Left Atrial Segmentation in a Few Seconds Using Fully Convolutional Network and Transfer Learning

Élodie Puybareau (1) , Zhao Zhou (2, 1) , Younes Khoudli (1) , Edwin Carlinet (1) , Yongchao Xu (1, 2) , Jérôme Lacotte , Thierry Géraud (1)

1 LRDE - Laboratoire de Recherche et de Développement de l'EPITA
2 HUST - Huazhong University of Science and Technology [Wuhan]

In this paper, we propose a fast automatic method that segments left atrial cavity from 3D GE-MRIs without any manual assistance , using a fully convolutional network (FCN) and transfer learning. This FCN is the base network of VGG-16, pre-trained on ImageNet for natural image classification, and fine tuned with the training dataset of the MICCAI 2018 Atrial Segmentation Challenge. It relies on the "pseudo-3D" method published at ICIP 2017, which allows for segmenting objects from 2D color images which contain 3D information of MRI volumes. For each n th slice of the volume to segment, we consider three images, corresponding to the (n − 1) th , n th , and (n + 1) th slices of the original volume. These three gray-level 2D images are assembled to form a 2D RGB color image (one image per channel). This image is the input of the FCN to obtain a 2D segmentation of the n th slice. We process all slices, then stack the results to form the 3D output segmentation. With such a technique, the segmentation of the left atrial cavity on a 3D volume takes only a few seconds. We reached a dice of 0.911 on the training set.

Domaines: Traitement des images [eess.IV]

Élodie Puybareau, Zhao Zhou, Younes Khoudli, Edwin Carlinet, Yongchao Xu, et al.. Left Atrial Segmentation in a Few Seconds Using Fully Convolutional Network and Transfer Learning. Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges --- 9th International Workshop, STACOM 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, pp.339-347, 2019, ⟨10.1007/978-3-030-12029-0_37⟩. ⟨hal-02176449⟩