Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter
Magnetic Resonance in Medicine · 2023-06 · 89 (6) · 2419-2431
DOI: 10.1002/mrm.29593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 24.01.2023. Verfasst von Haoyu Lan und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine, University of Southern Ca…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Neural Networks, Computer. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NINDS NIH HHS, NIA NIH HHS, NIMH NIH HHS.
Abstract (Originalsprache)
Purpose
To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter‐based image processing algorithm and the convolutional neural network.
Methods
We present a weakly supervised learning method for PVS segmentation by combing a rule‐based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data.
Results
The proposed method increases the true positive rate compared to the rule‐based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model.
Conclusions
Combing the filter‐based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter‐based image processing algorithm, the data driven PVS segmentation model using quality‐controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory of Neuro Imaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, USC Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
- NeuroScope Inc., New York, New York, USA.
ORCID-Profile: Haoyu Lan
Förderung
- NINDS NIH HHS
- NIA NIH HHS
- NIMH NIH HHS
- National Institute of Mental Health
- National Institute on Aging
Zitieren
APA
Lan, H., Lynch, K. M., Custer, R., Shih, N. C., Sherlock, P., Toga, A. W., Sepehrband, F., & Choupan, J. (2023). Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter. Magnetic Resonance in Medicine, 89(6), 2419-2431. https://doi.org/10.1002/mrm.29593
Vancouver
Lan H, Lynch KM, Custer R, Shih NC, Sherlock P, Toga AW, et al. Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter. Magnetic Resonance in Medicine. 2023;89(6):2419-2431. doi:10.1002/mrm.29593
BibTeX
@article{Lan2023,
author = {Lan, Haoyu and Lynch, Kirsten M and Custer, Rachel and Shih, Nien-Chu and Sherlock, Patrick and Toga, Arthur W and Sepehrband, Farshid and Choupan, Jeiran},
title = {Weakly supervised perivascular spaces segmentation with salient guidance of Frangi filter},
journal = {Magnetic Resonance in Medicine},
year = {2023},
volume = {89},
number = {6},
pages = {2419--2431},
doi = {10.1002/mrm.29593}
}
EUVIMED