Deep convolutional neural networks for automatic segmentation of left ventricle cavity from cardiac magnetic resonance images. Issue 8 (2nd August 2017)

• Record Type: Journal Article
• Authors: Yang, Xulei; Zeng, Zeng; Yi, Su
• Is Part Of: IET computer vision. Volume 11:Issue 8(2017)
• Page Start: 643
• Page End: 649
• Publication Date: 2017-08-02
• Subjects: biomedical MRI -- cardiovascular system -- convolution -- image segmentation -- learning (artificial intelligence) -- medical image processing -- neural nets -- object detection -- regression analysis; deep convolutional neural networks -- automatic left ventricle cavity segmentation framework -- cardiac magnetic resonance images -- deep learning approaches -- object segmentation framework -- localisation-segmentation framework -- regression model based convolutional neural networks -- deep neural network based U-Net architecture -- Dice loss function -- public endocardium-annotated CMR datasets; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2016.0482
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : This work conducts a feasibility study of deep learning approaches for automatic segmentation of left ventricle (LV) cavity from cardiac magnetic resonance (CMR) images. Automatic LV cavity segmentation is a challenging task, partially due to the small size of the object as compared to the large CMR image background, especially at the apex. To cater for small object segmentation, the authors present a localisation‐segmentation framework, to first locate the object in the large full image, then segment the object within the small cropped region of interest. The localisation is performed by a deep regression model based on convolutional neural networks, while the segmentation is done by the deep neural networks based on U‐Net architecture. They also employ the Dice loss function for the training process of the segmentation models, to investigate its effects on the segmentation performance. The deep learning models are trained and evaluated by using public endocardium‐annotated CMR datasets from York University and MICCAI 2009 LV Challenge websites. The average dice metric values of the authors' proposed framework are 0.91 and 0.93, respectively, on these two databases. These results are promising as compared to the best results achieved by the current state‐of‐art, which shows the potentials of deep learning approaches for this particular application.