New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities

Filho, Pedro Pedrosa Rebouças; Sarmento, Róger Moura; Holanda, Gabriel B.; Lima, Daniel de Alencar

doi:10.1016/j.cmpb.2017.06.011

Cited by 60 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Descriptions of tissue patterns depend on a textural analysis. With the development of image processing, tiny pixel-wise correlations existing between tissues can be quantified and combined in an artificial intelligence classifier to achieve a computer-aided diagnosis (CAD) system [15,16]. The CAD system can analyze textural patterns which might not be readily recognized by human beings and provide diagnostic suggestions.…”

Section: Introductionmentioning

confidence: 99%

Computer-Aided Detection of Hyperacute Stroke Based on Relative Radiomic Patterns in Computed Tomography

Hung

Hsieh

2019

Applied Sciences

View full text Add to dashboard Cite

Ischemic stroke is one of the leading causes of disability and death. To achieve timely assessments, a computer-aided diagnosis (CAD) system was proposed to perform early recognition of hyperacute ischemic stroke based on non-contrast computed tomography (NCCT). In total, 26 patients with hyperacute ischemic stroke (with onset <6 h previous) and 56 normal controls composed the image database. For each NCCT slice, textural features were extracted from Ranklet-transformed images which had enhanced local contrast. Textural differences between the two sides of an image were calculated and combined in a machine learning classifier to detect stroke areas. The proposed CAD system using Ranklet features achieved significantly higher accuracy (81% vs. 71%), specificity (90% vs. 79%), and area under the curve (Az) (0.81 vs. 0.73) than conventional textural features. Diagnostic suggestions provided by the CAD system are fast and promising and could be useful in the pipeline of hyperacute ischemic stroke assessments.

show abstract

Section: Introductionmentioning

confidence: 99%

Computer-Aided Detection of Hyperacute Stroke Based on Relative Radiomic Patterns in Computed Tomography

Hung

Hsieh

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The developed SSHC algorithm was simple and accurate with minimum manual intervention. Rebouças Filho et al 26 developed hybrid feature extraction techniques such as GLCM features, Hu's moment, local binary patterns (LBP), statistical moment, central moment, and Zernike's moment for extracting feature vectors from the collected brain scans. Second, the classification was performed using SVM, KNN, and Bayesian classifiers to classify the CT images.…”

Section: Related Workmentioning

confidence: 99%

Intracranial hemorrhage subtype classification using learned fully connected separable convolutional network

Korra

Mamidi

Soora

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary In recent decades, intracranial hemorrhage detection from computed tomography (CT) scans has gained considerable attention among researchers in the medical community. The major problem in dealing with the Radiological Society of North America (RSNA) dataset is a three dimensional representation of CT scan, where the labeled data are scarce and hard to obtain. To highlight this problem, a novel learned fully connected separable convolutional network is proposed in this research article. After collecting the CT scans, data augmentation is used to generate multiple image variations to improve the capacity of the proposed model generalization. Based on the albumentations library, the transformations are selected for data augmentation such as brightness adjustment, horizontal flipping, shifting, rotation, and scaling. The intracranial hemorrhage subtype classification is accomplished utilizing a learned fully connected separable convolutional network which significantly classifies six classes as any, intraparenchymal, subarachnoid, epidural, intraventricular, and subdural. In the resulting phase, the learned fully connected separable convolutional network obtained an average accuracy of 98.63%, sensitivity of 73.32%, specificity of 99.49%, and area under the curve of 98.98%, where the obtained results are effective compared with ResNet‐50, SE‐ResNeXt‐50, ResNeXt‐101, and ResNeXt‐101 with bidirectional long short term memory network.

show abstract

“…If the disease is detected early, the disease can be cured. Manual detection and quantification of brain's stroke injuries are cumbersome and time‐consuming process 7,8 . Thus, automatic method is utilized only to identify and classification process.…”

Section: Introductionmentioning

confidence: 99%

“…Manual detection and quantification of brain's stroke injuries are cumbersome and time-consuming process. 7,8 Thus, automatic method is utilized only to identify and classification process. While treating the patient, the differentiation of the stroke plays a fundamental role in radiologist field.…”

Section: Introductionmentioning

confidence: 99%

A bio‐inspired AlexNet‐DrpXLm architype for an effective brain stroke lesion detection and classification

Melingi¹,

Mojjada²,

Reddy³

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

In this article, a bio-inspired AlexNet-DrpXLm architype is proposed for an effective brain stroke lesion detection and classification within a short period. Here, the input CT image datasets are collected from Himalayan Institute of Medical Sciences, then the images are preprocessed to take away the noises and also enhance the quality of the images. After that, the input images are trained and the features are extracted with the help of AlexNet model, and then classified as the brain images of normal and abnormal. The last three layers of the AlexNet model are replaced with the dropout extreme learning machine (DrpXLM) classifier to classify the images in efficient manner. The DrpXLM weight parameters are tuned by improved dolphin swarm optimization algorithm. The proposed method attains higher accuracy 99.54%, high precision 90.43%, high F-score 89.40%, higher specificity 93.56%, higher sensitivity 93.56%, lower computational time 0.02 s, and the proposed method is compared to the existing methods, like random decision forest with gravitational search algorithm, hybrid native Bayes and sample weighted with random forest classification algorithm, and random forest with fractional-order Darwinian particle swarm optimization.

show abstract

New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities

Cited by 60 publications

References 34 publications

Computer-Aided Detection of Hyperacute Stroke Based on Relative Radiomic Patterns in Computed Tomography

Computer-Aided Detection of Hyperacute Stroke Based on Relative Radiomic Patterns in Computed Tomography

Intracranial hemorrhage subtype classification using learned fully connected separable convolutional network

A bio‐inspired AlexNet‐DrpXLm architype for an effective brain stroke lesion detection and classification

Contact Info

Product

Resources

About