Ten Fast Transfer Learning Models for Carotid Ultrasound Plaque Tissue Characterization in Augmentation Framework Embedded with Heatmaps for Stroke Risk Stratification

Background and Purpose: Only 1–2% of the internal carotid artery asymptomatic plaques are unstable as a result of >80% stenosis. Thus, unnecessary efforts can be saved if these plaques can be characterized and classified into symptomatic and asymptomatic using non-invasive B-mode ultrasound. Earlier plaque tissue characterization (PTC) methods were machine learning (ML)-based, which used hand-crafted features that yielded lower accuracy and unreliability. The proposed study shows the role of transfer learning (TL)-based deep learning models for PTC. Methods: As pertained weights were used in the supercomputer framework, we hypothesize that transfer learning (TL) provides improved performance compared with deep learning. We applied 11 kinds of artificial intelligence (AI) models, 10 of them were augmented and optimized using TL approaches—a class of Atheromatic™ 2.0 TL (AtheroPoint™, Roseville, CA, USA) that consisted of (i–ii) Visual Geometric Group-16, 19 (VGG16, 19); (iii) Inception V3 (IV3); (iv–v) DenseNet121, 169; (vi) XceptionNet; (vii) ResNet50; (viii) MobileNet; (ix) AlexNet; (x) SqueezeNet; and one DL-based (xi) SuriNet-derived from UNet. We benchmark 11 AI models against our earlier deep convolutional neural network (DCNN) model. Results: The best performing TL was MobileNet, with accuracy and area-under-the-curve (AUC) pairs of 96.10 ± 3% and 0.961 (p < 0.0001), respectively. In DL, DCNN was comparable to SuriNet, with an accuracy of 95.66% and 92.7 ± 5.66%, and an AUC of 0.956 (p < 0.0001) and 0.927 (p < 0.0001), respectively. We validated the performance of the AI architectures with established biomarkers such as greyscale median (GSM), fractal dimension (FD), higher-order spectra (HOS), and visual heatmaps. We benchmarked against previously developed Atheromatic™ 1.0 ML and showed an improvement of 12.9%. Conclusions: TL is a powerful AI tool for PTC into symptomatic and asymptomatic plaques.

Novel Instantaneous Wavelet Bicoherence for Vibration Fault Detection in Gear Systems

Higher order spectra exhibit a powerful detection capability of low-energy fault-related signal components, buried in background random noise. This paper investigates the powerful nonlinear non-stationary instantaneous wavelet bicoherence for local gear fault detection. The new methodology of selecting frequency bands that are relevant for wavelet bicoherence fault detection is proposed and investigated. The capabilities of wavelet bicoherence are proven for early-stage fault detection in a gear pinion, in which natural pitting has developed in multiple pinion teeth in the course of endurance gearbox tests. The results of the WB-based fault detection are compared with a stereo optical fault evaluation. The reliability of WB-based fault detection is quantified based on the complete probability of correct identification. This paper is the first attempt to investigate instantaneous wavelet bicoherence technology for the detection of multiple natural early-stage local gear faults, based on comprehensive statistical evaluation of the industrially relevant detection effectiveness estimate—the complete probability of correct fault detection.

Wilson statistics: derivation, generalization and applications to electron cryomicroscopy

The power spectrum of proteins at high frequencies is remarkably well described by the flat Wilson statistics. Wilson statistics therefore plays a significant role in X-ray crystallography and more recently in electron cryomicroscopy (cryo-EM). Specifically, modern computational methods for three-dimensional map sharpening and atomic modelling of macromolecules by single-particle cryo-EM are based on Wilson statistics. Here the first rigorous mathematical derivation of Wilson statistics is provided. The derivation pinpoints the regime of validity of Wilson statistics in terms of the size of the macromolecule. Moreover, the analysis naturally leads to generalizations of the statistics to covariance and higher-order spectra. These in turn provide a theoretical foundation for assumptions underlying the widespread Bayesian inference framework for three-dimensional refinement and for explaining the limitations of autocorrelation-based methods in cryo-EM.

Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, SPE

Wilson Statistics: Derivation, Generalization, and Applications to Electron Cryomicroscopy

The power spectrum of proteins at high frequencies is remarkably well described by the flat Wilson statistics. Wilson statistics therefore plays a significant role in X-ray crystallography and more recently in electron cryomicroscopy (cryo-EM). Specifically, modern computational methods for three-dimensional map sharpening and atomic modelling of macromolecules by single particle cryo-EM are based on Wilson statistics. Here we provide the first rigorous mathematical derivation of Wilson statistics. The derivation pinpoints the regime of validity of Wilson statistics in terms of the size of the macromolecule. Moreover, the analysis naturally leads to generalizations of the statistics to covariance and higher order spectra. These in turn provide theoretical foundation for assumptions underlying the widespread Bayesian inference framework for three-dimensional refinement and for explaining the limitations of autocorrelation based methods in cryo-EM.

Preliminary study in the analysis of the severity of cardiac pathologies using the higher-order spectra on the heart-beats signals

Phonocardiography is a technique for recording and interpreting the mechanical activity of the heart. The recordings generated by such a technique are called phonocardiograms (PCG). The PCG signals are acoustic waves revealing a wealth of clinical information about cardiac health. They enable doctors to better understand heart sounds when presented visually. Hence, multiple approaches have been proposed to analyze heart sounds based on PCG recordings. Due to the complexity and the high nonlinear nature of these signals, a computer-aided technique based on higher-order statistics (HOS) is employed, it is known to be an important tool since it takes into account the non-linearity of the PCG signals. This method also known as the bispectrum technique, can provide significant information to enhance the diagnosis for an accurate and objective interpretation of heart condition. The objective expected by this paper is to test in a preliminary way the parameters which can make it possible to establish a discrimination between the various signals of different pathologies and to characterize the cardiac abnormalities. This preliminary study will be done on a reduced sample (nine signals) before applying it subsequently to a larger sample. This work examines the effectiveness of using the bispectrum technique in the analysis of the pathological severity of different PCG signals. The presented approach showed that HOS technique has a good potential for pathological discrimination of various PCG signals.