scholarly journals Deep learning algorithms to segment and quantify the choroidal thickness and vasculature in swept-source optical coherence tomography images

2020 ◽  
pp. 2140002
Author(s):  
Gu Zheng ◽  
Yanfeng Jiang ◽  
Ce Shi ◽  
Hanpei Miao ◽  
Xiangle Yu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Choroidal Thickness ◽  
Automatic Segmentation ◽  
Learning Algorithms ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Practical Method ◽  
Training Data ◽  
Validation Data ◽  
Swept Source

Accurate segmentation of choroidal thickness (CT) and vasculature is important to better analyze and understand the choroid-related ocular diseases. In this paper, we proposed and implemented a novel and practical method based on the deep learning algorithms, residual U-Net, to segment and quantify the CT and vasculature automatically. With limited training data and validation data, the residual U-Net was capable of identifying the choroidal boundaries as precise as the manual segmentation compared with an experienced operator. Then, the trained deep learning algorithms was applied to 217 images and six choroidal relevant parameters were extracted, we found high intraclass correlation coefficients (ICC) of more than 0.964 between manual and automatic segmentation methods. The automatic method also achieved great reproducibility with ICC greater than 0.913, indicating good consistency of the automatic segmentation method. Our results suggested the deep learning algorithms can accurately and efficiently segment choroid boundaries, which will be helpful to quantify the CT and vasculature.

scholarly journals Automatic Segmentation of Choroid Layer Using Deep Learning on Spectral Domain Optical Coherence Tomography

2021 ◽  
Vol 11 (12) ◽  
pp. 5488
Author(s):  
Wei Ping Hsia ◽  
Siu Lun Tse ◽  
Chia Jen Chang ◽  
Yu Len Huang
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Choroidal Thickness ◽  
Automatic Segmentation ◽  
Average Error ◽  
Good Prediction ◽  
Optical Coherence ◽  
Learning Method ◽  
Subfoveal Choroidal Thickness ◽  
Fully Connected

The purpose of this article is to evaluate the accuracy of the optical coherence tomography (OCT) measurement of choroidal thickness in healthy eyes using a deep-learning method with the Mask R-CNN model. Thirty EDI-OCT of thirty patients were enrolled. A mask region-based convolutional neural network (Mask R-CNN) model composed of deep residual network (ResNet) and feature pyramid networks (FPNs) with standard convolution and fully connected heads for mask and box prediction, respectively, was used to automatically depict the choroid layer. The average choroidal thickness and subfoveal choroidal thickness were measured. The results of this study showed that ResNet 50 layers deep (R50) model and ResNet 101 layers deep (R101). R101 U R50 (OR model) demonstrated the best accuracy with an average error of 4.85 pixels and 4.86 pixels, respectively. The R101 ∩ R50 (AND model) took the least time with an average execution time of 4.6 s. Mask-RCNN models showed a good prediction rate of choroidal layer with accuracy rates of 90% and 89.9% for average choroidal thickness and average subfoveal choroidal thickness, respectively. In conclusion, the deep-learning method using the Mask-RCNN model provides a faster and accurate measurement of choroidal thickness. Comparing with manual delineation, it provides better effectiveness, which is feasible for clinical application and larger scale of research on choroid.

Attack Detection in Cloud Networks Based on Artificial Intelligence Approaches

2019 ◽  
pp. 63-84
Author(s):  
Zuleyha Yiner ◽  
Nurefsan Sertbas ◽  
Safak Durukan-Odabasi ◽  
Derya Yiltas-Kaplan
Keyword(s):  
Cloud Computing ◽  
Deep Learning ◽  
Learning Algorithms ◽  
General Information ◽  
Attack Detection ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Network Access ◽  
Cloud Infrastructure ◽  
Security Issues

Cloud computing that aims to provide convenient, on-demand, network access to shared software and hardware resources has security as the greatest challenge. Data security is the main security concern followed by intrusion detection and prevention in cloud infrastructure. In this chapter, general information about cloud computing and its security issues are discussed. In order to prevent or avoid many attacks, a number of machine learning algorithms approaches are proposed. However, these approaches do not provide efficient results for identifying unknown types of attacks. Deep learning enables to learning features that are more complex, and thanks to the collection of big data as a training data, deep learning achieves more successful results. Many deep learning algorithms are proposed for attack detection. Deep networks architecture is divided into two categories, and descriptions for each architecture and its related attack detection studies are discussed in the following section of chapter.

