Dataset Information

Electrical Impedance Tomography-Based Abdominal Subcutaneous Fat Estimation Method Using Deep Learning.

ABSTRACT: This paper proposes a deep learning method based on electrical impedance tomography (EIT) to estimate the thickness of abdominal subcutaneous fat. EIT for evaluating the thickness of abdominal subcutaneous fat is an absolute imaging problem that aims at reconstructing conductivity distributions from current-to-voltage data. Existing reconstruction methods based on EIT have difficulty handling the inherent drawbacks of strong nonlinearity and severe ill-posedness of EIT; hence, absolute imaging may not be possible using linearized methods. To handle nonlinearity and ill-posedness, we propose a deep learning method that finds useful solutions within a restricted admissible set by accounting for prior information regarding abdominal anatomy. We determined that a specially designed training dataset used during the deep learning process significantly reduces ill-posedness in the absolute EIT problem. In the preprocessing stage, we normalize current-voltage data to alleviate the effects of electrodeposition and body geometry by exploiting knowledge regarding electrode positions and body geometry. The performance of the proposed method is demonstrated through numerical simulations and phantom experiments using a 10 channel EIT system and a human-like domain.

SUBMITTER: Lee K

PROVIDER: S-EPMC7305546 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Electrical Impedance Tomography-Based Abdominal Subcutaneous Fat Estimation Method Using Deep Learning.

Lee Kyounghun K Yoo Minha M Jargal Ariungerel A Kwon Hyeuknam H

Computational and mathematical methods in medicine 20200611

This paper proposes a deep learning method based on electrical impedance tomography (EIT) to estimate the thickness of abdominal subcutaneous fat. EIT for evaluating the thickness of abdominal subcutaneous fat is an absolute imaging problem that aims at reconstructing conductivity distributions from current-to-voltage data. Existing reconstruction methods based on EIT have difficulty handling the inherent drawbacks of strong nonlinearity and severe ill-posedness of EIT; hence, absolute imaging m ...[more]

PMID: 32587631

Similar Datasets

Project description:BackgroundPendelluft, defined as asynchronous alveolar ventilation, is caused by different regional time constants or dynamic pleural pressure variations. The aim of the present study was to propose a simple method to evaluate pendelluft based on electrical impedance tomography (EIT). The efficacy of this method was demonstrated in well-known pendelluft scenarios in 6 patients.MethodsTwo patients with flail chest after accidents, two patients with acute respiratory distress syndrome (ARDS) and two patients with acutely exacerbated obstructive lung disease were prospectively included. EIT measurements were performed before and after surgery (in patients with flail chest, who had video-assisted thoracoscopic surgery with ribs fixation), or at two different levels of positive end-expiratory pressure (PEEP; ARDS patients), or two different time points (obstructive lung disease). Pendelluft was assessed by regional phase shift (defined as time difference between global and regional impedance-time curves) and amplitude differences (defined as the impedance difference between sum of all regional tidal variation and the global tidal variation).ResultsIn patients with flail chest, pendelluft diminished several days after surgery (pendelluft amplitude normalized to tidal impedance variation reduced from 88% to 2% in one patient, 12% to 2% in the other). Increased PEEP reduced the amplitude of pendelluft (from 3% to 0% in one patient, 20% to 2% in the other) but not necessarily the phase shifts (average time differences were <0.1 second for both patients for both ins- and expiration) in ARDS patients. Pendelluft assessment in obstructive lung diseases reflected the change in airway resistance (from 5% to 1% in one patient after broncholytic medication administration, as airway resistance fell from 15 to 11 cmH2O/L/s; from 9% to 35% in the other patient with acute exacerbation, the corresponding airway resistance increased from 15 to 22 cmH2O/L/s).ConclusionsThe proposed EIT-based method can be used to evaluate the degree of pendelluft in dimension of phase shift and amplitude difference.

Dataset Information

Electrical Impedance Tomography-Based Abdominal Subcutaneous Fat Estimation Method Using Deep Learning.

Publications

Electrical Impedance Tomography-Based Abdominal Subcutaneous Fat Estimation Method Using Deep Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets