Dr Iris Allajbeu

I’m an academic breast radiologist, currently serving as a Senior Clinical Research Associate and Honorary Consultant Radiologist in the Department of Radiology, at the University of Cambridge. With over 15 years of clinical, academic, and research experience, I specialise in the early detection of breast cancer using advanced imaging techniques, including contrast-enhanced mammography (CEM), abbreviated MRI, and automated breast ultrasound (ABUS), with a particular focus on AI and radiomics. My overarching goal is to develop more accurate and personalized breast screening, especially for women with dense breast tissue. 
 
In addition to my clinical and research roles, I serve as the Patient and Public Involvement and Engagement (PPIE) Lead in Radiology, promoting active involvement of patients and the public in the design and delivery of clinical research. I also supervise postgraduate and medical students, as well as clinical and research fellows, across multiple ongoing research projects 

Internationally, I am the President and founder of the Albanian Society of Breast Imaging (ALSOBI), Vice President of the Albanian Association of Radiology (AAR), and board member of the European Society of Breast Imaging (EUSOBI) International Relations Committee and Inequities Taskforce. I regularly lecture at major international radiology conferences such as ECR, ESOR, and EUSOBI and lead workshops and masterclasses on breast imaging. I’m also actively involved in curriculum development at the Western Balkans University Medical School, where I contribute as a Honorary Clinical Lecturer and Radiology curriculum co-Lead. 

My research portfolio includes serving as Co-Investigator on major multicenter clinical trials such as the Breast-Risk-Adaptive-Imaging-for-Density (BRAID) trial, a UK-wide study across 10 centers investigating the feasibility of supplemental screening for women with dense breasts, recently published in The Lancet. I am also Co-Investigator on the SYNERGIA trial, which integrates multi-modal data across breast cancer molecular subtypes to develop predictive models for treatment response, early relapse, and survival, and to identify early indicators of future metastatic recurrence. In addition, I serve as Principal Investigator on studies focused on evaluating quantitative imaging techniques and AI tools to enhance early detection of breast cancer through supplemental screening.   

I contribute actively to academic publishing as a peer reviewer and editorial board member for journals including European Radiology, Frontiers in Oncology, Insights into Imaging, Cancer Imaging, and Nature Scientific Reports. I have also authored and co-authored several books on cardiac and breast imaging.

Project/study information 

I currently lead projects on improving CEM diagnostic performance through quantitative methods and evaluating standalone AI performance on ABUS using data from the BRAID trial. I am particularly interested in large data platforms and developing new AI algorithms/tools for early detection and personalized treatment. 

Selected Recent Publications 

• Gilbert FJ, Payne NR, Allajbeu I, et al. Comparison of supplemental imaging techniques for women with dense breasts: the BRAID (Breast Screening Risk-Adapted Imaging for Density) randomised controlled trial. Lancet. 2024;403(10444):2000–2009. https://doi.org/10.1016/S0140-6736(24)00924-3
• Allajbeu I, Nanaa M, Manavaki R, et al. Improving the diagnostic performance of contrast-enhanced mammography through lesion conspicuity and enhancement quantification. Eur Radiol. 2025. https://doi.org/10.1007/s00330-025-11501-8
• Allajbeu I, Morris K, Nanaa M, et al. Introduction of automated breast ultrasound as an additional screening tool for dense breasts in the UK: a practical approach from the BRAID trial. Clin Radiol. 2024;79(5):e641–e650. https://doi.org/10.1016/j.crad.2023.11.029
• Nanaa M, Gupta VO, Hickman SE, Allajbeu I, et al. Accuracy of an artificial intelligence system for interval breast cancer detection at screening mammography. Radiology. 2024;312(2):e232303. https://doi.org/10.1148/radiol.232303
• Buddenkotte T, Rundo L, Woitek R, Allajbeu I, et al. Deep learning-based segmentation of multisite disease in ovarian cancer. Eur Radiol Exp. 2023;7(1):77. https://doi.org/10.1186/s41747-023-00413-1