Deep neural-kernel blocks

Mehrkanoon, Siamak

doi:10.1016/j.neunet.2019.03.011

Cited by 20 publications

(12 citation statements)

References 33 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The automatic segmentation algorithm of convolutional neural networks (CNNs) belongs to a multilevel supervised learning network structure algorithm. In this network structure, pooling layer and convolution layer are the two main parts, which work together to segment the target features in CNN [ 5 , 6 ]. Some studies used the multichannel CNN model to accurately divide the brain tumors of patients from the brain MRI images.…”

Section: Introductionmentioning

confidence: 99%

Predictive Value of CT Perfusion Imaging on the Basis of Automatic Segmentation Algorithm to Evaluate the Collateral Blood Flow Status on the Outcome of Reperfusion Therapy for Ischemic Stroke

Qingsong

Wang

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Our objective was to study the predictive value of CT perfusion imaging based on automatic segmentation algorithm for evaluating collateral blood flow status in the outcome of reperfusion therapy for ischemic stroke. All data of 30 patients with ischemic stroke reperfusion in our hospital were collected and examined by CT perfusion imaging. Convolutional neural network (CNN) algorithm was used to segment perfusion imaging map and evaluate the results. The patients were grouped by regional leptomeningeal collateral score (rLMCs). Binary logistic regression was used to analyze the independent influencing factors of collateral blood flow on brain CT perfusion. The modified Scandinavian Stroke Scale was used to evaluate the prognosis of patients, and the effects of different collateral flow conditions on prognosis were obtained. The accuracy of CNN segmentation image is 62.61%, the sensitivity is 87.42%, the similarity coefficient is 93.76%, and the segmentation result quality is higher. Blood glucose (95% CI = 0.943, P = 0.028 ) and ischemic stroke history (95% CI = 0.855, P = 0.003 ) were independent factors affecting the collateral blood flow status of stroke patients. CBF (95% CI = 0.818, P = 0.008 ) and CBV (95% CI = 0.796, P = 0.016 ) were independent influencing factors of CT perfusion parameters. After 3 weeks of onset, the prognostic function defect score of the good collateral flow group (11.11%) was lower than that of the poor group (41.67%) ( P < 0.05 ). The automatic segmentation algorithm has more accurate segmentation ability for stroke CT perfusion imaging and plays a good auxiliary role in the diagnosis of clinical stroke reperfusion therapy. The collateral blood flow state based on CT perfusion imaging is helpful to predict the treatment outcome of patients with ischemic stroke and further predict the prognosis of patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Predictive Value of CT Perfusion Imaging on the Basis of Automatic Segmentation Algorithm to Evaluate the Collateral Blood Flow Status on the Outcome of Reperfusion Therapy for Ischemic Stroke

Qingsong

Wang

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…In terms of network architecture design, we utilized techniques such as skip connections, residual learning, batch normalization, average pooling to improve the network performance. The advantages of the mentioned techniques have been reported in the literature [28], [38], [39]. However, assembling those approaches to get a best architecture is challenging.…”

Section: Discussionmentioning

confidence: 99%

Dual-Stage U-Shape Convolutional Network for Esophageal Tissue Segmentation in OCT Images

Gan

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Automatic segmentation is the crucial step for esophageal optical coherence tomography (OCT) image processing, which is able to highlight diagnosis-related tissue layers and provide characteristics such as shape and thickness for esophageal disease diagnosis. This study proposes a dual-stage framework using a specifically designed encoder-decoder network configuration for accurate and reliable esophageal layer segmentation, which is named as the dual-stage U-shape convolutional network (D-UCN). The proposed approach utilized one UCN to locate the target tissue region, which is followed by another UCN with similar architecture to achieve the final segmentation. In this way, the proposed strategy effectively solves the problems encountered in our previous studies, such as disturbance from neighboring diagnostically unrelated tissues, probe protection sheaths from the imaging equipment and the inevitable speckle noise. Experimental results on esophageal OCT B-scans from C57BL mice demonstrated that the proposed dual-stage framework achieved performance comparable to manual segmentation. The effectiveness and advantages of the dual-stage strategy are also confirmed in comparison with graph theory dynamic program (GTDP) and U-Net. INDEX TERMS Esophageal layer segmentation, Optical coherence tomography, Fully convolutional network, Medical image analysis. FIGURE 1. Demonstration of (a) a typical esophageal OCT image for mouse and (b) the corresponding manual segmentation result. B. FRAMEWORK AND ARCHITECTURE This study proposes a D-UCN framework to segment esophageal layers from OCT images in a dual-stage strategy. It consists of two cascaded parts with the same U-shape network architecture, UCN-I and UCN-II, as shown in Fig.

show abstract

“…In the AI community, methods that combine kernel methods with deep learning are now being developed, such as neural kernel networks [58,59], deep neural kernel blocks [60], and deep kernel learning [61,62]. A soft sensor based on deep kernel learning was recently applied in a polymerization process [63].…”

Section: Relationship Between Kernel Methods and Neural Networkmentioning

confidence: 99%

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

et al. 2019

View full text Add to dashboard Cite

Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set. In this paper, the applications of kernel methods for feature extraction in industrial process monitoring are systematically reviewed. First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools. Second, by reviewing a total of 230 papers, this work has identified 12 major issues surrounding the use of kernel methods for nonlinear feature extraction. Each issue was discussed as to why they are important and how they were addressed through the years by many researchers. We also present a breakdown of the commonly used kernel functions, parameter selection routes, and case studies. Lastly, this review provides an outlook into the future of kernel-based process monitoring, which can hopefully instigate more advanced yet practical solutions in the process industries.

show abstract

Deep neural-kernel blocks

Cited by 20 publications

References 33 publications

Predictive Value of CT Perfusion Imaging on the Basis of Automatic Segmentation Algorithm to Evaluate the Collateral Blood Flow Status on the Outcome of Reperfusion Therapy for Ischemic Stroke

Predictive Value of CT Perfusion Imaging on the Basis of Automatic Segmentation Algorithm to Evaluate the Collateral Blood Flow Status on the Outcome of Reperfusion Therapy for Ischemic Stroke

Dual-Stage U-Shape Convolutional Network for Esophageal Tissue Segmentation in OCT Images

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

Contact Info

Product

Resources

About