Clément Veyer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Clément Veyer has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Anne Humeau-Heurtier
Univ Angers, LARIS, SFR MATHSTIC, F-49000, Angers, France
2 shared publications - Jean-Baptiste Fasquel
Univ Angers, LARIS SFR MATHSTIC,Angers,France,F-49000
2 shared publications - Lucie Hertz-Pannier
UNIACT/Neurospin/JOLIOT/DRF/CEA-Saclay, U1141 NeuroDiderot/Inserm, CEA Paris University,France
2 shared publications - Mickael Dinomais
Univ Angers, LARIS, SFR MATHSTIC, Mdecine physique et de radaptation, CHU,Angers,France
2 shared publications - Patty Coupeau
Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France
2 shared publications Dmytro Polozenko
Univ Angers, LARIS SFR MATHSTIC,Angers,France,F-49000
1 shared publication
Latest Publications
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-View Graph Approach for Morphometry-Aware Semantic Image Segmentation
This paper extends the use of graph neural networks (GNN) to improve semantic segmentation with limited input data. After segmenting structures using a convolutional neural network (CNN), we propose to model the spatial relationships between the segmented regions through a graph. Then, we refine the suboptimal segmentation with a node classification. We consider a multi-view approach, one view regarding the probabilistic belonging predicted by the CNN, and the second view regarding regions' morphometry. This leads to a morphometryaware GNN. Two strategies are explored: a late-fusion one, consisting of two parallel GNNs, where each one receives a different view of the graph representing the segmented structures as input, and an early-fusion one, where node features are just a concatenation of the views. Experiments are conducted on both a synthetic and a medical dataset, including healthy and injured children's brain MRIs. Our method demonstrates superior performance on both datasets compared to the baseline, achieving a gain of 7% in accuracy compared to previous work on the synthetic dataset, a gain of 25% in Hausdorff distance on the medical dataset for healthy children, and a 15% gain for injured ones. When training data is limited to 12% of the whole training subset, we measure a gain of 64% for healthy children and of 26% for injured ones, emphasizing the robustness of the method integrating morphometric information in a multi-view manner.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Multi-View Graph Approach for Morphometry-Aware Semantic Image Segmentation
This paper extends the use of graph neural networks (GNN) to improve semantic segmentation with limited input data. After segmenting structures using a convolutional neural network (CNN), we propose to model the spatial relationships between the segmented regions through a graph. Then, we refine the suboptimal segmentation with a node classification. We consider a multi-view approach, one view regarding the probabilistic belonging predicted by the CNN, and the second view regarding regions' morphometry. This leads to a morphometryaware GNN. Two strategies are explored: a late-fusion one, consisting of two parallel GNNs, where each one receives a different view of the graph representing the segmented structures as input, and an early-fusion one, where node features are just a concatenation of the views. Experiments are conducted on both a synthetic and a medical dataset, including healthy and injured children's brain MRIs. Our method demonstrates superior performance on both datasets compared to the baseline, achieving a gain of 7% in accuracy compared to previous work on the synthetic dataset, a gain of 25% in Hausdorff distance on the medical dataset for healthy children, and a 15% gain for injured ones. When training data is limited to 12% of the whole training subset, we measure a gain of 64% for healthy children and of 26% for injured ones, emphasizing the robustness of the method integrating morphometric information in a multi-view manner.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multi-View Dispersion Entropy on Graphs: Application to the Detection of Cerebral Palsy After Neonatal Stroke
In this work, we present a novel method for quantifying irregularity in multi-view graph signals. This approach leverages the concept of dispersion entropy to measure disorder across multiple node-attribute views, while maintaining a fixed graph topology. Moreover, the ensemble dispersion entropy on graphs is proposed to obtain robust results. When applied to graphs computed from brain MRI of children (children with or without cerebral palsy), the results show a higher dispersion entropy for graphs of brain structures from pathological children. This emphasizes the disorder present in the brain of subjects suffering from cerebral palsy. Compared to recently obtained results using graph neural networks, the proposed hand-crafted approach has the advantage of being explicit and not relying on a training dataset. This work lays the foundation for a broader use of dispersion entropy in multi-view graph analysis, with promising applications in neuroscience.
- 13 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Multi-View Dispersion Entropy on Graphs: Application to the Detection of Cerebral Palsy After Neonatal Stroke
In this work, we present a novel method for quantifying irregularity in multi-view graph signals. This approach leverages the concept of dispersion entropy to measure disorder across multiple node-attribute views, while maintaining a fixed graph topology. Moreover, the ensemble dispersion entropy on graphs is proposed to obtain robust results. When applied to graphs computed from brain MRI of children (children with or without cerebral palsy), the results show a higher dispersion entropy for graphs of brain structures from pathological children. This emphasizes the disorder present in the brain of subjects suffering from cerebral palsy. Compared to recently obtained results using graph neural networks, the proposed hand-crafted approach has the advantage of being explicit and not relying on a training dataset. This work lays the foundation for a broader use of dispersion entropy in multi-view graph analysis, with promising applications in neuroscience.