Search

Your search keyword '"Chen, Jinghua"' showing total 1,605 results
Start Over Author "Chen, Jinghua"
1,605 results on '"Chen, Jinghua"'

4. Single-cell exome sequencing reveals polyclonal seeding and TRPS1 mutations in colon cancer metastasis

Author

Cai, Jianqiang, Zhang, Weilong, Lu, Yalan, Liu, Wenjie, Zhou, Haitao, Liu, Mei, Bi, Xinyu, Liu, Jianmei, Chen, Jinghua, Yin, Yanjiang, Deng, Yiqiao, Luo, Zhiwen, Yang, Yi, Chen, Qichen, Chen, Xiao, Xu, Zheng, Zhang, Yueyang, Wu, Chaoling, Long, Qizhao, Huang, Chunyuan, Yan, Changjian, Liu, Yan, Guo, Lei, Li, Weihua, Yuan, Pei, Jiao, Yucheng, Song, Wei, Wang, Xiaobing, Huang, Zhen, Ying, Jianming, and Zhao, Hong

Published
2024
Full Text
View/download PDF

11. Deep Learning Predicts Prevalent and Incident Parkinson's Disease From UK Biobank Fundus Imaging

Author

Tran, Charlie, Shen, Kai, Liu, Kang, Ashok, Akshay, Ramirez-Zamora, Adolfo, Chen, Jinghua, Li, Yulin, and Fang, Ruogu

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Parkinson's disease is the world's fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson's disease and automate diagnostics would greatly improve the treatment of patients with Parkinson's disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson's disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson's disease from UK Biobank fundus imaging. Our results show that Parkinson's disease individuals can be differentiated from age and gender-matched healthy subjects with an Area Under the Curve (AUC) of 0.77. This accuracy is maintained when predicting either prevalent or incident Parkinson's disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations., Comment: 17 pages, 4 figures, 2 tables, 4 supplementary tables

Published
2023
Full Text
View/download PDF

12. LAVA: Granular Neuron-Level Explainable AI for Alzheimer's Disease Assessment from Fundus Images

Author

Yousefzadeh, Nooshin, Tran, Charlie, Ramirez-Zamora, Adolfo, Chen, Jinghua, Fang, Ruogu, and Thai, My T.

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has been hypothesized as a diagnostic site for AD detection owing to its anatomical connection with the brain. Developed AI models for this purpose have yet to provide a rational explanation about the decision and neither infer the stage of disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granular Neuron-level Explainer (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to assess the AD continuum directly from the retinal imaging without longitudinal or clinical evaluation. This method is applied to validate the retinal vasculature as a biomarker and diagnostic modality for Alzheimer's Disease (AD) evaluation. UK Biobank cognitive tests and vascular morphological features suggest LAVA shows strong promise and effectiveness in identifying AD stages across the progression continuum., Comment: 27 pages, 11 figures

Published
2023

16. Design and Implementation of a Single Map of Meteorological Basic Information

Author

Chen Jinghua, Xiao Wenming, Zhang Qiang, Yang Heping, Zhang Zhiqiang, Cao Lei, and Chen Nan

Subjects
a single map of meteorological basic information, big data, data services, geographic information, Meteorology. Climatology, QC851-999
Abstract

A single map of meteorological basic information is a demonstration of the integration of meteorological data resources and industry data. By establishing a spatiotemporal linkage for meteorological big data applications, it solves the challenge of integrating multi-source meteorological data for application services. The information map enables unified access, processing, storage, and management of multi-source heterogeneous spatiotemporal data through three key technologies: Spatial processing of high-resolution meteorological grid data, retrieval of long sequences of massive grid data within arbitrary spatiotemporal ranges, and fusion services for meteorological data and three-dimensional terrain. It provides users with refined data acquisition services. The information map is created using the meteorological big data cloud platform. The virtual server resources, spatial database resources, and meteorological data resources utilized are all sourced from the meteorological big data cloud platform. The information map offers functions such as spatial analysis of multi-source data, layer management, online mapping, and scene application. It extends the data service mode of the meteorological big data cloud platform. For the first time in the meteorological industry, the Beidou grid location code technology has been utilized to create a map of fundamental meteorological information. Through spatial dimensionality reduction, two-dimensional longitude and latitude values are transformed into one-dimensional Beidou grid location codes. Through algorithms, rapid spatial positioning is achieved, addressing the issue of low efficiency in creating spatial indexes for massive data. The information map integrates five categories of data resources: Basic geography, natural resources, ecological environment, socio-economic, and meteorology. It can dynamically combine and construct thematic services based on various meteorological application scenarios, achieving fast and efficient multi-source data services and applications. A map of meteorological basic information provides business support through layer and geographic spatial retrieval services for the new generation of short-term and imminent forecasting and early warning systems. This promotes the development of business systems and ensures the efficient and stable operation of meteorological services. A single map of meteorological basic information supports spatial query services for public meteorological reality mini-programs and China Meteorological Data Network. It expands channels and methods for the public to access meteorological information through public meteorological services. A single map of meteorological basic information ensures the provision of customized grid data temporal query services for major events, achieving integrated meteorological data query services for historical, current, and forecasted events. Accurate meteorological data play a crucial role in ensuring the success of major national events, such as Beijing Winter Olympic Games and Winter Paralympic Games in 2022, as well as in providing essential weather forecasts for events like "7·20" extremely heavy rainstorm of Zhengzhou in 2021. Additionally, meteorological data is shared for social service purposes. A map of meteorological basic information provides effective support in ensuring "life safety, production development, a prosperous life, and a healthy ecology".

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results