MRI Boundary-Aware Segmentation of Multiple Sclerosis Lesions Using a Novel Mahalanobis Distance Map

The accurate segmentation of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) is essential for diagnosis, disease monitoring, and therapeutic assessment. Despite the significant advances in deep learning-based segmentation, the current boundary-aware approaches are limited by thei...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Gustavo Ulloa-Poblete, Alejandro Veloz, Sebastián Sánchez, Héctor Allende
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2025-10-01
Schriftenreihe:	Applied Sciences
Schlagworte:	multiple sclerosis lesion segmentation convolutional neural network magnetic resonance imaging distance map texture-aware loss function boundary-aware segmentation
Online-Zugang:	https://www.mdpi.com/2076-3417/15/19/10629
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!