Segmentation of Intraoperative Glioblastoma Hyperspectral Images Using Self-Supervised U-Net++

Marco Gazzoni, Marco La Salvia, Emanuele Torti, Elisa Marenzi, Raquel Leon, Samuel Ortega, Beatriz Martinez, Himar Fabelo, Himar Fabelo, Gustavo Callicò, Francesco Leporati

2025

Abstract

Brain tumour resection yields many challenges for neurosurgeons and even though histopathological analysis can help to complete tumour elimination, it is not feasible due to the extent of time and tissue demand for margin inspection. This paper presents a novel attention-based self-supervised methodology to improve current research on medical hyperspectral imaging as a tool for computer-aided diagnosis. We designed a novel architecture comprising the U-Net++ and the attention mechanism on the spectral domain, trained in a self-supervised framework to exploit contrastive learning capabilities and overcome dataset size problems arising in medical scenarios. We operated fifteen hyperspectral images from the publicly available HELICoiD dataset. Enhanced by extensive data augmentation, transfer-learning and self-supervision, we measured accuracy, specificity and recall values above 90% in the automatic end-to-end segmentation of intraoperative glioblastoma hyperspectral images. We evaluated our outcomes with the ground truths produced by the HELICoiD project, obtaining results that are comparable concerning the gold-standard procedure.

Paper Citation

in Harvard Style

Gazzoni M., La Salvia M., Torti E., Marenzi E., Leon R., Ortega S., Martinez B., Fabelo H., Callicò G. and Leporati F. (2025). Segmentation of Intraoperative Glioblastoma Hyperspectral Images Using Self-Supervised U-Net++. 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, SciTePress, pages 633-639. DOI: 10.5220/0013245900003912

in Bibtex Style

@conference{visapp25,
author={Marco Gazzoni and Marco La Salvia and Emanuele Torti and Elisa Marenzi and Raquel Leon and Samuel Ortega and Beatriz Martinez and Himar Fabelo and Gustavo Callicò and Francesco Leporati},
title={Segmentation of Intraoperative Glioblastoma Hyperspectral Images Using Self-Supervised U-Net++},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={633-639},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013245900003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Segmentation of Intraoperative Glioblastoma Hyperspectral Images Using Self-Supervised U-Net++
SN - 978-989-758-728-3
AU - Gazzoni M.
AU - La Salvia M.
AU - Torti E.
AU - Marenzi E.
AU - Leon R.
AU - Ortega S.
AU - Martinez B.
AU - Fabelo H.
AU - Callicò G.
AU - Leporati F.
PY - 2025
SP - 633
EP - 639
DO - 10.5220/0013245900003912
PB - SciTePress