scholarly journals Deep Learning-Based Segmentation and Quantification of Retinal Capillary Non-Perfusion on Ultra-Wide-Field Retinal Fluorescein Angiography

2020 ◽  
Vol 9 (8) ◽  
pp. 2537
Author(s):  
Joan M. Nunez do Rio ◽  
Piyali Sen ◽  
Rajna Rasheed ◽  
Akanksha Bagchi ◽  
Luke Nicholson ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fluorescein Angiography ◽  
Automatic Segmentation ◽  
Intraclass Correlation ◽  
Vascular Diseases ◽  
Dice Similarity Coefficient ◽  
Wide Field ◽  
Distribution Analysis ◽  
Topographical Distribution ◽  
Circular Grid

Reliable outcome measures are required for clinical trials investigating novel agents for preventing progression of capillary non-perfusion (CNP) in retinal vascular diseases. Currently, accurate quantification of topographical distribution of CNP on ultrawide field fluorescein angiography (UWF-FA) by retinal experts is subjective and lack standardisation. A U-net style network was trained to extract a dense segmentation of CNP from a newly created dataset of 75 UWF-FA images. A subset of 20 images was also segmented by a second expert grader for inter-grader reliability evaluation. Further, a circular grid centred on the FAZ was used to provide standardised CNP distribution analysis. The model for dense segmentation was five-fold cross-validated achieving area under the receiving operating characteristic of 0.82 (0.03) and area under precision-recall curve 0.73 (0.05). Inter-grader assessment on the 20 image subset achieves: precision 59.34 (10.92), recall 76.99 (12.5), and dice similarity coefficient (DSC) 65.51 (4.91), and the centred operating point of the automated model reached: precision 64.41 (13.66), recall 70.02 (16.2), and DSC 66.09 (13.32). Agreement of CNP grid assessment reached: Kappa 0.55 (0.03), perfused intraclass correlation (ICC) 0.89 (0.77, 0.93), non-perfused ICC 0.86 (0.73, 0.92), inter-grader agreement of CNP grid assessment values are Kappa 0.43 (0.03), perfused ICC 0.70 (0.48, 0.83), non-perfused ICC 0.71 (0.48, 0.83). Automated dense segmentation of CNP in UWF-FA images achieves performance levels comparable to inter-grader agreement values. A grid placed on the deep learning-based automatic segmentation of CNP generates a reliable and quantifiable method of measurement of CNP, to overcome the subjectivity of human graders.

scholarly journals Comparison of Anterior Ocular Biometric Measurements Using Swept-Source and Time-Domain Optical Coherence Tomography

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Sisi Chen ◽  
Rongrong Gao ◽  
Colm McAlinden ◽  
Junming Ye ◽  
Yiran Wang ◽  
...  
Keyword(s):  
Time Domain ◽  
Corneal Thickness ◽  
Intraclass Correlation ◽  
Anterior Segment ◽  
Anterior Chamber Depth ◽  
Correlation Coefficients ◽  
Random Order ◽  
Optical Coherence ◽  
Swept Source ◽  
Significant Difference

Purpose. To compare central corneal thickness (CCT), aqueous depth (AQD), and anterior chamber depth (ACD) measurements using the swept-source (CASIA SS-1000, Tomey, Japan) and time-domain (Visante, Carl Zeiss Meditec, USA) anterior segment optical coherence tomographers (OCT) in normal eyes. Methods. Sixty-eight eyes of 68 subjects were included. Three consecutive scans of each subject were obtained using both devices in a random order by one experienced operator. Standard deviation (Sw), coefficient of repeatability (CoR), coefficients of variation (CoV), and intraclass correlation coefficients (ICC) were used to evaluate the intraoperator repeatability. Agreement was assessed using the Bland–Altman plots and 95% limits of agreement (LoA). Results. All measurements of the swept-source OCT (SS-OCT) and time-domain OCT (TD-OCT) showed high repeatability with low CoR (CCT: 2.34 μm and 6.16 μm; AQD: 0.05 mm and 0.09 mm; ACD: 0.06 mm and 0.09 mm), low CoV (CCT: 0.16% and 0.42%; AQD: 0.61% and 0.97%; ACD: 0.53% and 0.83%), and high ICC (>0.98). The mean CCT with SS-OCT was slightly thicker than the results with TD-OCT (difference = 4.55 ± 2.62 μm, P<0.001). There was no statistically significant difference in AQD or ACD measurements between the two devices (0.01 ± 0.05 mm, P=0.111; 0.02 ± 0.05 mm, P=0.022, respectively). The 95% LoA between the SS-OCT and TD-OCT were −0.59 to 9.69 μm for CCT, −0.10 to 0.12 mm for AQD, and −0.09 to 0.12 mm for ACD. Conclusions. High levels of repeatability and agreement were found between the two devices for all three parameters, suggesting interchangeability. SS-OCT demonstrated superior repeatability compared with TD-OCT.

