Single channel photoplethysmography-based obstructive sleep apnea detection and arrhythmia classification

BACKGROUND: Simplified and easy-to-use monitoring approaches are crucial for the early diagnosis and prevention of obstructive sleep apnea (OSA) and its complications. OBJECTIVE: In this study, the OSA detection and arrhythmia classification algorithms based on single-channel photoplethysmography (PPG) are proposed for the early screening of OSA. METHODS: Thirty clinically diagnosed OSA patients participated in this study. Fourteen features were extracted from the PPG signals. The relationship between the number of features as inputs of the support vector machine (SVM) and performance of apnea events detection was evaluated. Also, a multi-classification algorithm based on the modified Hausdorff distance was proposed to recognize sinus rhythm and four arrhythmias highly related with SA. RESULTS: The feature set composed of meanPP, SDPP, RMSSD, meanAm, and meank1 could provide a satisfactory balance between the performance and complexity of the algorithm for OSA detection. Also, the arrhythmia classification algorithm achieves the average sensitivity, specificity and accuracy of 83.79%, 95.91% and 93.47%, respectively in the classification of all four types of arrhythmia and regular rhythm. CONCLUSION: Single channel PPG-based OSA detection and arrhythmia classification in this study can provide a feasible and promising approach for the early screening and diagnosis of OSA and OSA-related arrhythmias.

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation

White matter hyperintensities (WMH) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI-based segmentation methods are often sensitive to acquisition protocols, scanners, noise-level, and image contrast, failing to generalize to other populations and out-of-distribution datasets. Given these concerns, we propose a novel Bayesian 3D Convolutional Neural Network (CNN) with a U-Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. 432 subjects were recruited to train the CNNs from four multi-site imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multi-site study. We compared our model to two established state-of-the-art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U-Net achieved the highest Dice similarity coefficient of 0.89 ± 0.08 and the lowest modified Hausdorff distance of 2.98 ± 4.40 mm. We further validated our models highlighting their robustness on ′clinical adversarial cases′ simulating data with low signal-to-noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io

Automatic Ear Localization Using Entropy-Based Binary Jaya Algorithm and Weighted Hausdorff Distance

This paper presents an automatic human ear localization technique for handling uncontrolled scenarios such as illumination variation, poor contrast, partial occlusion, pose variation, ear ornaments, and background noise. The authors developed entropy-based binary Jaya algorithm (EBJA) and weighted doubly modified Hausdorff distance (W-MHD) to use edge information rather than pixels intensity values of the side face image. First, it embodies skin segmentation procedure using skin color model and successively remove spurious and non-ear edges which reduces the search space of the skin regions. Secondly, EBJA is proposed to trace dense edge regions as probable ear candidates. Thirdly, this paper developed an edge based weight function to represent the ear shape along with for the edge based template matching using W-MHD to identify true ear from a set of probable ear candidates. Experimental results using publicly available benchmark datasets demonstrate the competitiveness of the proposed technique in comparison to the state-of-the-art methods.

Analysis of the effectiveness of constraining metrics of geometric simplification algorithms based on expert evaluation of line detail

The paper reveals dependencies between the character of the line shape and combination of constraining metrics that allows comparable reduction in detail by different geometric simplification algorithms. The study was conducted in a form of the expert survey. geometrically simplified versions of three coastline fragments were prepared using three different geometric simplification algorithms—Douglas-peucker, Visvalingam-Whyatt and Li-Openshaw. Simplification was constrained by similar value of modified hausdorff distance (linear offset) and similar reduction of number of line bends (compression of the number of detail elements). Respondents were asked to give a numerical estimate of the detail of each image, based on personal perception, using a scale from one to ten. The results of the survey showed that lines perceived by respondents as having similar detail can be obtained by different algorithms. however, the choice of the metric used as a constraint depends on the nature of the line. Simplification of lines that have a shallow hierarchy of small bends is most effectively constrained by linear offset. As the line complexity increases, the compression metric for the number of detail elements (bends) increases its influence in the perception of detail. For one of the three lines, the best result was consistently obtained with a weighted combination of the analyzed metrics as a constraint. None of the survey results showed that only reducing the number of bends can be used as an effective characteristic of similar reduction in detail. It was therefore found that the linear offset metric is more indicative when describing changes in line detail.

