Mechanics informed fluoroscopy of esophageal transport

Sourav Halder; Shashank Acharya; Wenjun Kou; Peter J. Kahrilas; John E. Pandolfino; Neelesh A. Patankar

doi:10.1007/s10237-021-01420-0

Mechanics informed fluoroscopy of esophageal transport

Sourav Halder, Shashank Acharya, Wenjun Kou, Peter J. Kahrilas, John E. Pandolfino, Neelesh A. Patankar^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

Fluoroscopy is a radiographic procedure for evaluating esophageal disorders such as achalasia, dysphasia and gastroesophageal reflux disease. It performs dynamic imaging of the swallowing process and provides anatomical detail and a qualitative idea of how well swallowed fluid is transported through the esophagus. In this work, we present a method called mechanics informed fluoroscopy (FluoroMech) that derives patient-specific quantitative information about esophageal function. FluoroMech uses a convolutional neural network to perform segmentation of image sequences generated from the fluoroscopy, and the segmented images become input to a one-dimensional model that predicts the flow rate and pressure distribution in fluid transported through the esophagus. We have extended this model to identify and estimate potential physiomarkers such as esophageal wall stiffness and active relaxation ahead of the peristaltic wave in the esophageal musculature. FluoroMech requires minimal computational time and hence can potentially be applied clinically in the diagnosis of esophageal disorders.

Original language	English (US)
Pages (from-to)	925-940
Number of pages	16
Journal	Biomechanics and Modeling in Mechanobiology
Volume	20
Issue number	3
DOIs	https://doi.org/10.1007/s10237-021-01420-0
State	Published - Jun 2021

Funding

We acknowledge the support provided by Public Health Service Grants R01-DK079902 and P01-DK117824, and National Science Foundation Grants OAC 1450374 and OAC 1931372 in the completion of this work. We also acknowledge the computational resources provided by Northwestern University\u2019s Quest High Performance Computing Cluster. For this work, we have also utilized the Extreme Science and Engineering Discovery Environment (XSEDE) cluster Comet, at the San Diego Supercomputer Center through allocation TG-ASC170023, which is supported by National Science Foundation Grant Number ACI-1548562 (Towns et al. ).

Keywords

Convolutional neural network
Esophageal active relaxation
Esophageal wall stiffness
Flexible tube
Image segmentation
One-dimensional flow

ASJC Scopus subject areas

Biotechnology
Modeling and Simulation
Mechanical Engineering

Access to Document

10.1007/s10237-021-01420-0

Cite this

@article{108ebec8633049b7a5b19502b372d973,

title = "Mechanics informed fluoroscopy of esophageal transport",

abstract = "Fluoroscopy is a radiographic procedure for evaluating esophageal disorders such as achalasia, dysphasia and gastroesophageal reflux disease. It performs dynamic imaging of the swallowing process and provides anatomical detail and a qualitative idea of how well swallowed fluid is transported through the esophagus. In this work, we present a method called mechanics informed fluoroscopy (FluoroMech) that derives patient-specific quantitative information about esophageal function. FluoroMech uses a convolutional neural network to perform segmentation of image sequences generated from the fluoroscopy, and the segmented images become input to a one-dimensional model that predicts the flow rate and pressure distribution in fluid transported through the esophagus. We have extended this model to identify and estimate potential physiomarkers such as esophageal wall stiffness and active relaxation ahead of the peristaltic wave in the esophageal musculature. FluoroMech requires minimal computational time and hence can potentially be applied clinically in the diagnosis of esophageal disorders.",

keywords = "Convolutional neural network, Esophageal active relaxation, Esophageal wall stiffness, Flexible tube, Image segmentation, One-dimensional flow",

author = "Sourav Halder and Shashank Acharya and Wenjun Kou and Kahrilas, {Peter J.} and Pandolfino, {John E.} and Patankar, {Neelesh A.}",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.",

year = "2021",

month = jun,

doi = "10.1007/s10237-021-01420-0",

language = "English (US)",

volume = "20",

pages = "925--940",

journal = "Biomechanics and Modeling in Mechanobiology",

issn = "1617-7959",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "3",

}

TY - JOUR

T1 - Mechanics informed fluoroscopy of esophageal transport

AU - Halder, Sourav

AU - Acharya, Shashank

AU - Kou, Wenjun

AU - Kahrilas, Peter J.

AU - Pandolfino, John E.

AU - Patankar, Neelesh A.

PY - 2021/6

Y1 - 2021/6

N2 - Fluoroscopy is a radiographic procedure for evaluating esophageal disorders such as achalasia, dysphasia and gastroesophageal reflux disease. It performs dynamic imaging of the swallowing process and provides anatomical detail and a qualitative idea of how well swallowed fluid is transported through the esophagus. In this work, we present a method called mechanics informed fluoroscopy (FluoroMech) that derives patient-specific quantitative information about esophageal function. FluoroMech uses a convolutional neural network to perform segmentation of image sequences generated from the fluoroscopy, and the segmented images become input to a one-dimensional model that predicts the flow rate and pressure distribution in fluid transported through the esophagus. We have extended this model to identify and estimate potential physiomarkers such as esophageal wall stiffness and active relaxation ahead of the peristaltic wave in the esophageal musculature. FluoroMech requires minimal computational time and hence can potentially be applied clinically in the diagnosis of esophageal disorders.

AB - Fluoroscopy is a radiographic procedure for evaluating esophageal disorders such as achalasia, dysphasia and gastroesophageal reflux disease. It performs dynamic imaging of the swallowing process and provides anatomical detail and a qualitative idea of how well swallowed fluid is transported through the esophagus. In this work, we present a method called mechanics informed fluoroscopy (FluoroMech) that derives patient-specific quantitative information about esophageal function. FluoroMech uses a convolutional neural network to perform segmentation of image sequences generated from the fluoroscopy, and the segmented images become input to a one-dimensional model that predicts the flow rate and pressure distribution in fluid transported through the esophagus. We have extended this model to identify and estimate potential physiomarkers such as esophageal wall stiffness and active relaxation ahead of the peristaltic wave in the esophageal musculature. FluoroMech requires minimal computational time and hence can potentially be applied clinically in the diagnosis of esophageal disorders.

KW - Convolutional neural network

KW - Esophageal active relaxation

KW - Esophageal wall stiffness

KW - Flexible tube

KW - Image segmentation

KW - One-dimensional flow

UR - http://www.scopus.com/inward/record.url?scp=85102078419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85102078419&partnerID=8YFLogxK

U2 - 10.1007/s10237-021-01420-0

DO - 10.1007/s10237-021-01420-0

M3 - Article

C2 - 33651206

AN - SCOPUS:85102078419

SN - 1617-7959

VL - 20

SP - 925

EP - 940

JO - Biomechanics and Modeling in Mechanobiology

JF - Biomechanics and Modeling in Mechanobiology

IS - 3

ER -

Mechanics informed fluoroscopy of esophageal transport

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this