Zehui Zhao

Zehui Zhao

Auto-generated profile, based on publicly available information

Zehui Zhao

School of Computer Science, Queensland University of Technology, Brisbane, 4000, QLD, Australia

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2023 in Expert Systems with Applications
Verified
Journal Article
Open access
ZZZehui Zhao
Zehui Zhao
Laith AlzubaidiLaith Alzubaidi
Laith Alzubaidi
Jinglan ZhangJinglan Zhang
Jinglan Zhang
YDYe Duan
Ye Duan
YGYuantong Gu
Yuantong Gu

8 February 2025 in Pattern Recognition Letters
Verified
Journal Article
Open access
HAHaider A. Alwzwazy
Haider A. Alwzwazy
Laith AlzubaidiLaith Alzubaidi
Laith Alzubaidi
ZZZehui Zhao
Zehui Zhao
YGYuantong Gu
Yuantong Gu

17 September 2025 in Computers in Biology and Medicine
Verified
Journal Article
Open access
ZZZehui Zhao
Zehui Zhao
Laith AlzubaidiLaith Alzubaidi
Laith Alzubaidi
Jinglan ZhangJinglan Zhang
Jinglan Zhang
YDYe Duan
Ye Duan
UNUsman Naseem
Usman Naseem
YuanTong GuYuanTong Gu
YuanTong Gu
Deep learning has significantly advanced automatic medical diagnostics, releasing human resources from clinical pressure, yet the persistent challenge of data scarcity in this area hampers its further improvements and applications. To address this gap, we introduce a novel ensemble framework called 'Efficient Transfer and Self-supervised Learning based Ensemble Framework' (ETSEF). ETSEF leverages features from multiple pre-trained deep learning models to efficiently learn powerful representations from a limited number of data samples. To the best of our knowledge, ETSEF is the first strategy that combines two pre-training methodologies (Transfer Learning and Self-supervised Learning) with ensemble learning approaches. Various data enhancement techniques, including data augmentation, feature fusion, feature selection, and decision fusion, have also been deployed to maximise the efficiency and robustness of the ETSEF model. Five independent medical imaging tasks, including endoscopy, breast cancer detection, monkeypox detection, brain tumour detection, and glaucoma detection, were tested to demonstrate ETSEF's effectiveness and robustness. Facing limited sample numbers and challenging medical tasks, ETSEF has demonstrated its effectiveness by improving diagnostic accuracy by up to 13.3% compared to strong ensemble baseline models and up to 14.4% compared with recent state-of-the-art methods. Moreover, we emphasise the robustness and trustworthiness of the ETSEF method through various vision-explainable artificial intelligence techniques, including Grad-CAM, SHAP, and t-SNE. Compared to large-scale deep learning models, ETSEF can be flexibly deployed and maintain superior performance for challenging medical imaging tasks, demonstrating potential for application in areas lacking training data. The code is available at Github ETSEF.

11 August 2025 in Intelligent Systems with Applications
Verified
Journal Article
Open access
HAHaider A. Alwzwazy
Haider A. Alwzwazy
Laith AlzubaidiLaith Alzubaidi
Laith Alzubaidi
ZZZehui Zhao
Zehui Zhao
ASAhmed Saihood
Ahmed Saihood
SJSabah Abdulazeez Jebur
Sabah Abdulazeez Jebur
YuanTong GuYuanTong Gu
YuanTong Gu

22 March 2026 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
ZZZehui Zhao
Zehui Zhao
Laith AlzubaidiLaith Alzubaidi
Laith Alzubaidi
HAHaider A. Alwzwazy
Haider A. Alwzwazy
JZJinglan Zhang
Jinglan Zhang
ZAZaenab Alammar
Zaenab Alammar
YGYuantong Gu
Yuantong Gu
Nowadays, artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms have emerged as promising avenues for designing robust, scalable diagnostic and prognostic models from medical data. Despite the high performance these models exhibit, they still face significant challenges in the healthcare domain when trained with the traditional centralized learning paradigm, including data security, data heterogeneity, data scarcity, and computational limitations. Recent developments in decentralized learning have attracted attention from both academia and industry, providing a promising way to train high-performance AI models while maintaining data privacy. For instance, recent developments in federated learning have enabled the aggregation of local model weights to obtain a global model, rather than collecting data from each client for global training. Other emerging techniques have made use of blockchain techniques to ensure a safe peer-to-peer transaction, providing more options and possibilities for decentralized learning. In this review, we aim to explore the present and future of decentralized technologies in healthcare domain, where data privacy and model performance are high priorities in data sharing. This study primarily focuses on reviewing different decentralized learning paradigms combined with AI technologies in healthcare applications, including their difference in methodologies, performance, challenges, and future directions. We also highlighted the influence of base model selections on decentralized systems, such as performance variety, computational cost, and communication burden. In this context, we demonstrate that decentralized learning methods have a good potential to improve hospital collaboration, while making a trade-off between system performance and data privacy at a low cost. Furthermore, we provide future directions for current decentralized methods by summarizing the state of the art works and identifying open problems.

6 January 2026 in PeerJ Computer Science
Verified
Journal Article
Open access
zaenab Kareem Abood Alammarzaenab Kareem Abood Alammar
zaenab Kareem Abood Alammar
LALaith Alzubaidi
Laith Alzubaidi
JZJinglan Zhang
Jinglan Zhang
YLYuefeng Li
Yuefeng Li
ZZZehui Zhao
Zehui Zhao
YGYuantong Gu
Yuantong Gu
Aim: Musculoskeletal radiographs (X-rays) are commonly used to diagnose bone and joint abnormalities because they are affordable and accessible. Convolutional neural networks (CNN) have demonstrated strong performance in medical image classification. However, interpreting these images reliably is challenging due to a lack of labelled data, inherent image noise, and the lack of explainable artificial intelligence (AI). This research aims to improve the robustness against noise, accuracy, and interpretability of musculoskeletal radiograph classification by addressing these key challenges. Method: This study proposes an attention-enhanced deep learning framework that combines in-domain self-supervised pretraining, region-specific attention-based convolutional neural networks, and hierarchical feature fusion. To reduce redundancy and improve generalisation, descriptor-based feature selection is applied before classification. The final classification is performed through an ensemble of classifiers, and visual explanation techniques (such as Grad-CAM) are used to enhance model transparency. Finding: The proposed model demonstrated high classification accuracy, achieving 95.48% on the MURA dataset and 99.80% on the Chest X-ray dataset. The model worked reliably even when images were noisy and was able to detect essential signs in unclear scans. The visualisations showed that the attention layers focused on meaningful areas in the X-rays, making the results easier to understand. Implication: Integrating attention mechanisms, feature selection, and ensemble learning significantly mitigated overfitting and improved generalisation and explainability. The model demonstrated consistent performance across datasets and provided interpretable outputs, supporting its potential for clinical deployment. Conclusion: This study presents a robust and interpretable deep learning framework for musculoskeletal X-ray analysis. By addressing core limitations in existing models, namely, data scarcity, noise sensitivity, and a lack of explainability, the proposed method enhances the reliability of AI-assisted diagnosis in medical imaging.