An Integrated Model Combining Machine Learning and Deep Learning Algorithms for Classification of Rupture Status of IAs

The rupture risk assessment of intracranial aneurysms (IAs) is clinically relevant. How to accurately assess the rupture risk of IAs remains a challenge in clinical decision-making. We aim to build an integrated model to improve the assessment of the rupture risk of IAs. A total of 148 (39 ruptured...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in neurology Jg. 13; S. 868395
Hauptverfasser: Chen, Rong, Mo, Xiao, Chen, Zhenpeng, Feng, Pujie, Li, Haiyun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Media S.A 12.05.2022
Schlagworte:
deep learning
hemodynamic cloud
intracranial aneurysm
machine learning
Neurology
rupture risk
rupture risk
deep learning
hemodynamic cloud
intracranial aneurysm
machine learning
ISSN:1664-2295, 1664-2295
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The rupture risk assessment of intracranial aneurysms (IAs) is clinically relevant. How to accurately assess the rupture risk of IAs remains a challenge in clinical decision-making. We aim to build an integrated model to improve the assessment of the rupture risk of IAs. A total of 148 (39 ruptured and 109 unruptured) IA subjects were retrospectively computed with computational fluid dynamics (CFDs), and the integrated models were proposed by combining machine learning (ML) and deep learning (DL) algorithms. ML algorithms that include random forest (RF), k-nearest neighbor (KNN), XGBoost (XGB), support vector machine (SVM), and LightGBM were, respectively, adopted to classify ruptured and unruptured IAs. A Pointnet DL algorithm was applied to extract hemodynamic cloud features from the hemodynamic clouds obtained from CFD. Morphological variables and hemodynamic parameters along with the extracted hemodynamic cloud features were acted as the inputs to the classification models. The classification results with and without hemodynamic cloud features are computed and compared. Without consideration of hemodynamic cloud features, the classification accuracy of RF, KNN, XGB, SVM, and LightGBM was 0.824, 0.759, 0.839, 0.860, and 0.829, respectively, and the AUCs of them were 0.897, 0.584, 0.892, 0.925, and 0.890, respectively. With the consideration of hemodynamic cloud features, the accuracy successively increased to 0.908, 0.873, 0.900, 0.926, and 0.917. Meanwhile, the AUCs reached 0.952, 0.881, 0.950, 0.969, and 0.965 eventually. Adding consideration of hemodynamic cloud features, the SVM could perform best with the highest accuracy of 0.926 and AUC of 0.969, respectively. The integrated model combining ML and DL algorithms could improve the classification of IAs. Adding consideration of hemodynamic cloud features could bring more accurate classification, and hemodynamic cloud features were important for the discrimination of ruptured IAs.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Reviewed by: Chubin Ou, Macquarie University, Australia; Fuyou Liang, Shanghai Jiao Tong University, China
This article was submitted to Endovascular and Interventional Neurology, a section of the journal Frontiers in Neurology
Edited by: Xin Zhang, Southern Medical University, China
ISSN:1664-2295
1664-2295
DOI:10.3389/fneur.2022.868395