Contour-constrained Branch U-Net for Accurate Left Ventricular Segmentation in Echocardiography

Overview

Journal Med Biol Eng Comput

Publisher Springer

Specialties Biomedical Engineering
Medical Informatics

Date 2024 Oct 17

PMID 39417962

Authors

Mingjun Qu

Jinzhu Yang

Honghe Li

Yiqiu Qi

Qi Yu

Affiliations

Soon will be listed here.

Abstract

Using echocardiography to assess the left ventricular function is one of the most crucial cardiac examinations in clinical diagnosis, and LV segmentation plays a particularly vital role in medical image processing as many important clinical diagnostic parameters are derived from the segmentation results, such as ejection function. However, echocardiography typically has a lower resolution and contains a significant amount of noise and motion artifacts, making it a challenge to accurate segmentation, especially in the region of the cardiac chamber boundary, which significantly restricts the accurate calculation of subsequent clinical parameters. In this paper, our goal is to achieve accurate LV segmentation through a simplified approach by introducing a branch sub-network into the decoder of the traditional U-Net. Specifically, we employed the LV contour features to supervise the branch decoding process and used a cross attention module to facilitate the interaction relationship between the branch and the original decoding process, thereby improving the segmentation performance in the region LV boundaries. In the experiments, the proposed branch U-Net (BU-Net) demonstrated superior performance on CAMUS and EchoNet-dynamic public echocardiography segmentation datasets in comparison to state-of-the-art segmentation models, without the need for complex residual connections or transformer-based architectures. Our codes are publicly available at Anonymous Github https://anonymous.4open.science/r/Anoymous_two-BFF2/ .

References

Shah K, Xu H, Matsouaka R, Bhatt D, Heidenreich P, Hernandez A . Heart Failure With Preserved, Borderline, and Reduced Ejection Fraction: 5-Year Outcomes. J Am Coll Cardiol. 2017; 70(20):2476-2486. DOI: 10.1016/j.jacc.2017.08.074. View

Schiller N, Shah P, Crawford M, DeMaria A, Devereux R, FEIGENBAUM H . Recommendations for quantitation of the left ventricle by two-dimensional echocardiography. American Society of Echocardiography Committee on Standards, Subcommittee on Quantitation of Two-Dimensional Echocardiograms. J Am Soc Echocardiogr. 1989; 2(5):358-67. DOI: 10.1016/s0894-7317(89)80014-8. View

Clough J, Byrne N, Oksuz I, Zimmer V, Schnabel J, King A . A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology. IEEE Trans Pattern Anal Mach Intell. 2020; 44(12):8766-8778. PMC: 9721526. DOI: 10.1109/TPAMI.2020.3013679. View

Bougourzi F, Distante C, Dornaika F, Taleb-Ahmed A . PDAtt-Unet: Pyramid Dual-Decoder Attention Unet for Covid-19 infection segmentation from CT-scans. Med Image Anal. 2023; 86:102797. PMC: 10027962. DOI: 10.1016/j.media.2023.102797. View

Liu R, Pu W, Nan H, Zou Y . Retina image segmentation using the three-path Unet model. Sci Rep. 2023; 13(1):22579. PMC: 10730848. DOI: 10.1038/s41598-023-50141-0. View

Zhang H, Yang X, Li D, Cui Y, Zhao J, Qiu S . Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior. J Biomed Inform. 2023; 139:104304. DOI: 10.1016/j.jbi.2023.104304. View

Li X, Chen H, Qi X, Dou Q, Fu C, Heng P . H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes. IEEE Trans Med Imaging. 2018; 37(12):2663-2674. DOI: 10.1109/TMI.2018.2845918. View

Yan W, Wang Y, van der Geest R, Tao Q . Cine MRI analysis by deep learning of optical flow: Adding the temporal dimension. Comput Biol Med. 2019; 111:103356. DOI: 10.1016/j.compbiomed.2019.103356. View

Moradi S, Oghli M, Alizadehasl A, Shiri I, Oveisi N, Oveisi M . MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography. Phys Med. 2019; 67:58-69. DOI: 10.1016/j.ejmp.2019.10.001. View

10.

Liu F, Wang K, Liu D, Yang X, Tian J . Deep pyramid local attention neural network for cardiac structure segmentation in two-dimensional echocardiography. Med Image Anal. 2020; 67:101873. DOI: 10.1016/j.media.2020.101873. View

11.

Guo L, Lei B, Chen W, Du J, Frangi A, Qin J . Dual attention enhancement feature fusion network for segmentation and quantitative analysis of paediatric echocardiography. Med Image Anal. 2021; 71:102042. DOI: 10.1016/j.media.2021.102042. View

12.

Wu B, Fang Y, Lai X . Left ventricle automatic segmentation in cardiac MRI using a combined CNN and U-net approach. Comput Med Imaging Graph. 2020; 82:101719. DOI: 10.1016/j.compmedimag.2020.101719. View

13.

Song P, Li J, Fan H, Fan L . TGDAUNet: Transformer and GCNN based dual-branch attention UNet for medical image segmentation. Comput Biol Med. 2023; 167:107583. DOI: 10.1016/j.compbiomed.2023.107583. View

14.

Leclerc S, Smistad E, Pedrosa J, Ostvik A, Cervenansky F, Espinosa F . Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography. IEEE Trans Med Imaging. 2019; 38(9):2198-2210. DOI: 10.1109/TMI.2019.2900516. View

15.

Pedrosa J, Queiros S, Bernard O, Engvall J, Edvardsen T, Nagel E . Fast and Fully Automatic Left Ventricular Segmentation and Tracking in Echocardiography Using Shape-Based B-Spline Explicit Active Surfaces. IEEE Trans Med Imaging. 2017; 36(11):2287-2296. DOI: 10.1109/TMI.2017.2734959. View

16.

Messaoudi H, Belaid A, Ben Salem D, Conze P . Cross-dimensional transfer learning in medical image segmentation with deep learning. Med Image Anal. 2023; 88:102868. DOI: 10.1016/j.media.2023.102868. View