16
IRUS TotalDownloads
Altmetric
2D-3D Fully convolutional neural networks for cardiac MR segmentation
File | Description | Size | Format | |
---|---|---|---|---|
1707.09813v1.pdf | Accepted version | 659.62 kB | Adobe PDF | View/Open |
Title: | 2D-3D Fully convolutional neural networks for cardiac MR segmentation |
Authors: | Patravali, J Jain, S Chilamkurthy, S |
Item Type: | Conference Paper |
Abstract: | In this paper, we develop a 2D and 3D segmentation pipelines for fully automated cardiac MR image segmentation using Deep Convolutional Neural Networks (CNN). Our models are trained end-to-end from scratch using the ACD Challenge 2017 dataset comprising of 100 studies, each containing Cardiac MR images in End Diastole and End Systole phase. We show that both our segmentation models achieve near state-of-the-art performance scores in terms of distance metrics and have convincing accuracy in terms of clinical parameters. A comparative analysis is provided by introducing a novel dice loss function and its combination with cross entropy loss. By exploring different network structures and comprehensive experiments, we discuss several key insights to obtain optimal model performance, which also is central to the theme of this challenge. |
Issue Date: | 15-Mar-2019 |
Date of Acceptance: | 10-Sep-2017 |
URI: | http://hdl.handle.net/10044/1/71234 |
DOI: | https://doi.org/10.1007/978-3-319-75541-0_14 |
ISBN: | 9783319755403 |
Publisher: | Springer |
Start Page: | 130 |
End Page: | 139 |
Journal / Book Title: | Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges |
Volume: | 10663 |
Copyright Statement: | © 2018 Springer International Publishing AG. |
Conference Name: | Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges |
Keywords: | cs.CV cs.CV cs.CV cs.CV |
Notes: | Accepted in STACOM '17 |
Start Date: | 2017-09-10 |
Finish Date: | 2017-09-14 |
Conference Place: | Quebec City, Canada |
Online Publication Date: | 2018-03-15 |
Appears in Collections: | Computing Faculty of Engineering |