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Heart ◽  
2018 ◽  
Vol 104 (23) ◽  
pp. 1921-1928 ◽  
Author(s):  
Ming-Zher Poh ◽  
Yukkee Cheung Poh ◽  
Pak-Hei Chan ◽  
Chun-Ka Wong ◽  
Louise Pun ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Test Data ◽  
Predictive Value ◽  
Characteristic Curve ◽  
Performance Comparison ◽  
Learning System ◽  
Training Data ◽  
Validation Data ◽  
Data Set

ObjectiveTo evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms.MethodsWe trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison.ResultsIn the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924–0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%).ConclusionsIn this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.

scholarly journals Echocardiographic Features of Patients with Coronary Heart Disease and Angina Pectoris under Deep Learning Algorithms

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Xianjing Han ◽  
Guoxin Liang
Keyword(s):  
Coronary Heart Disease ◽  
Heart Disease ◽  
Deep Learning ◽  
Left Ventricle ◽  
Automatic Segmentation ◽  
Learning Algorithms ◽  
Left Ventricular ◽  
Comprehensive Analysis ◽  
Practical Application ◽  
Normal People

Based on the VGG19-fully convolutional network (FCN) (VGG19-FCN) and U-Net model in the deep learning algorithms, the left ventricle in the ultrasonic cardiogram was segmented automatically. In addition, this study evaluated the value of ultrasonic cardiogram features after segmentation by the optimized algorithm in diagnosing patients with coronary heart disease (CHD) and angina pectorisody; patients with arrhythmia; and pa. In this study, 30 patients with confirmed CHD and 30 normal people without CHD from the same hospital in a certain area were selected as the research objects. Firstly, the VGG19-FCN and U-Net model algorithms were selected to automatically segment the left ventricular part of the apical four-chamber static image, which was realized through the weights of the fine-tune basic model algorithm. Subsequently, the experimental subjects were divided into a normal group and a CHD group, and the data were obtained through the ultrasonic cardiogram feature analysis of automatic segmentation by the algorithm. The differences in the ejection fraction (EF), left ventricular fractional shortening (FS), and E/A values (in early and late of the diastolic phase) of the left ventricle for patients in the two groups were compared. In addition, the ultrasonic cardiogram left ventricular segmentation results of normal people and patients with CHD were compared. A comprehensive analysis suggested that the U-Net model was more suitable for the practical application of automatic ultrasonic cardiogram segmentation. According to the analyzed data results, the global systolic function parameters (EF, FS, and E/A values) of the left ventricle for patients showed statistically obvious differences ( P < 0.05 ). In summary, deep learning algorithms can effectively improve the efficiency of ultrasonic cardiogram left ventricular segmentation, show a great role in the diagnosis of CHD patients, and provide a reliable theoretical basis and foundation research on the subsequent CHD imaging diagnosis. The comprehensive analysis showed that the U-Net model was more suitable for the practical application of echocardiographic automatic segmentation, and this study can effectively improve the efficiency of echocardiographic left ventricular segmentation, which played an important role in the diagnosis of coronary heart disease, providing a reliable theoretical basis and foundation for subsequent CHD imaging research.

scholarly journals Automatic Segmentation and Cardiac Mechanics Analysis of Evolving Zebrafish Using Deep Learning

2021 ◽  
Vol 8 ◽  
Author(s):  
Bohan Zhang ◽  
Kristofor E. Pas ◽  
Toluwani Ijaseun ◽  
Hung Cao ◽  
Peng Fei ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Development ◽  
Imaging Techniques ◽  
Automatic Segmentation ◽  
Fluorescent Microscopy ◽  
Cardiac Mechanics ◽  
Light Sheet ◽  
Training Data ◽  
Volume Changes ◽  
Biomedical Analysis

