Assistant Professor
8 years of experience
Dr. Ali Haider Khan (Senior Member, IEEE) is an Assistant Professor at Beijing University of Technology (BJUT), specializing in medical image analysis, artificial intelligence, and healthcare informatics. With over eight years of academic and applied research experience, he has extensive hands-on expertise in maintaining, troubleshooting, and integrating medical imaging systems such as MRI, CT, and PET scanners with AI-driven diagnostic workflows.
Dr. Khan is proficient in deploying and managing high-performance computing clusters, GPU servers (NVIDIA DGX, CUDA-enabled systems), and deep learning frameworks (TensorFlow, PyTorch, MONAI) for image preprocessing, segmentation, registration, and classification. He has developed AI-based pipelines for cross-modality image registration, radiomics feature extraction, and disease stratification, ensuring reproducibility, data security, and clinical applicability.
He has led multiple training sessions, workshops, and seminars for students, clinicians, and researchers, creating technical manuals and best-practice guidelines for medical imaging and computational analysis. His work bridges scientific research and practical implementation, emphasizing hands-on expertise in both equipment handling and AI model deployment.
Dr. Khan has contributed over 45 publications in high-impact journals and conferences, focusing on interpretable AI, generative models for medical imaging, and multimodal healthcare analytics. His research continues to advance interdisciplinary AI applications in medical diagnostics and intelligent healthcare systems.
Advanced medical imaging modalities: MRI, CT, PET, and Ultrasound for diagnostic and research applications.
Image preprocessing and enhancement systems (e.g., ITK-SNAP, 3D Slicer, MATLAB Image Processing Toolbox).
AI-driven segmentation, registration, and classification pipelines using Deep Learning (PyTorch, TensorFlow, MONAI).
Cross-modality image registration and fusion techniques for multimodal medical datasets.
Radiomics feature extraction and model integration for disease stratification and prognosis.
Synthetic data generation and augmentation using Generative Adversarial Networks (GANs) for limited clinical datasets.
Workflow automation on high-performance computing (HPC) clusters and GPU-based systems (NVIDIA DGX, CUDA).
https://scholar.google.com/citations?user=k5ZHz1oAAAAJ&hl=en https://www.scopus.com/authid/detail.uri?authorId=57212034479 https://loop.frontiersin.org/people/2865540/overview
Register as an Expert
LOGIN
