Z
Zhaohui Liang
Researcher at York University
Publications - 7
Citations - 257
Zhaohui Liang is an academic researcher from York University. The author has contributed to research in topics: Deep learning & Generative model. The author has an hindex of 4, co-authored 7 publications receiving 156 citations.
Papers
More filters
Proceedings ArticleDOI
CNN-based image analysis for malaria diagnosis
Zhaohui Liang,Andrew Powell,Ilker Ersoy,Mahdieh Poostchi,Kamolrat Silamut,Kannappan Palaniappan,Peng Guo,Amir Hossain,Antani Sameer,Richard J. Maude,Jimmy Xiangji Huang,Stefan Jaeger,George R. Thoma +12 more
TL;DR: This study proposes a new and robust machine learning model based on a convolutional neural network (CNN) to automatically classify single cells in thin blood smears on standard microscope slides as either infected or uninfected.
Journal ArticleDOI
DL-ADR: a novel deep learning model for classifying genomic variants into adverse drug reactions
TL;DR: A novel deep learning model based on generative stochastic networks and hidden Markov chain to classify the observed samples with SNPs on five loci of two genes respectively to the vulnerable population of 14 types of adverse reactions is presented.
Journal ArticleDOI
Deep generative learning for automated EHR diagnosis of traditional Chinese medicine.
TL;DR: This study shows the two-step deep learning model achieves high performance for medical information retrieval over the conventional shallow models and is an appropriate knowledge-learning model for information retrieval of EMR system.
Proceedings ArticleDOI
Enhancing Automated COVID-19 Chest X-ray Diagnosis by Image-to-Image GAN Translation
TL;DR: In this paper, a conditional adversarial network (cGAN) was applied to perform image to image (Pix2Pix) translation from the non-COVID-19 chest X-ray domain to the COVID-2019 chest Xray domain.
Proceedings ArticleDOI
Discovery of the relations between genetic polymorphism and adverse drug reactions
TL;DR: A generative model is proposed to describe the joint distributions of occurrence of ADRs and the diversity of genetic sub-types of the input variables and the newly algorithm is more effective than the available conventional methods.