About Me
I am a Machine Learning Researcher with a PhD in Electronic Science and Technology from Hebei University of Technology, Tianjin, China, where I also earned my Master’s degree in Communication and Information Systems. Dur…
I am a Machine Learning Researcher with a PhD in Electronic Science and Technology from Hebei University of Technology, Tianjin, China, where I also earned my Master’s degree in Communication and Information Systems. During my doctoral studies, I was honored with the Outstanding International Graduate Award (2026), recognizing me as one of the top international students at Hebei University of Technology for my academic and research achievements. My research interests include Artificial Intelligence, Machine Learning, Computer Vision, Pattern Recognition, Image Processing, Explainable AI, and Medical Image Analysis.
Experience
PhD Researcher — Medical Image Analysis
<p>Conducted research in deep learning, computer vision, and medical image analysis, with a primary focus on retinal fundus image analysis. Developed and evaluated deep learning models for automated retinal disease detection and classification, incorporating image preprocessing, feature extraction, and model optimization techniques. Investigated convolutional neural networks, transfer learning, and advanced image processing methods to improve diagnostic accuracy, computational efficiency, and model reliability in medical imaging applications.</p>
Research Intern — Medical Imaging
<p>Assisted in the analysis of retinal imaging data acquired using Spectralis Optical Coherence Tomography (OCT), including reviewing OCT scans, retinal thickness maps, and retinal images. Supported the examination of retinal structures, assessment of retinal layer thickness, identification of imaging abnormalities, and interpretation of imaging findings to support clinical research and image analysis.</p>
IT Intern
<p>Designed and implemented a prototype web-based employee management platform to support the digital management of employee information and administrative records. </p>
PROJECTS
Towards Efficient Glaucoma Screening with Convolution-Involution
<p>Mouhafid M, Zhou Y, Shan C, & Xiao Z. (2025). Towards Efficient Glaucoma Screening with Modular Convolution-Involution Cascade Architecture. PeerJ Computer Science, 11: e2844. (Q2, SCI-indexed) DOI: 10.7717/peerj-cs.2844</p><p></p><p>This study introduces the Modular Convolution-Involution Cascade Network (MCICNet), an innovative CNN architecture designed to address these challenges in the context of glaucoma</p><p>detection. The model employs a combination of convolution and involution operations in a cascade structure, allowing for the effective capture of inter-channel dependencies within the feature extraction process. Furthermore, the classification phase integrates light gradient boosting machine (LightGBM) as a replacement for traditional FC layers, offering enhanced precision and generalization while reducing model complexity. Extensive experiments conducted on the LAG and ACRIMA datasets demonstrate that MCICNet achieves significant improvements compared to existing CNN and transformer-based models. The model attained a classification accuracy of 95.6% on the LAG dataset and 96.2% on ACRIMA, outperforming nine widely used CNN architectures (AlexNet, MobileNetV2, SqueezeNet, ResNet18, GoogLeNet, DenseNet121, EfficientNetB0, ShuffleNet, and VGG16), as well as three transformer-based models (ViT, MaxViT, and SwinT). Additionally, MCICNet showed superior performance over its variant without involution (MCICNetNoInvolution). With only 0.9 million parameters, MCICNet demonstrates substantial efficiency in resource utilization alongside its high learning capability, establishing it as an advanced and computationally efficient solution for glaucoma detection.</p><p></p>