Dr. Xiaowei Wang Profile

Dr. Xiaowei Wang

at Univ of Illinois at Chicago

SPIE Involvement:

Author

Publications (4)

Proceedings Article | 2 April 2024 Poster + Paper

Self-supervised learning based on StyleGAN for medical image classification on small labeled dataset

Zong Fan, Zhimin Wang, Chaojie Zhang, Muzaffer Özbey, Umberto Villa, Yao Hao, Zhongwei Zhang, Xiaowei Wang, Hua Li

Proceedings Volume 12926, 1292630 (2024) https://doi.org/10.1117/12.3006959

KEYWORDS: Education and training, Data modeling, Image classification, Medical imaging, Feature extraction, Performance modeling, Solid state lighting, Classification systems, Network architectures, Design

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Transformer-based classifier with feature aggregation for cancer subtype classification on histopathological images

Chaojie Zhang, Zong Fan, Zhimin Wang, Lulu Sun, Yao Hao, Zhongwei Zhang, Wade Thorstad, Hiram Gay, Xiaowei Wang, Mark Anastasio, Hua Li

Proceedings Volume 12926, 1292633 (2024) https://doi.org/10.1117/12.3007045

KEYWORDS: Education and training, Cancer, Transformers, Performance modeling, Tumor growth modeling, Histopathology, Image classification, Tumors, Data modeling, Tissues

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Deep-supervised adversarial learning-based classification for digital histologic images

Zhimin Wang, Zong Fan, Lulu Sun, Yao Hao, Hiram Gay, Wade Thorstad, Xiaowei Wang, Hua Li

Proceedings Volume 12471, 124711V (2023) https://doi.org/10.1117/12.2654402

KEYWORDS: Tumors, Image classification, Education and training, Image processing, Cancer, Data modeling, Feature extraction, Performance modeling, Pathology, Image restoration

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Deep learning-based multi-class COVID-19 classification with x-ray images

Zong Fan, Shenghua He, Su Ruan, Xiaowei Wang, Hua Li

Proceedings Volume 11598, 1159813 (2021) https://doi.org/10.1117/12.2582261

KEYWORDS: Image classification, X-rays, X-ray imaging, Chest imaging, Convolutional neural networks, Radiography, Network architectures

Read Abstract +

The COVID-19 pandemic continues spreading rapidly around the world and has caused devastating outcomes towards the health of the global population. The reverse transcription-polymerase chain reaction (RT-PCR) test, as the only current gold standard for screening infected cases, yields a relatively high false positive rate and low sensitivity on asymptomatic subjects. The use of chest X-ray radiography (CXR) images coupled with deep- learning (DL) methods for image classification, represents an attractive adjunct to or replacement for RT-PCR testing. However, its usage has been widely debated over the past few months and its potential effectiveness remains unclear. A number of DL-based methods have been proposed to classify the COVID-19 cases from the normal ones, achieving satisfying high performance. However, these methods show limited performance on the multi-class classification task for COVID-19, pneumonia and normal cases, mainly due to two factors: 1) the textures in COVID-19 CXR images are extremely similar to that of pneumonia cases, and 2) there are much fewer COVID-19 cases compared to the other two classes in the public domain. To address these challenges, a novel framework is proposed to learn a deep convolutional neural network (DCNN) model for accurately classifying COVID-19 and pneumonia cases from other normal cases by the use of CXR images. In addition to training the model by use of conventional classification loss which measures classification accuracy, the proposed method innovatively employs a reconstruction loss measuring image fidelity and an adversarial loss measuring class distribution fidelity to assist in the training of the main DCNN model to extract more informative features to support multi-class classification. The experiment results on a COVID-19 dataset demonstrate the superior classification performance of the proposed method in terms of accuracy compared to other existing DL-based methods. The experiment on another cancer dataset further implies the potential of applying the proposed methods in other medical imaging applications.

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years