Image-processing-based atmospheric river tracking method version 1 (IPART-1)

Automated detection of atmospheric rivers (ARs) has been heavily relying on magnitude thresholding on either the integrated water vapor (IWV) or integrated vapor transport (IVT). Magnitude-thresholding approaches can become problematic when detecting ARs in a warming climate, because of the increasing atmospheric moisture. A new AR detection method derived from an image-processing algorithm is proposed in this work. Different from conventional thresholding methods, the new algorithm applies threshold to the spatiotemporal scale of ARs to achieve the detection, thus making it magnitude independent and applicable to both IWV- and IVT-based AR detection. Compared with conventional thresholding methods, it displays lower sensitivity to parameters and a greater tolerance towards a wider range of water vapor flux intensities. A new method of tracking ARs is also proposed, based on a new AR axis identification method and a modified Hausdorff distance that gives a measure of the geographical distances of AR axes pairs.

Phase I non-linear profiles monitoring using a modified Hausdorff distance algorithm and clustering analysis

PurposeThe purpose of this paper is to propose a new non-parametric phase I control chart for the problem of non-linear profile outlier detection.Design/methodology/approachThe proposed non-parametric method is based on a modified Hausdorff distance, which does not require a restrictive assumption on the form of profiles. By obtaining the distance between each profile and the baseline profile, the authors introduced an iterative optimization clustering algorithm to identify outliers by clustering distances.FindingsThe simulation results show that the proposed method can distinguish outliers for structural changes of non-linear profiles. The authors also present a real industrial case example to highlight how practitioners can implement and make use of the proposed control chart in outlier detection applications, and it achieves higher accuracy in the outlier detection of complex profiles.Practical implicationsThe research results of this paper can be applied to any manufacturing or service system whose quality characteristics are characterized by non-linear profiles. This new approach provides quality practitioners a better decision-making tool for non-linear profile outlier detection.Originality/valueDue to the complexity of real-world applications, the non-linear profiles monitoring problem is yet to be addressed. However, the related research still remains rare. And the authors’ proposed non-linear profile control chart, which does not require a restrictive assumption on the form of profiles, shows its applicability and superiority in simulation study and real-world case.

Image Processing Based Atmospheric River Tracking Method Version 1 (IPART-1)

Automated detection of atmospheric rivers (ARs) has been heavily relying on magnitude thresholding on either the integrated water vapor (IWV) or integrated vapor transport (IVT). Magnitude thresholding approaches can become problematic when detecting ARs in a warming climate, because of the increasing atmospheric moisture. A new AR detection method derived from an image processing algorithm is proposed in this work. Different from conventional thresholding methods, the new algorithm applies threshold to the spatio-temporal scale of ARs to achieve the detection, thus making it magnitude independent and applicable to both IWV- and IVT-based AR detections. Compared with conventional thresholding methods, it displays lower sensitivity to parameters and a greater tolerance to a wider range of water vapor flux intensities. A new method of tracking ARs is also proposed, based on a new AR axis identification method, and a modified Hausdorff distance that gives a measure of the geographical distances of AR axes pairs.

Fully automatic segmentation of bee wing images

Bee preservation is important because approximately 70% of all pollination of food crops is made by them and this service costs more than $ 65 billion annually. In order to help this preservation, the identification of the bee species is necessary, and since this is a costly and time-consuming process, techniques that automate and facilitate this identification become relevant. Images of bees' wings in conjunction with computer vision and artificial intelligence techniques can be used to automate this process. This paper presents an approach to do segmentation of bees' wing images and feature extraction. Our approach was evaluated using the modified Hausdorff distance and F measure. The results were, at least, 24% more precise than the related approaches and the proposed approach was able to deal with noisy images.