Background: In the study of early cardiac development, it is essential to acquire accurate volume changes of the heart chambers. Although advanced imaging techniques, such as light-sheet fluorescent microscopy (LSFM), provide an accurate procedure for analyzing the heart structure, rapid, and robust segmentation is required to reduce laborious time and accurately quantify developmental cardiac mechanics.Methods: The traditional biomedical analysis involving segmentation of the intracardiac volume occurs manually, presenting bottlenecks due to enormous data volume at high axial resolution. Our advanced deep-learning techniques provide a robust method to segment the volume within a few minutes. Our U-net-based segmentation adopted manually segmented intracardiac volume changes as training data and automatically produced the other LSFM zebrafish cardiac motion images.Results: Three cardiac cycles from 2 to 5 days postfertilization (dpf) were successfully segmented by our U-net-based network providing volume changes over time. In addition to understanding each of the two chambers' cardiac function, the ventricle and atrium were separated by 3D erode morphology methods. Therefore, cardiac mechanical properties were measured rapidly and demonstrated incremental volume changes of both chambers separately. Interestingly, stroke volume (SV) remains similar in the atrium while that of the ventricle increases SV gradually.Conclusion: Our U-net-based segmentation provides a delicate method to segment the intricate inner volume of the zebrafish heart during development, thus providing an accurate, robust, and efficient algorithm to accelerate cardiac research by bypassing the labor-intensive task as well as improving the consistency in the results.

scholarly journals High interstudy repeatability of automatic deep learnt biventricular CMR measurements

2021 ◽  
Vol 22 (Supplement_2) ◽  
Author(s):  
S Alabed ◽  
K Karunasaagarar ◽  
F Alandejani ◽  
P Garg ◽  
J Uthoff ◽  
...  
Keyword(s):  
Pulmonary Hypertension ◽  
Deep Learning ◽  
Automatic Segmentation ◽  
Intraclass Correlation ◽  
Therapy Response ◽  
Left Ventricular ◽  
Dice Similarity Coefficient ◽  
Learning Approaches ◽  
Fully Automatic ◽  
Automatic Contouring

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): Wellcome Trust (UK), NIHR (UK) Introduction Cardiac magnetic resonance (CMR) measurements have significant diagnostic and prognostic value. Accurate and repeatable measurements are essential to assess disease severity, evaluate therapy response and monitor disease progression. Deep learning approaches have shown promise for automatic left ventricular (LV) segmentation on CMR, however fully automatic right ventricular (RV) segmentation remains challenging. We aimed to develop a biventricular automatic contouring model and evaluate the interstudy repeatability of the model in a prospectively recruited cohort. Methods A deep learning CMR contouring model was developed in a retrospective multi-vendor (Siemens and General Electric), multi-pathology cohort of patients, predominantly with heart failure, pulmonary hypertension and lung diseases (n = 400, ASPIRE registry). Biventricular segmentations were made on all CMR studies across cardiac phases. To test the accuracy of the automatic segmentation, 30 ASPIRE CMRs were segmented independently by two CMR experts. Each segmentation was compared to the automatic contouring with agreement assessed using the Dice similarity coefficient (DSC).  A prospective validation cohort of 46 subjects (10 healthy volunteers and 36 patients with pulmonary hypertension) were recruited to assess interstudy agreement of automatic and manual CMR assessments. Two CMR studies were performed during separate sessions on the same day. Interstudy repeatability was assessed using intraclass correlation coefficient (ICC) and Bland-Altman plots.  Results DSC showed high agreement (figure 1) comparing automatic and expert CMR readers, with minimal bias towards either CMR expert. The scan-scan repeatability CMR measurements were higher for all automatic RV measurements (ICC 0.89 to 0.98) compared to manual RV measurements (0.78 to 0.98). LV automatic and manual measurements were similarly repeatable (figure 2). Bland-Altman plots showed strong agreement with small mean differences between the scan-scan measurements (figure 2). Conclusion Fully automatic biventricular short-axis segmentations are comparable with expert manual segmentations, and have shown excellent interstudy repeatability.

