Life Sciences & Biotechnology
Title : | Acoustic Modeling and Analysis of Pulmonary System |
Area of research : | Life Sciences & Biotechnology |
Focus area : | Theoretical Sciences, Health Care, Machine Learning |
Principal Investigator : | Dr. Prasanta Kumar Ghosh, Indian Institute Of Science, Bangalore, Karnataka |
Timeline Start Year : | 2023 |
Timeline End Year : | 2026 |
Contact info : | prasantg@ee.iisc.ernet.in |
Details
Executive Summary : | Introduction A pulmonary system is a network of organs and tissues that help us to breath. A typical pulmonary system in humans consists of lungs, larynx, trachea, bronchi, bronchioles, alveoli and thoracic diaphragm. Inspiratory sounds measured simultaneously over the extrathoracic trachea and at the chest surface contain highly unique regional information[1]. The characteristic patterns in the recorded data are associated with the conditions affecting airway patency such as asthma and obstructive sleep apnea. There is a potential for the recorded sounds to be used in clinical practices for the diagnosis and monitoring of various respiratory conditions[2]. For such potential clinical application to be most useful, the relation between these sounds and the underlying anatomy (anatomical-acoustical relationship), and ultimately pathophysiology, needs to be determined. Research in acoustics has traditionally focused on developing physical models using analytical, numerical and experimental techniques. These models are used to infer the properties of the environment and the performance of the machinery. With increasing amounts of data, data-driven approaches have made an enormous success. Machine learning (ML) techniques have extended the frontiers in automated data processing and pattern recognition in many fields, including speech and image processing, computer vision and geophysical science. However, the benefits of ML (in acoustics) cannot be fully realized without building the indispensable physical models using computational tools. Objectives Development of an acoustical model of the respiratory system that is based on its anatomy and physiology Solving the model with physics-informed neural networks (PINNs) so that a synergy of the strengths of the physical intuition and data-driven insights can be obtained. Application of the model to understand the acoustical signature of the respiratory sound produced by asthmatic patients. |
Total Budget (INR): | 6,60,000 |
Organizations involved