Supervised machine learning based classification scheme to segment the brainstem on MRI in multicenter brain tumor treatment context

J. Dolz (1) , Anne Laprie (2) , Soléakhéna Ken (2) , Henri-Arthur Leroy (1, 3) , Nicolas Reyns (1, 3) , Laurent Massoptier (3) , Maximilien Vermandel (1, 3)

1 ONCO-THAI - Thérapies Laser Assistées par l'Image pour l'Oncologie - U 1189
2 ICHN - Imagerie cérébrale et handicaps neurologiques
3 Noyaux gris centraux

Purpose To constrain the risk of severe toxicity in radiotherapy and radiosurgery, precise volume delineation of organs at risk (OARs) is required. This task is still manually performed, which is time-consuming and prone to observer variability. To address these issues, and as alternative to atlas-based segmentation methods, machine learning techniques, such as support vector machines (SVM), have been recently presented to segment subcortical structures on magnetic resonance images (MRI).

Domaines: Cancer

J. Dolz, Anne Laprie, Soléakhéna Ken, Henri-Arthur Leroy, Nicolas Reyns, et al.. Supervised machine learning based classification scheme to segment the brainstem on MRI in multicenter brain tumor treatment context. International Journal of Computer Assisted Radiology and Surgery, 2015, pp.1/16. ⟨hal-01181348⟩