Key result
Unet++ outperforms standard architectures for LV ultrasound segmentation with a ~91% Dice coefficient.
Why the study?
Accurate detection of internal left ventricular endocardial boundaries is critical, but standard Unet architectures may lose small image details during encoder-to-decoder information transfer.
Does Unet++ improve the segmentation of left ventricular endocardial boundaries on 2D ultrasound images compared to Unet and wide Unet?
Does Unet++ improve the segmentation of left ventricular endocardial boundaries on 2D ultrasound images compared to Unet and wide Unet?
Unet++ provides superior segmentation of the left ventricular endocardial border on 2D echocardiograms compared to standard Unet architectures.
Answers are grounded in this paper and cite their sources.
May improve automated LV segmentation on echocardiography; extends U-Net variants but leaves open prospective validation.
In this paper, we compare common Unet architectures with upgrade version Unet++ for segmentation of the the left ventricular (LV) endocardial boundaries on ultrasound images, which were obtained by ultrasound studies of the heart. The key difference of Unet++ from Unet is the improved skip connections between encoder and decoder by adding convolution blocks. Such implementation allows us to transfer information from encoder to decoder with avoiding to loss of small details of the ultrasound image. It is very important to detect internal boundaries accuratly. We evaluated Unet++ in comparison Unet and wide Unet. The Dice coefficient for the LV segmentation with Unet++ is 91.20%. This result of Unet++ for the LV area segmentation outperforms Unet and wide Unet architectures.
No takes yet. Share an insight, caveat, or question.
Zyuzin et al. (2019) studied Left ventricular endocardial boundary segmentation on ultrasound images. Unet++ architecture vs. Unet and wide Unet architectures was evaluated on Dice coefficient for LV segmentation. Unet++ architecture for left ventricular endocardial boundary segmentation on ultrasound images achieved a Dice coefficient of 91.20%, outperforming standard Unet and wide Unet architectures.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: