NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans

Purpose This study evaluates the nnU-Net for segmenting brain, skin, tumors, and ventricles in contrast-enhanced T1 (T1CE) images, benchmarking it against an established mesh growing algorithm (MGA). Methods We used 67 retrospectively collected annotated single-center T1CE brain scans for training m...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Acta neurochirurgica 2024-02, Vol.166 (1), p.92-92, Article 92
Hauptverfasser:	de Boer, Mathijs, Kos, Tessa M., Fick, Tim, van Doormaal, Jesse A. M., Colombo, Elisa, Kuijf, Hugo J., Robe, Pierre A. J. T., Regli, Luca P., Bartels, Lambertus W., van Doormaal, Tristan P. C.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Automation Brain tumors Datasets Deep learning Image processing Interventional Radiology Magnetic resonance imaging Medicine Medicine & Public Health Minimally Invasive Surgery Neural networks Neurology Neuroradiology Neurosurgery Neurosurgery general Oncology Original Original Article Patients Planning Segmentation Skin Surgical Orthopedics Three dimensional imaging Tumors Ventricle Ventricles (cerebral) Visualization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!