Adventitious lung sounds (ALS) as crackles and wheezes are present in different lung alterations and their automated characterization and recognition have become relevant. In fact, recently their 2D spatial distribution (SD) imaging has been proposed to help diagnose of pulmonary diseases. In this work, independent component analysis (ICA) by infomax was used to find crackles sources and from them to apply a time variant autoregressive model (TVAR) to count and imaging the ALS. The proposed methodology was assessed on multichannel LS recordings by embedding simulated fine crackles with known SD in recorded normal breathing sounds. Afterwards, the adventitious image of two patients with fibrosis and emphysema were obtained and contrasted with the classical pulmonary auscultation provided by a pneumologist. The results showed that combining ICA and TVAR leads to a robust methodology to imaging ALS.

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC.2013.6609760DOI Listing

Publication Analysis

Top Keywords

adventitious lung
8
lung sounds
8
imaging als
8
imaging
4
sounds imaging
4
imaging ica-tvar
4
ica-tvar scheme
4
scheme adventitious
4
sounds als
4
als crackles
4

Similar Publications

Background: Lung auscultation using a smartphone built-in microphone is promising for home monitoring of pediatric respiratory diseases. Our aim was to compare respiratory sounds recorded by a smartphone and a digital stethoscope by assessing the proportion of quality recordings and adventitious sounds detected by each device.

Methods: A comparative early feasibility study with children from a public school in Northern Portugal was conducted.

View Article and Find Full Text PDF

(1) Background: Methyl jasmonate-treated adventitious root extract (MeJA-DMARE), enriched with phenolics, has enhanced bioactivities. However, phenolics possess low stability and bioavailability. Substantial evidence indicates that plant extract-phospholipid complex assemblies, known as phytosomes, represent an innovative drug delivery system.

View Article and Find Full Text PDF

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning.

Bioengineering (Basel)

June 2024

Department of Electrical Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.

Respiratory diseases are among the leading causes of death, with many individuals in a population frequently affected by various types of pulmonary disorders. Early diagnosis and patient monitoring (traditionally involving lung auscultation) are essential for the effective management of respiratory diseases. However, the interpretation of lung sounds is a subjective and labor-intensive process that demands considerable medical expertise, and there is a good chance of misclassification.

View Article and Find Full Text PDF

(1) Background: Phytochemicals are crucial antioxidants that play a significant role in preventing cancer. (2) Methods: We explored the use of methyl jasmonate (MeJA) in the in vitro cultivation of adventitious roots (DMAR) and evaluated its impact on secondary metabolite production in DMAR, optimizing concentration and exposure time for cost-effectiveness. We also assessed its anti-inflammatory and anti-lung cancer activities and related gene expression levels.

View Article and Find Full Text PDF
Article Synopsis
  • The Covid-19 pandemic made it hard for hospitals to care for patients with severe lung problems, especially in Intensive Care Units (ICUs).
  • This study looked at how sounds from patients’ lungs could help doctors understand their lung damage and predict how long they would stay in the ICU and their chances of survival.
  • The researchers found that certain lung sounds, like “squawks” and “crackles,” were important because they related to how patients were doing and could help doctors make better decisions about their care.
View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!