loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Eddardaa Ben Loussaief ; Mohammed Ayad ; Hatem Rashwan and Domenec Puig

Affiliation: Department of Computer Science and Mathematics of Security, University Rovira I Virgili, Tarragona, Spain

Keyword(s): MRI Segmentation, Adaptive Affinity Module, Kernel Loss, Unseen Generalization.

Abstract: The joint use of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating information from multiple data domains has shown promise in improving model generalizabil-ity and adaptability. However, this approach often demands substantial computational resources, hindering its practicality. In response, knowledge distillation (KD) has garnered attention as a solution. KD involves training lightweight models to emulate the behavior of more resource-intensive models, thereby mitigating the computational burden while maintaining performance. This paper addresses the pressing need to develop a lightweight and generalizable model for medical imaging segmentation that can effectively handle data integration challenges. Our proposed approach introduces a novel relation-based knowledge framework by seamlessly combining adaptive affinity-based and kernel-based distillation. This methodology empowers the student model to accurately replicate the feature representations of the teacher model, facilitating robust performance even in the face of domain shift and data heterogeneity. To validate our approach, we conducted experiments on publicly available multi-source MRI prostate. The results demonstrate a significant enhancement in segmentation performance using lightweight networks. Notably, our method achieves this improvement while reducing both inference time and storage usage. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 216.73.216.202

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Ben Loussaief, E., Ayad, M., Rashwan, H. and Puig, D. (2025). Cross-Site Relational Distillation for Enhanced MRI Segmentation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3; ISSN 2184-4321, SciTePress, pages 508-515. DOI: 10.5220/0013181300003912

@conference{visapp25,
author={Eddardaa {Ben Loussaief} and Mohammed Ayad and Hatem Rashwan and Domenec Puig},
title={Cross-Site Relational Distillation for Enhanced MRI Segmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={508-515},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013181300003912},
isbn={978-989-758-728-3},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Cross-Site Relational Distillation for Enhanced MRI Segmentation
SN - 978-989-758-728-3
IS - 2184-4321
AU - Ben Loussaief, E.
AU - Ayad, M.
AU - Rashwan, H.
AU - Puig, D.
PY - 2025
SP - 508
EP - 515
DO - 10.5220/0013181300003912
PB - SciTePress