Inferring Respiratory and Circulatory Parameters from Electrical Impedance Tomography With Deep Recurrent Models
نویسندگان
چکیده
Electrical impedance tomography (EIT) is a noninvasive imaging modality that allows continuous assessment of changes in regional bioimpedance different organs. One its most common biomedical applications monitoring ventilation distribution critically ill patients treated intensive care units. In this work, we put forward proof-of-principle study demonstrates how one can reconstruct synchronously measured respiratory or circulatory parameters from the EIT image sequence using deep learning model trained an end-to-end fashion. For purpose, devise architecture with convolutional feature extractor whose output processed by recurrent neural network. We demonstrate accurately infer absolute volume, flow, normalized airway pressure and within certain limitations even arterial blood signal alone, way generalizes to unseen without prior calibration. As outlook direct clinical relevance, furthermore feasibility reconstructing transpulmonary combination pressure, as potentially replace invasive measurement esophageal pressure. With these results, hope stimulate further studies building on framework work.
منابع مشابه
Applications of Electrical Impedance Tomography in Neurology
Introduction: Electrical impedance tomography (EIT) is a non-invasive technique utilized in various medical applications, including brain imaging and other neurological diseases. Recognizing the physiological and anatomical characteristics of organs based on their electrical properties is one of the main applications of EIT, as each variety of tissue structure has its own electrical characteris...
متن کاملElectrical impedance tomography : from topology
Abstract: A level set based shape and topology optimization approach to electrical impedance tomography (EIT) problems with piecewise constant conductivities is introduced. The proposed solution algorithm is initialized by using topological sensitivity analysis. Then it relies on the notion of shape derivatives to update the shape of the domains where conductivity takes different values.
متن کاملElectrical Impedance Tomography in Acute Respiratory Distress Syndrome
Electrical impedance tomography (EIT) is an emerging new imaging modality not yet routinely used in a clinical setting. The generation of EIT scans is based on the non-invasive measurement of electrical properties of tissues which does not require the use of radiation. Thoracic EIT examinations have been shown to track changes in regional lung volumes at scan rates of up to 40-50 scans/s. Exper...
متن کاملElectrical Impedance Tomography: from Topology to Shape
A level set based shape and topology optimization approach to electrical impedance tomography (EIT) problems with piecewise constant conductivities is introduced. The proposed solution algorithm is initialized by using topological sensitivity analysis. Then it relies on the notion of shape derivatives to update the shape of the domains where the conductivity takes its different values.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal of Biomedical and Health Informatics
سال: 2021
ISSN: ['2168-2208', '2168-2194']
DOI: https://doi.org/10.1109/jbhi.2021.3059016