Classification of left atrial appendage morphology using Deep learning

Mikayle A. Holm; Alex Deakyne; Erik Gaasedelen; Weston Upchurch; Paul A. Iaizzo

doi:10.1115/DMD2020-9018

Classification of left atrial appendage morphology using Deep learning

Mikayle A. Holm, Alex Deakyne, Erik Gaasedelen, Weston Upchurch, Paul A. Iaizzo

Surgery

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Atrial fibrillation, a common cardiac arrhythmia, can lead to blood clots in the left atrial appendage (LAA) of the heart, increasing the risk of stroke. Understanding the LAA morphology can indicate the likelihood of a blood clot. Therefore, a classification convolutional neural network was implemented to predict the LAA morphology. Using 2D images of 3D models created from MRI scans of fixed human hearts and a pre-trained network, an 8.7% error rate was achieved. The network can be improved with more data or expanded to classify the LAA from the automatically segmented DICOM datasets and measure the LAA ostia.

Original language	English (US)
Title of host publication	Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020
Publisher	American Society of Mechanical Engineers (ASME)
ISBN (Electronic)	9780791883549
DOIs	https://doi.org/10.1115/DMD2020-9018
State	Published - 2020
Event	2020 Design of Medical Devices Conference, DMD 2020 - Minneapolis, United States Duration: Apr 6 2020 → Apr 9 2020

Publication series

Name	Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020

Conference

Conference	2020 Design of Medical Devices Conference, DMD 2020
Country/Territory	United States
City	Minneapolis
Period	4/6/20 → 4/9/20

Bibliographical note

Publisher Copyright:
Copyright © 2020 ASME

Keywords

Deep learning
Left atrial appendage

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access

10.1115/DMD2020-9018

OpenUrl availability

Full text

Cite this

Holm, M. A., Deakyne, A., Gaasedelen, E., Upchurch, W., & Iaizzo, P. A. (2020). Classification of left atrial appendage morphology using Deep learning. In Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020 (Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DMD2020-9018

Classification of left atrial appendage morphology using Deep learning. / Holm, Mikayle A.; Deakyne, Alex; Gaasedelen, Erik et al.
Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020. American Society of Mechanical Engineers (ASME), 2020. (Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Holm, MA, Deakyne, A, Gaasedelen, E, Upchurch, W & Iaizzo, PA 2020, Classification of left atrial appendage morphology using Deep learning. in Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020. Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020, American Society of Mechanical Engineers (ASME), 2020 Design of Medical Devices Conference, DMD 2020, Minneapolis, United States, 4/6/20. https://doi.org/10.1115/DMD2020-9018

Holm MA, Deakyne A, Gaasedelen E, Upchurch W, Iaizzo PA. Classification of left atrial appendage morphology using Deep learning. In Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020. American Society of Mechanical Engineers (ASME). 2020. (Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020). doi: 10.1115/DMD2020-9018

Holm, Mikayle A. ; Deakyne, Alex ; Gaasedelen, Erik et al. / Classification of left atrial appendage morphology using Deep learning. Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020. American Society of Mechanical Engineers (ASME), 2020. (Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020).

@inproceedings{0dbd797ef67444a1bcbd0271468c360a,

title = "Classification of left atrial appendage morphology using Deep learning",

abstract = "Atrial fibrillation, a common cardiac arrhythmia, can lead to blood clots in the left atrial appendage (LAA) of the heart, increasing the risk of stroke. Understanding the LAA morphology can indicate the likelihood of a blood clot. Therefore, a classification convolutional neural network was implemented to predict the LAA morphology. Using 2D images of 3D models created from MRI scans of fixed human hearts and a pre-trained network, an 8.7% error rate was achieved. The network can be improved with more data or expanded to classify the LAA from the automatically segmented DICOM datasets and measure the LAA ostia.",

keywords = "Deep learning, Left atrial appendage",

author = "Holm, {Mikayle A.} and Alex Deakyne and Erik Gaasedelen and Weston Upchurch and Iaizzo, {Paul A.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2020 ASME; 2020 Design of Medical Devices Conference, DMD 2020 ; Conference date: 06-04-2020 Through 09-04-2020",

year = "2020",

doi = "10.1115/DMD2020-9018",

language = "English (US)",

series = "Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020",

publisher = "American Society of Mechanical Engineers (ASME)",

booktitle = "Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020",

}

TY - GEN

T1 - Classification of left atrial appendage morphology using Deep learning

AU - Holm, Mikayle A.

AU - Deakyne, Alex

AU - Gaasedelen, Erik

AU - Upchurch, Weston

AU - Iaizzo, Paul A.

PY - 2020

Y1 - 2020

N2 - Atrial fibrillation, a common cardiac arrhythmia, can lead to blood clots in the left atrial appendage (LAA) of the heart, increasing the risk of stroke. Understanding the LAA morphology can indicate the likelihood of a blood clot. Therefore, a classification convolutional neural network was implemented to predict the LAA morphology. Using 2D images of 3D models created from MRI scans of fixed human hearts and a pre-trained network, an 8.7% error rate was achieved. The network can be improved with more data or expanded to classify the LAA from the automatically segmented DICOM datasets and measure the LAA ostia.

AB - Atrial fibrillation, a common cardiac arrhythmia, can lead to blood clots in the left atrial appendage (LAA) of the heart, increasing the risk of stroke. Understanding the LAA morphology can indicate the likelihood of a blood clot. Therefore, a classification convolutional neural network was implemented to predict the LAA morphology. Using 2D images of 3D models created from MRI scans of fixed human hearts and a pre-trained network, an 8.7% error rate was achieved. The network can be improved with more data or expanded to classify the LAA from the automatically segmented DICOM datasets and measure the LAA ostia.

KW - Deep learning

KW - Left atrial appendage

UR - http://www.scopus.com/inward/record.url?scp=85090668255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85090668255&partnerID=8YFLogxK

U2 - 10.1115/DMD2020-9018

DO - 10.1115/DMD2020-9018

M3 - Conference contribution

AN - SCOPUS:85090668255

T3 - Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020

BT - Frontiers in Biomedical Devices, BIOMED - 2020 Design of Medical Devices Conference, DMD 2020

PB - American Society of Mechanical Engineers (ASME)

T2 - 2020 Design of Medical Devices Conference, DMD 2020

Y2 - 6 April 2020 through 9 April 2020

ER -

Classification of left atrial appendage morphology using Deep learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this