Radiomics features on non-contrast computed tomography predict early enlargement of spontaneous intracerebral hemorrhage

Radiomics features on non-contrast computed tomography predict early enlargement of spontaneous intracerebral hemorrhage

Highlights•To explore value of radiomics features on NCCT in early enlargement of SICH. •A total of 1227 texture features of each cerebral hematoma were obtained. •Linear Support Vector Classifier showed the highest accuracy. •Radiomics features on NCCT showed good performance in predicting HE of SI...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Clinical neurology and neurosurgery 2019-10, Vol.185, p.105491-105491, Article 105491
Hauptverfasser: Li, Hui, Xie, Yuanliang, Wang, Xiang, Chen, Faxiang, Sun, Jianqing, Jiang, Xiaoli
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Artificial intelligence
Colorectal cancer
Computed tomography
Consent
Enlargement
Expansion
Hematoma
Hemorrhage
Intracerebral hemorrhage
Machine learning
Medical ethics
Model accuracy
Neurology
Neurosurgery
Nonuniformity
Prediction models
Radiomics
Sensitivity
Signs
Software
Wavelet transforms
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Highlights•To explore value of radiomics features on NCCT in early enlargement of SICH. •A total of 1227 texture features of each cerebral hematoma were obtained. •Linear Support Vector Classifier showed the highest accuracy. •Radiomics features on NCCT showed good performance in predicting HE of SICH.
ISSN:0303-8467
1872-6968
DOI:10.1016/j.clineuro.2019.105491