# Difference between revisions of "Publications/zhao.19.stacom"

### From LRDE

(Created page with "{{Publication | published = true | date = 2020-02-07 | authors = Zhou Zhao, Nicolas Boutry, Élodie Puybareau, Thierry Géraud | title = A Two-Stage Temporal-Like Fully Convol...") |
|||

Line 10: | Line 10: | ||

| volume = 12009 |
| volume = 12009 |
||

| pages = 405 to 413 |
| pages = 405 to 413 |
||

− | | abstract = Automatic segmentation of the left ventricle (LV) of a living human heart in a magnetic resonance (MR) image (2D+t) allows to measure some clinical significant indices like the regional wall thicknesses (RWT), cavity dimensions, cavity and myocardium areas, and cardiac phase. Here, we propose a novel framework made of a sequence of two fully convolutional networks (FCN). The first is a modified temporal-like VGG16 (the "localization network") and is used to localize roughly the LV (filled-in) epicardium position in each MR volume. The second FCN is a modified temporal-like VGG16 too, but devoted to segment the LV myocardium and cavity (the "segmentation network"). We evaluate the proposed method with 5-fold-cross-validation on the MICCAI 2019 LV Full Quantification Challenge dataset. For the network used to localize the epicardium, we obtain an average dice index of 0.8953 on validation set. For the segmentation network, we obtain an average dice index of 0.8664 on validation set (there, data augmentation is used). The mean absolute error (MAE) of average cavity and myocardium areas, dimensions, RWT are 114.77~mm |
+ | | abstract = Automatic segmentation of the left ventricle (LV) of a living human heart in a magnetic resonance (MR) image (2D+t) allows to measure some clinical significant indices like the regional wall thicknesses (RWT), cavity dimensions, cavity and myocardium areas, and cardiac phase. Here, we propose a novel framework made of a sequence of two fully convolutional networks (FCN). The first is a modified temporal-like VGG16 (the "localization network") and is used to localize roughly the LV (filled-in) epicardium position in each MR volume. The second FCN is a modified temporal-like VGG16 too, but devoted to segment the LV myocardium and cavity (the "segmentation network"). We evaluate the proposed method with 5-fold-cross-validation on the MICCAI 2019 LV Full Quantification Challenge dataset. For the network used to localize the epicardium, we obtain an average dice index of 0.8953 on validation set. For the segmentation network, we obtain an average dice index of 0.8664 on validation set (there, data augmentation is used). The mean absolute error (MAE) of average cavity and myocardium areas, dimensions, RWT are <math>114.77~\text{mm}^2</math>; 0.9220~mm; 0.9185~mm respectively. The computation time of the pipeline is less than 2~s for an entire 3D volume. The error rate of phase classification is 7.6364%, which indicates that the proposed approach has a promising performance to estimate all these parameters. |

| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.19.stacom.pdf |
| lrdepaper = http://www.lrde.epita.fr/dload/papers/zhao.19.stacom.pdf |
||

| lrdeprojects = Olena |
| lrdeprojects = Olena |
||

Line 58: | Line 58: | ||

(there, data augmentation is used). The mean absolute error |
(there, data augmentation is used). The mean absolute error |
||

(MAE) of average cavity and myocardium areas, dimensions, |
(MAE) of average cavity and myocardium areas, dimensions, |
||

− | RWT are 114.77~mm |
+ | RWT are $114.77~\text<nowiki>{</nowiki>mm<nowiki>}</nowiki>^2$; 0.9220~mm; 0.9185~mm |

− | The computation time of the pipeline is less |
+ | respectively. The computation time of the pipeline is less |

− | an entire 3D volume. The error rate of phase |
+ | than 2~s for an entire 3D volume. The error rate of phase |

− | is 7.6364\%, which indicates that the |
+ | classification is 7.6364\%, which indicates that the |

− | a promising performance to estimate |
+ | proposed approach has a promising performance to estimate |

+ | all these parameters.<nowiki>}</nowiki> |
||

<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||

## Revision as of 10:29, 7 February 2020

- Authors
- Zhou Zhao, Nicolas Boutry, Élodie Puybareau, Thierry Géraud
- Where
- Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges—10th International Workshop, STACOM 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Revised Selected Papers
- Type
- inproceedings
- Publisher
- Springer
- Projects
- Olena
- Keywords
- Image
- Date
- 2020-02-07

## Abstract

Automatic segmentation of the left ventricle (LV) of a living human heart in a magnetic resonance (MR) image (2D+t) allows to measure some clinical significant indices like the regional wall thicknesses (RWT), cavity dimensions, cavity and myocardium areas, and cardiac phase. Here, we propose a novel framework made of a sequence of two fully convolutional networks (FCN). The first is a modified temporal-like VGG16 (the "localization network") and is used to localize roughly the LV (filled-in) epicardium position in each MR volume. The second FCN is a modified temporal-like VGG16 too, but devoted to segment the LV myocardium and cavity (the "segmentation network"). We evaluate the proposed method with 5-fold-cross-validation on the MICCAI 2019 LV Full Quantification Challenge dataset. For the network used to localize the epicardium, we obtain an average dice index of 0.8953 on validation set. For the segmentation network, we obtain an average dice index of 0.8664 on validation set (there, data augmentation is used). The mean absolute error (MAE) of average cavity and myocardium areas, dimensions, RWT are ; 0.9220~mm; 0.9185~mm respectively. The computation time of the pipeline is less than 2~s for an entire 3D volume. The error rate of phase classification is 7.6364%, which indicates that the proposed approach has a promising performance to estimate all these parameters.

## Documents

## Bibtex (lrde.bib)

@InProceedings{ zhao.19.stacom, author = {Zhou Zhao and Nicolas Boutry and \'Elodie Puybareau and Thierry G\'eraud}, title = {A Two-Stage Temporal-Like Fully Convolutional Network Framework for Left Ventricle Segmentation and Quantification on {MR} Images}, booktitle = {Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges---10th International Workshop, STACOM 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Revised Selected Papers}, year = 2020, editor = {Mihaela Pop and Maxime Sermesant and Oscar Camara and Xiahai Zhuang and Shuo Li and Alistair Young and Tommaso Mansi and Avan Suinesiaputra}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, volume = {12009}, pages = {405--413}, abstract = {Automatic segmentation of the left ventricle (LV) of a living human heart in a magnetic resonance (MR) image (2D+t) allows to measure some clinical significant indices like the regional wall thicknesses (RWT), cavity dimensions, cavity and myocardium areas, and cardiac phase. Here, we propose a novel framework made of a sequence of two fully convolutional networks (FCN). The first is a modified temporal-like VGG16 (the "localization network") and is used to localize roughly the LV (filled-in) epicardium position in each MR volume. The second FCN is a modified temporal-like VGG16 too, but devoted to segment the LV myocardium and cavity (the "segmentation network"). We evaluate the proposed method with 5-fold-cross-validation on the MICCAI 2019 LV Full Quantification Challenge dataset. For the network used to localize the epicardium, we obtain an average dice index of 0.8953 on validation set. For the segmentation network, we obtain an average dice index of 0.8664 on validation set (there, data augmentation is used). The mean absolute error (MAE) of average cavity and myocardium areas, dimensions, RWT are $114.77~\text{mm}^2$; 0.9220~mm; 0.9185~mm respectively. The computation time of the pipeline is less than 2~s for an entire 3D volume. The error rate of phase classification is 7.6364\%, which indicates that the proposed approach has a promising performance to estimate all these parameters.} }