2018
DOI: 10.1016/j.compbiomed.2018.05.027
|View full text |Cite
|
Sign up to set email alerts
|

Ischemic stroke lesion segmentation using stacked sparse autoencoder

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
26
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 58 publications
(26 citation statements)
references
References 29 publications
0
26
0
Order By: Relevance
“…In particular, supervised learning with deep convolutional neural networks (DCNNs) is being utilized to solve many problems in MRI. Given training pairs of MR images, DCNNs have been trained to perform many challenging and clinically useful tasks, including image reconstruction of undersampled data, segmentation of structures, and synthesis of images with higher resolution or images from a different modality . Many training pairs—examples of the input and target images—are required to train the network, which effectively learns the mapping relationship between the input and target domains.…”
Section: Introductionmentioning
confidence: 99%
“…In particular, supervised learning with deep convolutional neural networks (DCNNs) is being utilized to solve many problems in MRI. Given training pairs of MR images, DCNNs have been trained to perform many challenging and clinically useful tasks, including image reconstruction of undersampled data, segmentation of structures, and synthesis of images with higher resolution or images from a different modality . Many training pairs—examples of the input and target images—are required to train the network, which effectively learns the mapping relationship between the input and target domains.…”
Section: Introductionmentioning
confidence: 99%
“…It allowed us to detect more deep lesions and provided better segmentation of periventricular lesion boundaries. Praveen et al 105 showed that a deep architecture is using SAE layers. The experimental results showed that the proposed approach significantly outperforms the state-of-the-art methods in terms of precision, DC, and recall.…”
Section: Resultsmentioning
confidence: 99%
“…In the case of processing stroke with CNNs, the featurization of the images is a key application [75,124] and depends on the signal-to-noise ratio in the image, which can be improved by target identification via segmentation to select regions of interest [124]. According to Praveen et al, [193], a CNN learns to discriminate local features and returns better performance than hand-crafted features.…”
Section: Feature Extractionmentioning
confidence: 99%