Youness Mellak
I am a postdoctoral researcher at LaTIM, Université de Bretagne Occidentale in Brest, France. My work lies at the intersection of medical imaging physics, inverse problems, and machine learning.
I am particularly interested in scalable generative priors for three-dimensional reconstruction, direct PET reconstruction from detector measurements, positron-range correction, and physics-informed learning. My current research explores diffusion and flow models for PET, CT, and MRI at clinical volume sizes.
I completed my Ph.D. at LaTIM in 2025 with the thesis Deep learning approaches for PET imaging: three-gamma PET, positron range correction and direct reconstruction.
Code and material related to my work can be found on the publications page and on GitHub. The best way to reach me is by email.
experience
Generative modeling and learned priors for large-scale 3D inverse problems, including low-dose PET, sparse-view CT, and undersampled MRI.
Direct PET reconstruction, positron-range correction, Monte Carlo surrogate modeling, and direct three-gamma PET reconstruction.
Learning-based analysis of volumetric OCT data, including severity grading, explainability, and three-dimensional instance segmentation.
news
| Jul 18, 2026 | 3D Latent Implicit Diffusion for Scalable Volume Generation was accepted as a Lightning Talk and Poster at the 2026 IEEE NSS/MIC/RTSD conference. |
|---|---|
| Jul 18, 2026 | Frozen Stable Diffusion VAE as a Slice-Wise Encoder for Scalable 3-D Medical Image Generation was accepted for a Poster presentation at the 2026 IEEE NSS/MIC/RTSD conference. |
selected publications
- Continuous 3-D Latent Diffusion for Medical Generation and ReconstructionManuscript under review, 2026
@article{mellak2026continuous3d, title = {Continuous 3-D Latent Diffusion for Medical Generation and Reconstruction}, author = {Mellak, Youness and De Paepe, Antoine and Visvikis, Dimitris and Bousse, Alexandre}, journal = {Manuscript under review}, year = {2026}, } - Dual-Input Dynamic Convolution for Positron Range Correction in PET Image ReconstructionIEEE Transactions on Radiation and Plasma Medical Sciences, 2025
@article{mellak2025ddconv, title = {Dual-Input Dynamic Convolution for Positron Range Correction in PET Image Reconstruction}, author = {Mellak, Youness and Bousse, Alexandre and Merlin, Thibaut and {\'E}mond, {\'E}lise and Hakulinen, Mikko and Visvikis, Dimitris}, journal = {IEEE Transactions on Radiation and Plasma Medical Sciences}, year = {2025}, doi = {10.1109/TRPMS.2025.3647264}, } - Direct3γ: A Pipeline for Direct Three-Gamma PET Image ReconstructionIEEE Transactions on Radiation and Plasma Medical Sciences, 2025
@article{mellak2025direct3gamma, title = {Direct3γ: A Pipeline for Direct Three-Gamma PET Image Reconstruction}, author = {Mellak, Youness and Bousse, Alexandre and Merlin, Thibaut and Giovagnoli, Debora and Visvikis, Dimitris}, journal = {IEEE Transactions on Radiation and Plasma Medical Sciences}, year = {2025}, doi = {10.1109/TRPMS.2025.3577810}, }