A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Faanes, Mathilde Gajda, Bouget, David, Jakola, Asgeir S., Smith, Timothy R., Kavouridis, Vasileios K., Latini, Francesco, Jensdottir, Margret, Milos, Peter, Redebrandt, Henrietta Nittby, Sjöberg, Rickard L., Mahesparan, Rupavathana, Pedersen, Lars Kjelsberg, Solheim, Ole, Reinertsen, Ingerid
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915686474842112
author Faanes, Mathilde Gajda
Bouget, David
Jakola, Asgeir S.
Smith, Timothy R.
Kavouridis, Vasileios K.
Latini, Francesco
Jensdottir, Margret
Milos, Peter
Redebrandt, Henrietta Nittby
Sjöberg, Rickard L.
Mahesparan, Rupavathana
Pedersen, Lars Kjelsberg
Solheim, Ole
Reinertsen, Ingerid
author_facet Faanes, Mathilde Gajda
Bouget, David
Jakola, Asgeir S.
Smith, Timothy R.
Kavouridis, Vasileios K.
Latini, Francesco
Jensdottir, Margret
Milos, Peter
Redebrandt, Henrietta Nittby
Sjöberg, Rickard L.
Mahesparan, Rupavathana
Pedersen, Lars Kjelsberg
Solheim, Ole
Reinertsen, Ingerid
contents T2-weighted fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) scans are important for diagnosis, treatment planning and monitoring of brain tumors. Depending on the brain tumor type, the FLAIR hyperintensity volume is an important measure to asses the tumor volume or surrounding edema, and an automatic segmentation of this would be useful in the clinic. In this study, around 5000 FLAIR images of various tumors types and acquisition time points from different centers were used to train a unified FLAIR hyperintensity segmentation model using an Attention U-Net architecture. The performance was compared against dataset specific models, and was validated on different tumor types, acquisition time points and against BraTS. The unified model achieved an average Dice score of 88.65\% for pre-operative meningiomas, 80.08% for pre-operative metastasis, 90.92% for pre-operative and 84.60% for post-operative gliomas from BraTS, and 84.47% for pre-operative and 61.27\% for post-operative lower grade gliomas. In addition, the results showed that the unified model achieved comparable segmentation performance to the dataset specific models on their respective datasets, and enables generalization across tumor types and acquisition time points, which facilitates the deployment in a clinical setting. The model is integrated into Raidionics, an open-source software for CNS tumor analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points
Faanes, Mathilde Gajda
Bouget, David
Jakola, Asgeir S.
Smith, Timothy R.
Kavouridis, Vasileios K.
Latini, Francesco
Jensdottir, Margret
Milos, Peter
Redebrandt, Henrietta Nittby
Sjöberg, Rickard L.
Mahesparan, Rupavathana
Pedersen, Lars Kjelsberg
Solheim, Ole
Reinertsen, Ingerid
Computer Vision and Pattern Recognition
Artificial Intelligence
T2-weighted fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) scans are important for diagnosis, treatment planning and monitoring of brain tumors. Depending on the brain tumor type, the FLAIR hyperintensity volume is an important measure to asses the tumor volume or surrounding edema, and an automatic segmentation of this would be useful in the clinic. In this study, around 5000 FLAIR images of various tumors types and acquisition time points from different centers were used to train a unified FLAIR hyperintensity segmentation model using an Attention U-Net architecture. The performance was compared against dataset specific models, and was validated on different tumor types, acquisition time points and against BraTS. The unified model achieved an average Dice score of 88.65\% for pre-operative meningiomas, 80.08% for pre-operative metastasis, 90.92% for pre-operative and 84.60% for post-operative gliomas from BraTS, and 84.47% for pre-operative and 61.27\% for post-operative lower grade gliomas. In addition, the results showed that the unified model achieved comparable segmentation performance to the dataset specific models on their respective datasets, and enables generalization across tumor types and acquisition time points, which facilitates the deployment in a clinical setting. The model is integrated into Raidionics, an open-source software for CNS tumor analysis.
title A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.17566