Research Assistant Professor
PhD (NEU), ME (HIT), BE (HDU)
Academic Appointments
- Research Assistant Professor, Department of Ophthalmology and Visual Sciences, CUHK
Biography
Dr Jiang obtained his Ph.D. in Biomedical Engineering from Northeast University in 2018. Throughout his studies, he was awarded the National Scholarship and honored as an Academic Star at Northeast University. After completing his doctorate, he worked as the Chief Scientist of AI Algorithms at Beijing ZhenHealth Company for over 3 years. During his tenure, he secured nearly 20 Chinese and international invention patents and developed several commercially viable products, including an ophthalmic multi-disease detection system and a diabetic retinopathy grading system. He also played a key role in helping the company achieve NMPA Class III certification for the “Computer-Aided Diagnosis of Diabetic Retinopathy” software, making it the fifth certified entity in China. Additionally, he was recognized as a Senior AI Engineer by the Chinese Academy of Sciences in 2020. In November 2021, he joined Southern University of Science and Technology as a postdoctoral researcher, focusing on intelligent medical image analysis, eye-tracking-assisted diagnosis, and few-shot learning. To date, he has authored 15 academic papers as the first or corresponding author.
Research Areas
Intelligent Medical Image Analysis: Developing medical-based foundation models for early detection of multiple ophthalmic and systemic diseases.
Eye-Tracking Human-In-The-Loop Assisted Diagnosis: Developing a human-in-the-loop eye-tracking assisted diagnosis system guided by medical prior knowledge.
Trustworthy AI Technology: Few-shot learning, noise-tolerant learning, and interpretable reinforcement learning in real-world clinical settings.
Research Programmes
- Medical-based foundational models for early detection of multiple ophthalmic diseases
- Eye-tracking-guided human-in-the-loop assisted diagnosis system
- Few-shot learning for detecting rare ophthalmic diseases in real clinical scenarios
Representative Publications:
- Jiang H, Gao M, Huang J, Tang C, Zhang X and Liu J. DCAMIL: Eye-tracking guided dual-cross-attention multi-instance learning for refining fundus disease detection. Expert Systems with Applications, 2024.
- Jiang H, Gao M, Liu Z, Tang C, Zhang X, Jiang S, Yuan W and Liu Jiang. GlanceSeg: Real-time microaneurysm lesion segmentation with gaze-map-guided foundation model for early detection of diabetic retinopathy. IEEE Journal of Biomedical and Health Informatics, 2024.
- Jiang H, Hou Y, Miao H, Ye H, Gao M, Li X, Jin R and Liu J. Eye tracking based deep learning analysis for the early detection of diabetic retinopathy: a pilot study. Biomedical Signal Processing and Control, 2023.
- Gao M, Jiang H, Zhu L, Jiang Z, Geng M, Ren Q and Lu Y. Discriminative ensemble meta-learning with co-regularization for rare fundus diseases diagnosis. Medical Image Analysis, 2023.
- Jiang H, Gao M, Li H, Jin R, Miao H and Liu J. Multi-learner based deep meta-learning for few-shot medical image classification. IEEE Journal of Biomedical and Health Informatics, 2022.
- Jiang H, Gao M, Yang K, Zhang D, Ma H and Qian W. (2021, November). Neonatal Fundus Image Registration and Mosaic Using Improved Speeded Up Robust Features Based on Shannon Entropy. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).
- Jiang H, Xu J, Shi R, Yang K, Zhang D, Gao M, Ma H and Qian W. (2020, July). A multi-label deep learning model with interpretable Grad-CAM for diabetic retinopathy classification. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).
- Jiang, H, Yang K, Gao M, Zhang D, Ma H and Qian W. (2019, July). An interpretable ensemble deep learning model for diabetic retinopathy disease classification. In 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC).
- Jiang H, Ma H, Qian W, Gao M and Li Y. An automatic detection system of lung nodule based on multigroup patch-based deep learning network. IEEE journal of biomedical and health informatics, 2017.
