TY - JOUR
T1 - LVNet
T2 - Lightweight Model for Left Ventricle Segmentation for Short Axis Views in Echocardiographic Imaging
AU - Awasthi, Navchetan
AU - Vermeer, Lars
AU - Fixsen, Louis S.
AU - Lopata, Richard G.P.
AU - Pluim, Josien P.W.
N1 - Funding Information:
This work was supported in part by the 4TU Precision Medicine Program through the High Tech for a Sustainable Future, a framework commissioned by the four Universities of Technology of the Netherlands.
Publisher Copyright:
© 2022 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Lightweight segmentation models are becoming more popular for fast diagnosis on small and low cost medical imaging devices. This study focuses on the segmentation of the left ventricle (LV) in cardiac ultrasound (US) images. A new lightweight model [LV network (LVNet)] is proposed for segmentation, which gives the benefits of requiring fewer parameters but with improved segmentation performance in terms of Dice score (DS). The proposed model is compared with state-of-the-art methods, such as UNet, MiniNetV2, and fully convolutional dense dilated network (FCdDN). The model proposed comes with a post-processing pipeline that further enhances the segmentation results. In general, the training is done directly using the segmentation mask as the output and the US image as the input of the model. A new strategy for segmentation is also introduced in addition to the direct training method used. Compared with the UNet model, an improvement in DS performance as high as 5% for segmentation with papillary (WP) muscles was found, while showcasing an improvement of 18.5% when the papillary muscles are excluded. The model proposed requires only 5% of the memory required by a UNet model. LVNet achieves a better trade-off between the number of parameters and its segmentation performance as compared with other conventional models. The developed codes are available at https://github.com/navchetanawasthi/Left_Ventricle_Segmentation.
AB - Lightweight segmentation models are becoming more popular for fast diagnosis on small and low cost medical imaging devices. This study focuses on the segmentation of the left ventricle (LV) in cardiac ultrasound (US) images. A new lightweight model [LV network (LVNet)] is proposed for segmentation, which gives the benefits of requiring fewer parameters but with improved segmentation performance in terms of Dice score (DS). The proposed model is compared with state-of-the-art methods, such as UNet, MiniNetV2, and fully convolutional dense dilated network (FCdDN). The model proposed comes with a post-processing pipeline that further enhances the segmentation results. In general, the training is done directly using the segmentation mask as the output and the US image as the input of the model. A new strategy for segmentation is also introduced in addition to the direct training method used. Compared with the UNet model, an improvement in DS performance as high as 5% for segmentation with papillary (WP) muscles was found, while showcasing an improvement of 18.5% when the papillary muscles are excluded. The model proposed requires only 5% of the memory required by a UNet model. LVNet achieves a better trade-off between the number of parameters and its segmentation performance as compared with other conventional models. The developed codes are available at https://github.com/navchetanawasthi/Left_Ventricle_Segmentation.
KW - Deep learning (DL)
KW - lightweight models
KW - neural networks
KW - segmentation
KW - ultrasound (US) imaging
KW - Echocardiography
KW - Image Processing, Computer-Assisted/methods
KW - Ultrasonography
KW - Muscles
KW - Heart Ventricles/diagnostic imaging
UR - http://www.scopus.com/inward/record.url?scp=85128698222&partnerID=8YFLogxK
U2 - 10.1109/TUFFC.2022.3169684
DO - 10.1109/TUFFC.2022.3169684
M3 - Article
C2 - 35452387
AN - SCOPUS:85128698222
SN - 0885-3010
VL - 69
SP - 2115
EP - 2128
JO - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
JF - IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
IS - 6
ER -