Automated MRI‐based segmentation of intracranial arterial calcification by restricting feature complexity

Purpose To develop an automated deep learning model for MRI‐based segmentation and detection of intracranial arterial calcification. Methods A novel deep learning model under the variational autoencoder framework was developed. A theoretically grounded dissimilarity loss was proposed to refine netwo...

Full description

Saved in:
Bibliographic Details
Published in:Magnetic resonance in medicine Vol. 93; no. 1; pp. 384 - 396
Main Authors: Wang, Xin, Canton, Gador, Guo, Yin, Zhang, Kaiyu, Akcicek, Halit, Yaman Akcicek, Ebru, Hatsukami, Thomas, Zhang, Jin, Sun, Beibei, Zhao, Huilin, Zhou, Yan, Shapiro, Linda, Mossa‐Basha, Mahmud, Yuan, Chun, Balu, Niranjan
Format: Journal Article
Language:English
Published: United States Wiley Subscription Services, Inc 01.01.2025
Subjects:
Adult
Aged
Algorithms
Arteriosclerosis
Automation
Brain - diagnostic imaging
Calcification
Calcification (ectopic)
calcification segmentation
Complexity
Deep Learning
Feature extraction
Female
Humans
Image analysis
Image Interpretation, Computer-Assisted - methods
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
information bottleneck
intracranial arteries
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Male
Metric space
Middle Aged
Recall
Segmentation
Statistical analysis
Statistical tests
variational autoencoders
Vascular Calcification - diagnostic imaging
deep learning
variational autoencoders
calcification segmentation
intracranial arteries
information bottleneck
ISSN:0740-3194, 1522-2594, 1522-2594
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose To develop an automated deep learning model for MRI‐based segmentation and detection of intracranial arterial calcification. Methods A novel deep learning model under the variational autoencoder framework was developed. A theoretically grounded dissimilarity loss was proposed to refine network features extracted from MRI and restrict their complexity, enabling the model to learn more generalizable MR features that enhance segmentation accuracy and robustness for detecting calcification on MRI. Results The proposed method was compared with nine baseline methods on a dataset of 113 subjects and showed superior performance (for segmentation, Dice similarity coefficient: 0.620, area under precision‐recall curve [PR‐AUC]: 0.660, 95% Hausdorff Distance: 0.848 mm, Average Symmetric Surface Distance: 0.692 mm; for slice‐wise detection, F1 score: 0.823, recall: 0.764, precision: 0.892, PR‐AUC: 0.853). For clinical needs, statistical tests confirmed agreement between the true calcification volumes and predicted values using the proposed approach. Various MR sequences, namely T1, time‐of‐flight, and SNAP, were assessed as inputs to the model, and SNAP provided unique and essential information pertaining to calcification structures. Conclusion The proposed deep learning model with a dissimilarity loss to reduce feature complexity effectively improves MRI‐based identification of intracranial arterial calcification. It could help establish a more comprehensive and powerful pipeline for vascular image analysis on MRI.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0740-3194
1522-2594
1522-2594
DOI:10.1002/mrm.30283