Enhanced Ischemic Stroke Lesion Segmentation in MRI Using Attention U-Net with Generalized Dice Focal Loss
Applied Sciences · 11.09.2024 · 14 (18) · 8183
DOI: 10.3390/app14188183 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 11.09.2024. Verfasst von Beatriz P. Garcia-Salgado und 6 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Schlaganfall
Abstract (Originalsprache)
Ischemic stroke lesion segmentation in MRI images represents significant challenges, particularly due to class imbalance between foreground and background pixels. Several approaches have been developed to achieve higher F1-Scores in stroke lesion segmentation under this challenge. These strategies include convolutional neural networks (CNN) and models that represent a large number of parameters, which can only be trained on specialized computational architectures that are explicitly oriented to data processing. This paper proposes a lightweight model based on the U-Net architecture that handles an attention module and the Generalized Dice Focal loss function to enhance the segmentation accuracy in the class imbalance environment, characteristic of stroke lesions in MRI images. This study also analyzes the segmentation performance according to the pixel size of stroke lesions, giving insights into the loss function behavior using the public ISLES 2015 and ISLES 2022 MRI datasets. The proposed model can effectively segment small stroke lesions with F1-Scores over 0.7, particularly in FLAIR, DWI, and T2 sequences. Furthermore, the model shows reasonable convergence with their 7.9 million parameters at 200 epochs, making it suitable for practical implementation on mid and high-end general-purpose graphic processing units.
Zitieren
APA
Garcia-Salgado, B. P., Almaraz-Damian, J. A., Cervantes-Chavarria, O., Ponomaryov, V., Reyes-Reyes, R., Cruz-Ramos, C., & Sadovnychiy, S. (2024). Enhanced Ischemic Stroke Lesion Segmentation in MRI Using Attention U-Net with Generalized Dice Focal Loss. Applied Sciences, 14(18), 8183. https://doi.org/10.3390/app14188183
Vancouver
Garcia-Salgado BP, Almaraz-Damian JA, Cervantes-Chavarria O, Ponomaryov V, Reyes-Reyes R, Cruz-Ramos C, et al. Enhanced Ischemic Stroke Lesion Segmentation in MRI Using Attention U-Net with Generalized Dice Focal Loss. Applied Sciences. 2024;14(18):8183. doi:10.3390/app14188183
BibTeX
@article{GarciaSalgado2024,
author = {Garcia-Salgado, Beatriz P. and Almaraz-Damian, Jose A. and Cervantes-Chavarria, Oscar and Ponomaryov, Volodymyr and Reyes-Reyes, Rogelio and Cruz-Ramos, Clara and Sadovnychiy, Sergiy},
title = {Enhanced Ischemic Stroke Lesion Segmentation in MRI Using Attention U-Net with Generalized Dice Focal Loss},
journal = {Applied Sciences},
year = {2024},
volume = {14},
number = {18},
pages = {8183},
doi = {10.3390/app14188183}
}
EUVIMED