About Me
I am passionate about advancing medical AI technologies that can improve patient care and clinical decision-making. My journey in medical imaging began during my undergraduate studies at Bogazici University, where I worked on Alzheimer's disease detection using brain connectomes in the VAVlab under the guidance of Prof. Burak Acar.
During my research career, I have had the privilege of collaborating with leading experts in the field. At the Athinoula A. Martinos Center for Biomedical Imaging, I worked with Prof. Berkin Bilgic and Prof. Qiyuan Tian on cutting-edge diffusion MRI techniques and deep learning applications. This experience deepened my understanding of the intersection between advanced imaging technologies and artificial intelligence.
I also completed a research internship with the COMPAI Lab at TUM, working under the supervision of Prof. Julia Schnabel, Dr. Veronika Zimmer, and Dr. Cosmin Bercea. This collaboration focused on unsupervised representation learning for Alzheimer's disease, resulting in innovative approaches to medical image analysis.
Currently, I am pursuing my PhD at King's College London under the supervision of Dr. Jorge Cardoso, and Prof. Sebastien Ourselin, where I am developing AI-based smart orchestration systems for medical imaging workflows. My research aims to create intelligent systems that can automatically optimize imaging protocols, enhance diagnostic accuracy across various medical imaging modalities.
Research Interests
Education
PhD in Medical AI
King's College London
2024-2028MSc in Biomedical Computing
Technical University of Munich (TUM)
2022-2024BSc in Electrical & Electronics Engineering
Bogazici University
2017-2022Recent Updates
-
July 2025MR-CLIP accepted at MICCAI MLMI Workshop 2025
-
April 2025Presented ZS-PRIME at ISMRM 2025
-
October 2024Started my PhD at King's College London
-
October 2024Finished my Master's Degree in Biomedical Computing at TUM!
-
October 2024Received Best Paper Award for our work on Unsupervised Alzheimer's Disease Analysis in MICCAI EMERGE Workshop!
-
September 2022Started at TUM for my Master's Degree in Biomedical Computing
-
September 2022Started working as a Machine Learning Intern at deepc, working on benchmarking radiology AI, detection of body part with deep learning and NLP solutions
-
June 2022Graduated from Bogazici University with a BSc degree in Electrical and Electronics Engineering
-
May 2022Presented my first abstract in ISMRM 2022
Research Projects
MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
MICCAI MLMI Workshop 2025 - MR-CLIP is a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations without requiring manual labels. Trained on diverse clinical data, it enables robust, anatomy-invariant representations for tasks like cross-modal retrieval and contrast classification, even in the presence of incomplete or noisy metadata.
Zero-Shot Self-Supervised Distortion-Free Diffusion MRI Reconstruction
ISMRM 2025 - ZS-PRIME combines advanced field map estimation (PRIME) with zero-shot self-supervised training, achieving distortion-free, high-resolution multi-shot diffusion MRI from undersampled data. This obviates the dependency on external training datasets, setting a new benchmark for efficient, high-fidelity diffusion MRI.
Unsupervised Analysis of Alzheimer's Disease Signatures using 3D Deformable Autoencoders
MICCAI EMERGE Workshop 2024 (Best Paper Award) - We present MORPHADE (Morphological Autoencoders for Alzheimer's Disease Detection), a novel unsupervised learning approach which uses deformations to allow the analysis of 3D T1-weighted brain images. To the best of our knowledge, this is the first use of deformations with deep unsupervised learning to not only detect, but also localize and assess the severity of structural changes in the brain due to AD.
Simulation of acquisition shifts in T2 Flair MR images to stress test AI segmentation networks
Journal of Medical Imaging, 2024 - This work's goal is to provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2w FLAIR MRI protocols.
Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies
ISMRM 2023, NeuroImage: Clinical, 2023 - Participated in QUAD Challenge in MICCAI 2022 and got the 4th place with combination of methods DUnet and deepDTI.
DUnet: Quantifying the uncertainty of neural networks using Monte Carlo dropout for safer and more accurate deep learning based quantitative MRI
ISMRM 2022 - Dropout is conventionally used during the training phase as regularization method and for quantifying uncertainty in deep learning. We propose to use dropout during training as well as inference steps, and average multiple predictions to improve the accuracy, while reducing and quantifying the uncertainty.