Azarmehr, Neda, Ye, Xujiong, Janan, Faraz , Howard, James P, Francis, Darrel P and Zolgharni, Massoud (2019) Automated Segmentation of Left Ventricle in 2D echocardiography using deep learning. In: Medical Imaging with Deep Learning 2019, 8-10th July 2019, London.
Full content URL: https://openreview.net/pdf?id=Sye8klvmcN
![]() | There is a more recent version of this item available. |
Documents |
|
![]() |
PDF
1f97b985d34d2e6695e386fa6e03158ea3166a01.pdf - Whole Document Available under License Creative Commons Attribution 4.0 International. 374kB |
Item Type: | Conference or Workshop contribution (Paper) |
---|---|
Item Status: | Live Archive |
Abstract
Following the successful application of the U-Net to medical images, there have been different encoder-decoder models proposed as an improvement to the original U-Net for segmenting echocardiographic images. This study aims to examine the performance of the state-of-the-art proposed models claimed to have better accuracies, as well as the original U-Net model by applying them to an independent dataset of patients to segment the endocardium of the Left Ventricle in 2D automatically. The prediction outputs of the models are used to evaluate the performance of the models by comparing the automated results against the expert annotations (gold standard). Our results reveal that the original U-Net model outperforms other models by achieving an average Dice coefficient of 0.92±0.05, and Hausdorff distance of 3.97±0.82.
Keywords: | Echocardiography, Segmentation, Deep Learning |
---|---|
Subjects: | G Mathematical and Computer Sciences > G760 Machine Learning G Mathematical and Computer Sciences > G121 Mechanics (Mathematical) G Mathematical and Computer Sciences > G400 Computer Science |
Divisions: | College of Science > School of Computer Science |
Related URLs: | |
ID Code: | 38038 |
Deposited On: | 30 Oct 2019 13:59 |
Available Versions of this Item
- Automated Segmentation of Left Ventricle in 2D echocardiography using deep learning. (deposited 30 Oct 2019 13:59) [Currently Displayed]
Repository Staff Only: item control page