Training Models 20X Faster in Medical Image Analysis

no code implementations MIDL 2019 Dong Yang, Holger Roth, Xiaosong Wang, Ziyue Xu, Yan Cheng, Daguang Xu

Analyzing high-dimensional medical images (2D/3D/4D CT, MRI, histopathological images, etc.)

Weakly supervised segmentation from extreme points

no code implementations2 Oct 2019 Holger Roth, Ling Zhang, Dong Yang, Fausto Milletari, Ziyue Xu, Xiaosong Wang, Daguang Xu

Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images.

BIG-bench Machine Learning Weakly supervised segmentation

Correlation via synthesis: end-to-end nodule image generation and radiogenomic map learning based on generative adversarial network

no code implementations8 Jul 2019 Ziyue Xu, Xiaosong Wang, Hoo-chang Shin, Dong Yang, Holger Roth, Fausto Milletari, Ling Zhang, Daguang Xu

Radiogenomic map linking image features and gene expression profiles is useful for noninvasively identifying molecular properties of a particular type of disease.

Clustering Image Generation

Spatio-Temporal Convolutional LSTMs for Tumor Growth Prediction by Learning 4D Longitudinal Patient Data

no code implementations23 Feb 2019 Ling Zhang, Le Lu, Xiaosong Wang, Robert M. Zhu, Mohammadhadi Bagheri, Ronald M. Summers, Jianhua Yao

Results validate that the ST-ConvLSTM produces a Dice score of 83. 2%+-5. 1% and a RVD of 11. 2%+-10. 8%, both significantly outperforming (p<0. 05) other compared methods of linear model, ConvLSTM, and generative adversarial network (GAN) under the metric of predicting future tumor volumes.

Image Segmentation Left Ventricle Segmentation +2

Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs

no code implementations19 Jul 2018 Yu-Xing Tang, Xiaosong Wang, Adam P. Harrison, Le Lu, Jing Xiao, Ronald M. Summers

In addition, highly confident samples (measured by classification probabilities) and their corresponding class-conditional heatmaps (generated by the CNN) are extracted and further fed into the AGCL framework to guide the learning of more distinctive convolutional features in the next iteration.

Classification General Classification +1

NegBio: a high-performance tool for negation and uncertainty detection in radiology reports

1 code implementation16 Dec 2017 Yifan Peng, Xiaosong Wang, Le Lu, Mohammadhadi Bagheri, Ronald Summers, Zhiyong Lu

Negative and uncertain medical findings are frequent in radiology reports, but discriminating them from positive findings remains challenging for information extraction.


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

no code implementations23 Jan 2017 Xiaosong Wang, Le Lu, Hoo-chang Shin, Lauren Kim, Mohammadhadi Bagheri, Isabella Nogues, Jianhua Yao, Ronald M. Summers

The recent rapid and tremendous success of deep convolutional neural networks (CNN) on many challenging computer vision tasks largely derives from the accessibility of the well-annotated ImageNet and PASCAL VOC datasets.

Clustering General Classification +3

Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database

no code implementations25 Mar 2016 Xiaosong Wang, Le Lu, Hoo-chang Shin, Lauren Kim, Isabella Nogues, Jianhua Yao, Ronald Summers

Obtaining semantic labels on a large scale radiology image database (215, 786 key images from 61, 845 unique patients) is a prerequisite yet bottleneck to train highly effective deep convolutional neural network (CNN) models for image recognition.


Cannot find the paper you are looking for? You can Submit a new open access paper.