Cover Image

3D shallow deep neural network for fast and precise segmentation of left atrium

Knowledge of the underlying anatomy of the left atrium can promote improved diagnostic protocols and clinical interventions. Hence, an automatic segmentation of the left atrium on magnetic resonance imaging (MRI) can support diagnosis, treatment and surgery planning of heart. However, due to the sma...

Full description

Saved in:
Bibliographic Details
Main Authors: Kausar, Asma, Razzak, Imran, Shapiai, Mohammad Ibrahim, Beheshti, Amin
Format: Article
Published: Springer Science and Business Media Deutschland GmbH 2023
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/107999/
http://dx.doi.org/10.1007/s00530-021-00776-8
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.107999
record_format eprints
spelling my.utm.1079992024-10-16T07:09:46Z http://eprints.utm.my/107999/ 3D shallow deep neural network for fast and precise segmentation of left atrium Kausar, Asma Razzak, Imran Shapiai, Mohammad Ibrahim Beheshti, Amin T Technology (General) Knowledge of the underlying anatomy of the left atrium can promote improved diagnostic protocols and clinical interventions. Hence, an automatic segmentation of the left atrium on magnetic resonance imaging (MRI) can support diagnosis, treatment and surgery planning of heart. However, due to the small size of left atrium with respect to the whole MRI volume, accurate segmentation of left atrium is challenging. Most of the existing deep learning approaches are based on cropping or cascading networks. In this work, we present a novel deep learning architecture for the segmentation of left atrium from MRI volume which incorporates the residual learning based encoder-decoder network. We introduce a loss function and parameter adjustments to deal with the issue of class imbalance and unavailability of large medical imaging dataset. To facilitate the high quality segmentation, we present a three-dimensional multi-scale residual learning based architecture that maintains coarse and fine level features throughout the network. Experimental results have shown a considerable improvement in segmentation performance by surpassing the current benchmarks (especially the winner of Left Atrial Segmentation Challenge-2018) with fewer parameters compared to the state-of-the-art approaches, thus potentially supporting cardiac diagnosis and surgery without adding any extensive pre-processing of input volumes or any post-processing on the base network’s output. Springer Science and Business Media Deutschland GmbH 2023 Article PeerReviewed Kausar, Asma and Razzak, Imran and Shapiai, Mohammad Ibrahim and Beheshti, Amin (2023) 3D shallow deep neural network for fast and precise segmentation of left atrium. Multimedia Systems, 29 (3). pp. 1739-1749. ISSN 0942-4962 http://dx.doi.org/10.1007/s00530-021-00776-8 DOI : 10.1002/gch2.202300047
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Kausar, Asma
Razzak, Imran
Shapiai, Mohammad Ibrahim
Beheshti, Amin
3D shallow deep neural network for fast and precise segmentation of left atrium
description Knowledge of the underlying anatomy of the left atrium can promote improved diagnostic protocols and clinical interventions. Hence, an automatic segmentation of the left atrium on magnetic resonance imaging (MRI) can support diagnosis, treatment and surgery planning of heart. However, due to the small size of left atrium with respect to the whole MRI volume, accurate segmentation of left atrium is challenging. Most of the existing deep learning approaches are based on cropping or cascading networks. In this work, we present a novel deep learning architecture for the segmentation of left atrium from MRI volume which incorporates the residual learning based encoder-decoder network. We introduce a loss function and parameter adjustments to deal with the issue of class imbalance and unavailability of large medical imaging dataset. To facilitate the high quality segmentation, we present a three-dimensional multi-scale residual learning based architecture that maintains coarse and fine level features throughout the network. Experimental results have shown a considerable improvement in segmentation performance by surpassing the current benchmarks (especially the winner of Left Atrial Segmentation Challenge-2018) with fewer parameters compared to the state-of-the-art approaches, thus potentially supporting cardiac diagnosis and surgery without adding any extensive pre-processing of input volumes or any post-processing on the base network’s output.
format Article
author Kausar, Asma
Razzak, Imran
Shapiai, Mohammad Ibrahim
Beheshti, Amin
author_facet Kausar, Asma
Razzak, Imran
Shapiai, Mohammad Ibrahim
Beheshti, Amin
author_sort Kausar, Asma
title 3D shallow deep neural network for fast and precise segmentation of left atrium
title_short 3D shallow deep neural network for fast and precise segmentation of left atrium
title_full 3D shallow deep neural network for fast and precise segmentation of left atrium
title_fullStr 3D shallow deep neural network for fast and precise segmentation of left atrium
title_full_unstemmed 3D shallow deep neural network for fast and precise segmentation of left atrium
title_sort 3d shallow deep neural network for fast and precise segmentation of left atrium
publisher Springer Science and Business Media Deutschland GmbH
publishDate 2023
url http://eprints.utm.my/107999/
http://dx.doi.org/10.1007/s00530-021-00776-8
_version_ 1814043576775999488
score 13.211869

Similar Items