Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks

2021 ◽  
Author(s):  
Chung-Ming Lo ◽  
Peng-Hsiang Hung ◽  
Daw-Tung Lin
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Convolutional Neural Networks ◽  
Rapid Assessment ◽  
Deep Convolutional Neural Networks

scholarly journals Automatic segmentation of cerebral infarcts in follow-up computed tomography images with convolutional neural networks

2019 ◽  
Vol 12 (9) ◽  
pp. 848-852 ◽  
Author(s):  
Renan Sales Barros ◽  
Manon L Tolhuisen ◽  
Anna MM Boers ◽  
Ivo Jansen ◽  
Elena Ponomareva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Convolutional Neural Networks ◽  
Infarct Volume ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Reference Standard ◽  
Computed Tomography Images

Background and purposeInfarct volume is a valuable outcome measure in treatment trials of acute ischemic stroke and is strongly associated with functional outcome. Its manual volumetric assessment is, however, too demanding to be implemented in clinical practice.ObjectiveTo assess the value of convolutional neural networks (CNNs) in the automatic segmentation of infarct volume in follow-up CT images in a large population of patients with acute ischemic stroke.Materials and methodsWe included CT images of 1026 patients from a large pooling of patients with acute ischemic stroke. A reference standard for the infarct segmentation was generated by manual delineation. We introduce three CNN models for the segmentation of subtle, intermediate, and severe hypodense lesions. The fully automated infarct segmentation was defined as the combination of the results of these three CNNs. The results of the three-CNNs approach were compared with the results from a single CNN approach and with the reference standard segmentations.ResultsThe median infarct volume was 48 mL (IQR 15–125 mL). Comparison between the volumes of the three-CNNs approach and manually delineated infarct volumes showed excellent agreement, with an intraclass correlation coefficient (ICC) of 0.88. Even better agreement was found for severe and intermediate hypodense infarcts, with ICCs of 0.98 and 0.93, respectively. Although the number of patients used for training in the single CNN approach was much larger, the accuracy of the three-CNNs approach strongly outperformed the single CNN approach, which had an ICC of 0.34.ConclusionConvolutional neural networks are valuable and accurate in the quantitative assessment of infarct volumes, for both subtle and severe hypodense infarcts in follow-up CT images. Our proposed three-CNNs approach strongly outperforms a more straightforward single CNN approach.

scholarly journals Rib fracture detection in computed tomography images using deep convolutional neural networks

Medicine ◽  
2021 ◽  
Vol 100 (20) ◽  
pp. e26024
Author(s):  
Masafumi Kaiume ◽  
Shigeru Suzuki ◽  
Koichiro Yasaka ◽  
Haruto Sugawara ◽  
Yun Shen ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Rib Fracture ◽  
Fracture Detection ◽  
Deep Convolutional Neural Networks ◽  
Computed Tomography Images
Sign in / Sign up

Export Citation Format

Share Document