Fatih Aksu

Full profile and recent publications of Fatih Aksu.

Fatih Aksu

Researcher

Fatih Aksu

Postdoctoral Researcher @ Università Campus Bio-Medico di Roma

Fatih Aksu is a Postdoctoral Researcher at Università Campus Bio-Medico di Roma (UCBM). He earned his PhD in Artificial Intelligence (Health and Life Sciences) from UCBM, where his doctoral work centered on advancing multimodal deep learning through intermediate fusion strategies and designing resilient AI frameworks that integrate federated learning with triplet networks. He received his B.Sc. and M.Sc. degrees in Electrical and Electronics Engineering from Middle East Technical University. His research focuses on deep learning methods applied to biomedical domains, with a particular emphasis on the diagnosis and prognosis of lung cancer. Methodologically, his work spans multimodal deep learning, synthetic image generation, 3D medical vision foundation models, digital pathology analysis using whole slide images, and resilient AI frameworks.

Multimodal Learning Deep Learning Computer Vision Generative AI

Recent Publications

  1. [18F]FDG PET/CT Radiomics for Predicting Pathological Risk Subtypes of Thymic Epithelial Tumors: A Bicentric Study
    2026
  2. Virtual Scanning for NSCLC Histology: Investigating the Discriminatory Power of Synthetic PET
    arXiv preprint arXiv:2605.02746, 2026
  3. Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC
    arXiv preprint arXiv:2603.15100, 2026
  4. Transformer-Based Analysis for Detecting Pulmonary Nodules in CT Scans: Preliminary Results
    2025
  5. Next-Gen Health: from Multimodal AI to Foundation Models
    2025
  6. NSCLC histological subtype classification from CT scans using generalist 3D medical foundation models
    2025
  7. Multi-stage intermediate fusion for multimodal learning to classify non-small cell lung cancer subtypes from CT and PET
    2025
  8. Enhancing NSCLC Histological Subtype Classification: A Federated Learning Approach Using Triplet Loss
    2025
  9. A systematic review of intermediate fusion in multimodal deep learning for biomedical applications
    2025
  10. Towards AI-driven Next Generation Personalized Healthcare and Well-being
    2024