Automated segmentation of subarachnoid hemorrhages with convolutional neural networks

Barros, Renan Sales; Steen, Wessel E. van der; Boers, Anna M. M.; Zijlstra, Ijsbrand A.J.; Berg, René van den; Youssoufi, Wassim El; Urwald, Alexandre; Verbaan, Dagmar; Vandertop, W. Peter; Majoie, Charles B. L. M.; Olabarriaga, Sílvia D.; Marquering, Henk A.

doi:10.1016/j.imu.2020.100321

Cited by 31 publications

(23 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a previously presented method for automated intracranial hemorrhage segmentation11 to exclude the parenchymal hemorrhages of the CNN-based infarct segmentation. These hemorrhage voxels were not used to train the CNN.…”

Section: Methodsmentioning

confidence: 99%

“…Its hyperparameters were optimized for segmentation of a single foreground structure in head NCCT scans, which in this case was the infarcted brain tissue. Previously, the same CNN architecture was successfully used for intracranial hemorrhage segmentation 11. This CNN architecture determines the probability of the voxel at the center of an image patch being foreground (infarcted tissue) or background (any other tissue).…”

Section: Methodsmentioning

confidence: 99%

“…Previously, the same CNN architecture was successfully used for intracranial hemorrhage segmentation. 11 This CNN architecture determines the probability of the voxel at the center of an image patch being foreground (infarcted tissue) or background (any other tissue). This probability was subsequently dichotomized using a cut-off value, which was optimized with the data in the validation set.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

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

Barros

Tolhuisen

Boers

et al. 2019

J NeuroIntervent Surg

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

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

Barros

Tolhuisen

Boers

et al. 2019

J NeuroIntervent Surg

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2019, Clerigues et al [9] presented and evaluated an automation method for segmenting the nucleus of acute stroke lesions on CT scan images using Convolutional Neural Networks (CNN). Barros, et al [10] automatically segmented subarachnoid hemorrhage and Chin, et al [4] detected ischemic stroke using CNN. From their second research, CNN produced good work performance with an accuracy of more than 90%.…”

Section: Introductionmentioning

confidence: 99%

Ischemic Stroke Classification using Random Forests Based on Feature Extraction of Convolutional Neural Networks

Saragih¹,

Rustam²,

Aldila³

et al. 2020

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Stroke has become a global health problem, due to high mortality and disability, with two-thirds of all strokes occurring in developing countries. In Indonesia, stroke is a disease with the highest mortality rate, namely in the first rank for more than two decades, 1990-2017. Stroke is divided into two types, ischemic and hemorrhagic; however, 87% of stroke sufferers are ischemic stroke. Suppose an ischemic stroke is found, and the patient is a new sufferer. In that case, the patient should get direct treatment because there is a golden period in stroke management that is if 4.5 hours to help and reduce the risk of death or permanent disability. High mortality and disability raise awareness of the importance of early detection of ischemic stroke; therefore, research has been carried out, especially in technology. To carry out automatic diagnosis, machine learning and deep learning can be used, especially because of their ability to provide high accuracy prediction results. In this study, the authors will provide an update in the detection of ischemic stroke based on patient CT scan by replacing NN's role on CNN with random forests. Thus, after feature extraction on CNN, the fully connected layer on CNN is completely replaced by random forests in classifying data. Based on the proposed method, the accuracy of testing is 100% when the percentage of the testing dataset is 10% and the number of trees more than 100 with criterion Gini or entropy.

show abstract

“…Garnier et al [7] used CNN as automatic diagnostics of tuberculosis. Barros et al [8] segmented subarachnoid hemorrhage and Chin et al [9] detected ischemic stroke using CNN. Based on their research, CNN produces good work performance with an accuracy of more than 90%.…”

mentioning

confidence: 99%

A hybrid model based on convolutional neural networks and fuzzy kernel K-medoids for lung cancer detection

Saragih

Rustam

Aurelia

2021

IJEECS

View full text Add to dashboard Cite

Lung cancer is the deadliest cancer worldwide. Correct diagnosis of lung cancer is one of the main tasks that is challenging tasks, so the patient can be treated as soon as possible. In this research, we proposed a hybrid model based on convolutional neural networks (CNN) and fuzzy kernel k-medoids (FKKM) for lung cancer detection, where the magnetic resonance imaging (MRI) images are transmitted to CNN, and then the output is used as new input for FKKM. The dataset used in this research consist of MRI images taken from someone who had lung cancer with the treatment of anti programmed cell death-1 (anti-PD1) immunotherapy in 2016 that obtained from the cancer imaging archive. The proposed method obtained accuracy, sensitivity, precision, specificity, and F1-score 100% by using radial basis function (RBF) kernel with sigma of {10-8, 10-4, 10-3, 5x10-2, 10-1, 1, 104} in 20-fold cross-validation. The computational time is only taking less than 10 seconds to forward dataset to CNN and 3.85 ± 0.6 seconds in FKKM model. So, the proposed method is more efficient in time and has a high performance for detecting lung cancer from MRI images.

show abstract

Automated segmentation of subarachnoid hemorrhages with convolutional neural networks

Cited by 31 publications

References 17 publications

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

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

Ischemic Stroke Classification using Random Forests Based on Feature Extraction of Convolutional Neural Networks

A hybrid model based on convolutional neural networks and fuzzy kernel K-medoids for lung cancer detection

Contact Info

Product

Resources

About