Search

Cardiovascular diseases are a leading cause of mortality worldwide. This study introduces an innovative end-to-end pipeline for automated measurement of Carotid Intima-Media Thickness (CIMT) from ultrasound images, a crucial step in assessing cardiovascular risk. The process begins with the localization of the Region of Interest (ROI) using the You Only Look Once (YOLO) v5, followed by the application of various image enhancement methods. For precise segmentation of the Intima-Media Complex (IMC), a Deep Learning model is employed, featuring an encoder-decoder architecture, Self-Organizing Neural Networks (Self-ONN), multi-stage feature fusion, and deep supervision. The Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm is then utilized to combine these segmented masks, producing a final mask for precise CIMT measurement. This method achieved a Dice score of 82.03% and an Intersection over Union of 69.55% on the public Carotid Ultrasound Binary Segmentation (CUBS) dataset. Furthermore, the novel CIMT calculation technique demonstrated a mean squared error of 0.049 mm and a mean average error of 0.166 mm. The utilization of YOLOv5 for ROI selection significantly improved the accuracy of CIMT measurements, ensuring the most relevant regions are considered for analysis. The application of the STAPLE algorithm for prediction consensus demonstrates significant promise in producing optimal segmentation masks. In conclusion, this research, along with its continual enhancements, holds promise for facilitating the integration of human expertise and Deep Learning technologies, thereby refining diagnostic processes and contributing to the advancement of healthcare standards. • Complete CIMT solution: ROI detection, IMC segmentation, mask post-processing. • Innovative IMC segmentation: deep supervised fusion in encoder-decoder. • Unique CIMT calculation from segmentation mask. • In-depth interobserver variability analysis on public dataset subset. • Extensive exploration of image enhancement's impact on automation. [ABSTRACT FROM AUTHOR]

The world is slowly recovering from the Coronavirus disease 2019 (COVID-19) pandemic; however, humanity has experienced one of its According to work by Mishra et al. (2020), the study's first phase included a cohort of 5,262 subjects, with 3,325 Fitbit users constituting the majority. However, among this large cohort of 5,262 subjects, most significant trials in modern times only to learn about its lack of preparedness in the face of a highly contagious pathogen. To better prepare the world for any new mutation of the same pathogen or the newer ones, technological development in the healthcare system is a must. Hence, in this work, PCovNet+, a deep learning framework, was proposed for smartwatches and fitness trackers to monitor the user's Resting Heart Rate (RHR) for the infection-induced anomaly. A convolutional neural network (CNN)-based variational autoencoder (VAE) architecture was used as the primary model along with a long short-term memory (LSTM) network to create latent space embeddings for the VAE. Moreover, the framework employed pre-training using normal data from healthy subjects to circumvent the data shortage problem in the personalized models. This framework was validated on a dataset of 68 COVID-19-infected subjects, resulting in anomalous RHR detection with precision, recall, F-beta, and F-1 score of 0.993, 0.534, 0.9849, and 0.6932, respectively, which is a significant improvement compared to the literature. Furthermore, the PCovNet+ framework successfully detected COVID-19 infection for 74% of the subjects (47% presymptomatic and 27% post-symptomatic detection). The results prove the usability of such a system as a secondary diagnostic tool enabling continuous health monitoring and contact tracing. • A CNN-VAE-based anomaly detection model and an LSTM network to generate temporal-aware embeddings of the latent vector of the primary model is used. • Healthy patient data is used to pretrain the base model and fine-tuned using each subject's baseline data to achieve a personalized version. • The proposed model is validated on 68 COVID-19-infected individuals' data. [ABSTRACT FROM AUTHOR]