Rate My Professor Amr Ahmed

Ahmed’s research specializes in applications of artificial intelligence and machine learning integrated with computer vision and image/video processing for the analysis, understanding, and interpretation of visual and textual contents. His primary interests include supporting medical diagnosis through liver characterisation, lesion detection, segmentation, and classification; personalised health screening and monitoring; content-based image retrieval; and multimodal data fusion. Further areas encompass video annotation, scene understanding, semantic analysis, video matching and similarity, and handwriting recognition, particularly in Arabic. He leads the Medical Image/Video Analysis Research Group and is a member of the Health Research Institute. Ahmed has supervised several PhD and MSc by research students as well as research assistants. Notable recent publications include “HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology” (2026), “Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters: TOGA” (2026), “Post Hoc Interpretability of Deep Learning Models for Breast Cancer Histopathological Images with Variational Autoencoders” (2025), and “A Neurophysiological Model based on Resting-State EEG Functional Connectivity Features for Assessing Semantic Long-term Memory Performance” (2024). He is a member of the British Computer Society, the International Association of Engineers, and the IEEE Computer Society.