Abstract

Abstract
Objective: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. Methods: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. Results: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. Conclusions: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. Significance: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity, which may provide an enhanced classification of clinical outcomes.

Abstract

Abstract
[No abstract available]

Abstract
Many complex systems exist in the physical world and therefore can be modeled by networks in which their nodes and edges are embedded in space. However, classical network motifs only use purely topological information and disregard other features. In this paper we introduce a novel and general subgraph abstraction that incorporates spatial information, therefore enriching its characterization power. Moreover, we describe and implement a method to compute and count our spatial subgraphs in any given network. We also provide initial experimental results by using our methodology to produce spatial fingerprints of real road networks, showcasing its discrimination power and how it captures more than just simple topology.

Abstract
This paper proposes a tool that extracts data from computational tomography (CT) scans of long bones, applies filters to allow a distinction between cortical and cancellous tissue, and converts the tissues into a three-dimensional (3D) model that can be used to generate finite element meshes. In order to identify the best segmentation technique for the problem under study, cortical, cancellous and medulla tissue segmentation was tested based on image histogram information, simple Hounsfield scale (HU) information, HU scale information with morphological operator filters, and active contour methods (active contour, random walker segmentation and findContours). These segmentations were evaluated qualitatively through a visual comparison and quantitatively through the calculation of the Dice Coefficient (DICE) and Mean-Squared Error (MSE) parameters. The developed algorithm presents a Dice higher than 0.95 and a MSE lower than 0.01 for cortical tissue segmentation, which allows it to be used as a bone characterization method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.