Publications

NC-Reg : Neural Cortical Maps for Rigid Registration

Published in IEEE 23rd International Symposium on Biomedical Imaging (ISBI), 2026

This work highlights the potential of neural representations to streamline registration workflows and extend to broader neuroimaging applications.

Recommended citation: Vati, Ines, Pierrick Bourgeat, Rodrigo Santa Cruz, Vincent Dore, Olivier Salvado, Clinton Fookes, and Léo Lebrat. "NC-REG: Neural Cortical Maps for Rigid Registration." In 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI), pp. 1-6. IEEE, 2026.
Download Paper | Download Slides

Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI–MICCAI 2024 Challenge Results

Published in arXiv, 2025

Despite their clinical significance, automatic enlarged PVS (EPVS) segmentation remains challenging due to their small size, variable morphology, similarity with other pathological features, and limited annotated datasets. This paper presents the EPVS Challenge organized at MICCAI 2024, which aims to advance the development of automated algorithms for EPVS segmentation across multi-site data.

Recommended citation: Wu, Y., Zhang, Y., Dong, Z., Ji, F., Tan, A. S., Tan, G., ... & Zhou, J. H. (2025). Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI--MICCAI 2024 Challenge Results. arXiv preprint arXiv:2512.18197.
Download Paper

Advanced Deep Learning Models Enhance Piriform Cortex Segmentation for Epilepsy Surgery

Published in ISMRM & ISMRT, 2025

The piriform cortex (PC) is emerging as an important structure for surgery for drug-resistant mesial temporal lobe epilepsy, where resection improves postsurgical outcomes. Current segmentation methods remain suboptimal, necessitating advanced solutions.

Recommended citation: Javier Antonio Urriola Yaksic, Leo Lebrat, Hang Min, Alex Pagnozzi, Ying Xia, Ines Vati, Charles X Li, Senali Weeratunga, Merran Courney, Jurgen Fripp, Matthew Gutman, Andrew Neal, Ben Sinclair, Terrence J O Brien, DanaKai Bradford. (ISMRM 2025) Advanced Deep Learning Models Enhance Piriform Cortex Segmentation for Epilepsy Surgery.
Download Paper

MICCAI 2024 Enlarged Perivascular Spaces (EPVS) Segmentation Challenge

Published in MICCAI, 2024

Segmenting enlarged perivascular spaces (EPVS) in brain MRIs is particularly challenging as they can vary in size, shape, and location, making them difficult to identify and segment accurately. However, EPVS is important as it is a key marker and early indicator of cerebral vascular diseases.
The challenge provided a limited dataset with only 100 fully annotated training scans, 50 validation scans, and 70 scans for independent testing, sourced from multiple sites and scanners to reflect real-world clinical and research conditions (with varying cognitive profiles). The dataset includes T1-weighted, T2-weighted and FLAIR.