Associate Professor
Khalifa University
Office Address: Khalifa University, P.O. Box 127788, Abu Dhabi, United Arab Emirates
Phone: +971 2 312 4780
Email: aamir.raja@ku.ac.ae
Recent peer-reviewed research in photon-counting CT and medical imaging physics.
Loading publications...
Graduate researchers supervised by Dr. Aamir Raja — current PhD students at Khalifa University and completed thesis students.
Loading students...
Conference posters, awards, lab milestones, and video highlights from the research group.
Developing a machine learning-based smart radiation monitoring tool that connects with CT scanners and/or hospital PACS servers to automatically collect dose data into a central database for national-level comparison.
Combining nanoparticle technology with spectral CT and task-based image quality assessment to identify non-toxic, high-atomic-number contrast elements using clinical dual-energy CT and photon-counting CT systems.
Developing machine learning image denoising and correction techniques for metal-related artefacts in photon-counting CT, addressing beam hardening, photon starvation, and partial volume effects near implants.
Building deep learning post-reconstruction material decomposition algorithms for photon-counting CT to identify and quantify multiple materials indistinguishable in conventional CT.
Quality Assessment Framework for Photon Counting CT
QAF is a web-based framework designed to support image quality assessment for photon-counting detector (PCD) computed tomography in both clinical and research settings. The framework addresses core analytical requirements by providing standardized, reproducible, and scalable evaluation tools. It is designed and developed to facilitate integration into clinical workflows while also supporting advanced research applications. QAF offers comprehensive functionality for systematic image quality evaluation across a wide range of scanner configurations and acquisition protocols.
QAF web platform alongside spectral photon-counting CT systems at Khalifa University — including the MARS microlab (5×120) and a bench-top system for 2D and 3D imaging.
QAF provides a web-based, protocol-agnostic platform that consolidates SNR, NPS, MTF, and material-identification analyses into a single standardized environment for spectral photon-counting and conventional CT.
Through harmonized ROI definitions, automated processing pipelines, and structured reporting, QAF replaces fragmented in-house scripts with a scalable framework that enables cross-scanner, cross-protocol, and cross-site comparability.
Phantom-based evaluations demonstrate how QAF quantitatively characterizes trade-offs between spatial resolution, noise properties, and acquisition settings, supporting objective, task-specific protocol refinement.
By streamlining acceptance testing, routine quality assurance, and longitudinal system monitoring, QAF facilitates the transition of multi-energy CT from experimental research to standardized clinical implementation.
Future releases will extend the framework with integrated material-decomposition validation and metal artefact reduction (MAR) assessment modules, enabling end-to-end evaluation of spectral accuracy, correction algorithms, and quantitative performance.