A deep learning approach for the automatic identification of the left atrium within CT scans

Alex Deakyne, Erik Gaasedelen, Paul A. Iaizzo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent advancements in deep learning have led to the possibility of increased performance in computer vision tools. A major development has been the usage of Convolutional Neural Networks (CNN) for automatically detecting features within a given image. Architectures such as YOLO1 have obtained incredibly high performances for the real-time detection of every-day objects within images. However to date, there have been few reports of deep learning applied to detect anatomical features within CT scans; especially those within the cardiovascular space. We propose here an automatic anatomical feature detection pipeline for identifying the features of the left atrium using a CNN. Slices of CT scans were fed into a single neural network which predicted the four bounding box coordinates that encapsulate the left atrium. The network can be optimized end-to-end and generate predictions at great speed, achieving a validation smooth L1 loss of 11.95 when predicting the left atrial bounding boxes.

Original languageEnglish (US)
Title of host publicationFrontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791841037
DOIs
StatePublished - Jan 1 2019
Event2019 Design of Medical Devices Conference, DMD 2019 - Minneapolis, United States
Duration: Apr 15 2019Apr 18 2019

Publication series

NameFrontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019

Conference

Conference2019 Design of Medical Devices Conference, DMD 2019
CountryUnited States
CityMinneapolis
Period4/15/194/18/19

Fingerprint

Computerized tomography
Neural networks
Computer vision
Pipelines
Deep learning

Keywords

  • CNN
  • Computer Vision
  • Deep Learning
  • Object Detection

Cite this

Deakyne, A., Gaasedelen, E., & Iaizzo, P. A. (2019). A deep learning approach for the automatic identification of the left atrium within CT scans. In Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019 (Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DMD2019-3282

A deep learning approach for the automatic identification of the left atrium within CT scans. / Deakyne, Alex; Gaasedelen, Erik; Iaizzo, Paul A.

Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019. American Society of Mechanical Engineers (ASME), 2019. (Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Deakyne, A, Gaasedelen, E & Iaizzo, PA 2019, A deep learning approach for the automatic identification of the left atrium within CT scans. in Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019. Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019, American Society of Mechanical Engineers (ASME), 2019 Design of Medical Devices Conference, DMD 2019, Minneapolis, United States, 4/15/19. https://doi.org/10.1115/DMD2019-3282
Deakyne A, Gaasedelen E, Iaizzo PA. A deep learning approach for the automatic identification of the left atrium within CT scans. In Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019. American Society of Mechanical Engineers (ASME). 2019. (Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019). https://doi.org/10.1115/DMD2019-3282
Deakyne, Alex ; Gaasedelen, Erik ; Iaizzo, Paul A. / A deep learning approach for the automatic identification of the left atrium within CT scans. Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019. American Society of Mechanical Engineers (ASME), 2019. (Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019).
@inproceedings{c6a6c2d6a2bd4c919abe8fd5036453b2,
title = "A deep learning approach for the automatic identification of the left atrium within CT scans",
abstract = "Recent advancements in deep learning have led to the possibility of increased performance in computer vision tools. A major development has been the usage of Convolutional Neural Networks (CNN) for automatically detecting features within a given image. Architectures such as YOLO1 have obtained incredibly high performances for the real-time detection of every-day objects within images. However to date, there have been few reports of deep learning applied to detect anatomical features within CT scans; especially those within the cardiovascular space. We propose here an automatic anatomical feature detection pipeline for identifying the features of the left atrium using a CNN. Slices of CT scans were fed into a single neural network which predicted the four bounding box coordinates that encapsulate the left atrium. The network can be optimized end-to-end and generate predictions at great speed, achieving a validation smooth L1 loss of 11.95 when predicting the left atrial bounding boxes.",
keywords = "CNN, Computer Vision, Deep Learning, Object Detection",
author = "Alex Deakyne and Erik Gaasedelen and Iaizzo, {Paul A.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1115/DMD2019-3282",
language = "English (US)",
series = "Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019",

}

TY - GEN

T1 - A deep learning approach for the automatic identification of the left atrium within CT scans

AU - Deakyne, Alex

AU - Gaasedelen, Erik

AU - Iaizzo, Paul A.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Recent advancements in deep learning have led to the possibility of increased performance in computer vision tools. A major development has been the usage of Convolutional Neural Networks (CNN) for automatically detecting features within a given image. Architectures such as YOLO1 have obtained incredibly high performances for the real-time detection of every-day objects within images. However to date, there have been few reports of deep learning applied to detect anatomical features within CT scans; especially those within the cardiovascular space. We propose here an automatic anatomical feature detection pipeline for identifying the features of the left atrium using a CNN. Slices of CT scans were fed into a single neural network which predicted the four bounding box coordinates that encapsulate the left atrium. The network can be optimized end-to-end and generate predictions at great speed, achieving a validation smooth L1 loss of 11.95 when predicting the left atrial bounding boxes.

AB - Recent advancements in deep learning have led to the possibility of increased performance in computer vision tools. A major development has been the usage of Convolutional Neural Networks (CNN) for automatically detecting features within a given image. Architectures such as YOLO1 have obtained incredibly high performances for the real-time detection of every-day objects within images. However to date, there have been few reports of deep learning applied to detect anatomical features within CT scans; especially those within the cardiovascular space. We propose here an automatic anatomical feature detection pipeline for identifying the features of the left atrium using a CNN. Slices of CT scans were fed into a single neural network which predicted the four bounding box coordinates that encapsulate the left atrium. The network can be optimized end-to-end and generate predictions at great speed, achieving a validation smooth L1 loss of 11.95 when predicting the left atrial bounding boxes.

KW - CNN

KW - Computer Vision

KW - Deep Learning

KW - Object Detection

UR - http://www.scopus.com/inward/record.url?scp=85073887426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073887426&partnerID=8YFLogxK

U2 - 10.1115/DMD2019-3282

DO - 10.1115/DMD2019-3282

M3 - Conference contribution

AN - SCOPUS:85073887426

T3 - Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019

BT - Frontiers in Biomedical Devices, BIOMED - 2019 Design of Medical Devices Conference, DMD 2019

PB - American Society of Mechanical Engineers (ASME)

ER -