scholarly journals Automatic segmentation and cardiac mechanics analysis of evolving zebrafish using deep-learning

2021 ◽  
Author(s):  
Bohan Zhang ◽  
Kristofor Pas ◽  
Toluwani Ijaseun ◽  
Hung Cao ◽  
Peng Fei ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Development ◽  
Imaging Techniques ◽  
Automatic Segmentation ◽  
Fluorescent Microscopy ◽  
Cardiac Mechanics ◽  
Light Sheet ◽  
Training Data ◽  
Volume Changes ◽  
Biomedical Analysis

AbstractObjectiveIn the study of early cardiac development, it is important to acquire accurate volume changes of the heart chambers. Although advanced imaging techniques, such as light-sheet fluorescent microscopy (LSFM), provide an accurate procedure for analyzing the structure of the heart, rapid and robust segmentation is required to reduce laborious time and accurately quantify developmental cardiac mechanics.MethodsThe traditional biomedical analysis involving segmentation of the intracardiac volume is usually carried out manually, presenting bottlenecks due to enormous data volume at high axial resolution. Our advanced deep-learning techniques provide a robust method to segment the volume within a few minutes. Our U-net based segmentation adopted manually segmented intracardiac volume changes as training data and produced the other LSFM zebrafish cardiac motion images automatically.ResultsThree cardiac cycles from 2 days post fertilization (dpf) to 5 dpf were successfully segmented by our U-net based network providing volume changes over time. In addition to understanding the cardiac function for each of the two chambers, the ventricle and atrium were separated by 3D erode morphology methods. Therefore, cardiac mechanical properties were measured rapidly and demonstrated incremental volume changes of both chambers separately. Interestingly, stroke volume (SV) remains similar in the atrium while that of the ventricle increases SV gradually.ConclusionOur U-net based segmentation provides a delicate method to segment the intricate inner volume of zebrafish heart during development; thus providing an accurate, robust and efficient algorithm to accelerate cardiac research by bypassing the labor-intensive task as well as improving the consistency in the results.

scholarly journals Achieving remanufacturing inspection using deep learning

2020 ◽  
Author(s):  
Chigozie Nwankpa ◽  
Solomon Eze ◽  
Winifred Ijomah ◽  
Anthony Gachagan ◽  
Stephen Marshall
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Learning Algorithms ◽  
Inspection System ◽  
Valuable Insight ◽  
Validation Data ◽  
Learning Techniques ◽  
Starting Point ◽  
Wide Range ◽  
Preliminary Study

Abstract Deep learning has emerged as a state-of-the-art learning technique across a wide range of applications, including image recognition, object detection and localisation, natural language processing, prediction and forecasting systems. With significant applicability, deep learning could be used in new and broader areas of applications, including remanufacturing. Remanufacturing is a process of taking used products through disassembly, inspection, cleaning, reconditioning, reassembly and testing to ascertain that their condition meets new products conditions with warranty. This process is complex and requires a good understanding of the respective stages for proper analysis. Inspection is a critical process in remanufacturing, which guarantees the quality of the remanufactured products. It is currently an expensive manual operation in the remanufacturing process that depends on operator expertise, in most cases. This research investigates the application of deep learning algorithms to inspection in remanufacturing, towards automating the inspection process. This paper presents a novel vision-based inspection system based on deep convolution neural network (DCNN) for eight types of defects, namely pitting, rust, cracks and other combination faults. The materials used for this feasibility study were 100 cm × 150 cm mild steel plate material, purchased locally, and captured using a USB webcam of 0.3 megapixels. The performance of this preliminary study indicates that the DCNN can classify with up to 100% accuracy on validation data and above 96% accuracy on a live video feed, by using 80% of the sample dataset for training and the remaining 20% for testing. Therefore, in the remanufacturing parts inspection, the DCNN approach has high potential as a method that could surpass the current technologies used in the design of inspection systems. This research is the first to apply deep learning techniques in remanufacturing inspection. The proposed method offers the potential to eliminate expert judgement in inspection, save cost, increase throughput and improve precision. This preliminary study demonstrates that deep learning techniques have the potential to revolutionise inspection in remanufacturing. This research offers valuable insight into these opportunities, serving as a starting point for future applications of deep learning algorithms to remanufacturing.

Sign in / Sign up

Export Citation Format

Share Document