Gabriele Lozupone

Postdoctoral Research Fellow in Artificial Intelligence

gabriele.lozupone@unicas.it | University of Cassino and Southern Lazio, Italy

Education

PhD in Artificial Intelligence
University of Cassino and Southern Lazio | 2026

Completed the doctoral programme and defended a thesis on artificial intelligence methods for neurodegenerative disease analysis from 3D medical imaging.

Master's Degree in Computer Engineering
University of Cassino and Southern Lazio | 2023

Graduated with highest honors (110/110 cum laude)

Bachelor's Degree in Computer and Telecommunications Engineering
University of Cassino and Southern Lazio | 2020

Final grade: 107/110

Research Experience

Postdoctoral Research Fellow in Artificial Intelligence
University of Cassino and Southern Lazio | 2026–present

Research on neurodegenerative disease progression from longitudinal 3D MRI using foundation models, generative AI, and representation learning; including large-scale experimentation and model validation for medical research.

Visiting Researcher
Radboud University Medical Center | 2025

Research stay at Nijmegen, Netherlands, focused on diffusion models for unsupervised representation learning in medical imaging.

Research Conference Speaker
International Conference on Pattern Recognition (ICPR) | 2024

Presented research on Alzheimer's diagnosis using handwriting analysis with Transformers and CNNs.

Skills

AI & Machine Learning: Computer Vision, Diffusion Models, Foundation Models, Transformers, Deep Learning, Explainable AI

Programming: Python, C#, JavaScript, HTML/CSS, SQL

Frameworks & Tools: PyTorch, Flutter, Firebase, SQL Server, Git

Languages: Italian (Native), English (Professional)

Publications

This CV includes a selection of publications. For a complete list, please visit my website.

  1. Lozupone, G., Bria, A., Fontanella, F., Meijer, F.J.A., De Stefano, C., Huisman, H. (2026). Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging. Medical Image Analysis, 103932.
  2. Lozupone, G., Nardone, E., Pace, C.D., D'Alessandro, T. (2025). Transformers and CNNs in Neurodiagnostics: Handwriting Analysis for Alzheimer's Diagnosis. International Conference on Pattern Recognition.
  3. Lozupone, G., Bria, A., Fontanella, F., Meijer, F.J.A., De Stefano, C. (2024). AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis using 2D CNNs on 3D MRI brain scans. Computer Methods and Programs in Biomedicine (Under submission).

Projects

LDAE: Latent Diffusion Autoencoder

A novel encoder-decoder diffusion-based framework for efficient unsupervised learning in medical imaging.

AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis

An innovative method for Alzheimer's disease diagnosis using 3D MRI with enhanced explainability.

DiffusionModels-Theory2Code

A comprehensive educational resource covering both theoretical foundations and practical implementations of diffusion models in PyTorch.