Abstract
Deep learning methods are showing progressive development in the medical imaging field. The accuracy of segmentation is improving challengingly with various deep techniques. Cardiac imaging is a very useful modality to evaluate functional analysis of the right ventricle. We propose an integrated model with the learning approach and Active Contour Method in this paper. We have customized UNet architecture on the basis of performance parameters such as dice metric and Haussdorff distance, training accuracy and testing accuracy etc. with MICCAI 2012 RVSC data. Six layer (6L)-UNet architecture was selected for learning the model. The predicted results of UNet are given to active contour model. These are considered as seed points to extract RV contours. Thus, our model replaces the semi-automatic active contour method into fully automatic segmentation method. It shows promising average results of dice metric and Haussdorff distance such as 0.9 and 2 mm. The active contour method is significant to remove undesired surroundingsĀ from extracted ROI.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kot et al. (2020) U-net and active contour methods for brain tumour segmentation and visualization. IEEE, 978-1-7281-6926-2/20
Petitjean C, Dacher J (2011) A review of segmentation methods in short axis cardiac MR images. Med Image Anal
Punithakumar K, Noga M, Boulanger P (2013) Cardiac right ventricular segmentation via point correspondence. In: 35th Annual international conference, IEEE EMBS, pp 4010ā4013
Zhang H et al (2010) 4-D cardiac MR image analysis: left and right ventricular morphology and function. IEEE Trans Med Imaging 29(2)
Haddad et al (2008) Right ventricular function in cardiovascular disease part I: anatomy physiology aging and functional assessment of the right ventricle. Circulation 117(11):1436ā1448
Guo et al. (2018) Local motion intensity clustering (LMIC) model for segmentation of right ventricle in cardiac MRI images. IEEE J Biomed Health Informatics 10:1109
Rai et al (2020) Integrating deep learning with active contour models in remote sensing image segmentation. IEEE, 978-1-7281-6044-3/20
Giannakidis A, Kamnitsas K (2016) Fast fully automatic segmentation of the severely abnormal human right ventricle from cardiovascular magnetic resonance images using a multi-scale 3D convolutional neural network. IEEE Comput Soc 42ā46
Wang Z et al (2014) Direct estimation of cardiac biventricular volumes with an adapted Bayesian formulation. IEEE Trans Biomed Eng 61(4)
Tarroni G et al (2013) Near-automated 3D segmentation of left and right ventricles on magnetic resonance images. In: 8th International symposium on image and signal processing and analysis, pp 522ā527
Bai et al (2015) A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion. MedIA Image Anal 26(1):133ā145
Bernard et al (2016) Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography. IEEE Trans Med Imag 35(4):967ā977
Peng et al (2016) A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. Magn Reson Mater Phy. Springer 29:155ā195
Yang et al (2013) Right ventricle segmentation by temporal information constrained gradient vector flow. In: IEEE International conference on systems, man, and cybernetics, pp 2551ā2555
Bai W et al (2013) A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: application to cardiac MR images. IEEE Trans Med Imaging 32(7)
Avendi M, Kheradvar A, Jafarkhani H (2016) A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. MedIA Image Anal 30:108ā119
Yang et al (2019) A deep learning segmentation approach in free-breathing real-time cardiac magnetic resonance imaging. Hindawi, BioMed Research International
Zotti et al. (2018) Convolutional neural network with shape prior applied to cardiac MRI segmentation. IEEE J Biomed Health Informat. https://doi.org/10.1109/JBHI.2018.2865450
Li et al (2018) Dilated-inception net: multi-scale feature aggregation for cardiac right ventricle segmentation. IEEE, pp 0018ā9294 (c)
Chen et al (2020) Deep learning for cardiac image segmentation: a review. Front Cardiovascul Med. https://doi.org/10.3389/fcvm.2020.00025
Zheng et al (2018) 3D consistent & robust segmentation of cardiac images by deep learning with spatial propagation. IEEE Trans Med Imaging. https://doi.org/10.1109/tmi.2018.2820742
Zhou et al (2019) A review: deep learning for medical image segmentation using multi-modality fusion. 2590ā0056, Array 3ā4, 100004
Bhan A, Goyal A, Ray V (2015) Fast fully automatic multiframe segmentation of left ventricle in cardiac MRI images using local adaptive K-means clustering and connected component labeling. In: 2nd International conference on signal processing and integrated networks
Emad O, Yassine I, Fahmy A (2015) Automatic localization of the left ventricle in cardiac MRI images using deep learning. IEEE, pp 683ā686
Petitjean et al (2015) Right ventricle segmentation from cardiac MRI: A collation study. Med Image Anal 19:187ā202
Kermani et al (2020) NF-RCNN: heart localization and right ventricle wall motion abnormality detection in cardiac MRI. Elsevier. Physica Medica 70
Kumar P, Noga M, Boulanger P (2013) Cardiac right ventricular segmentation via point correspondence. In: IEEE EMBS, 35th Annual international conference, pp 4010ā4013
Cicek et al (2016) 3D U-net: learning dense volumetric segmentation from sparse annotation. In: Medical image computing and computer-assisted interventionāMICCAI 2016. Lecture notes in computer science, vol 9901. Springer, Cham. https://doi.org/10.1007/978-3-319-46723-8_49
Zhu et al (2013) Automatic delineation of myocardial wall from CT images via shape segmentation and variational region growing. IEEE Trans Biomed Eng 60(10):2887ā2895
Li et al (2011) A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans Image Process 20(7):2007ā2016
Dou et al (2017) 3D deeply supervised network for automated segmentation of volumetric medical images. Elsevier, Medical Image Analysis, pp 40ā54
Lianyu et al (2021) Unsupervised segmentation framework with active contour models for cine cardiac MRI. IEEE. https://doi.org/10.1109/ICIP42928.2021.9506229
Kass M, Witkin A, Terzopoulo D (1988) Snakes: active contour model. Int J Comput Vision 321ā331
Nosrati M, Hamarneh G (2016) Incorporating prior knowledge in medical image segmentation: a survey. arxiv.org/abs/1607.01092
Avendi M, Kheradvar A, Jafarkhani H (2017) Automatic segmentation of the right ventricle from cardiac MRI using a learning-based approach. Magnet Resonance Med. Wiley, New York, NY, USA. https://doi.org/10.1002/mrm.26631
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Abhijit Yadav, A., Ganorkar, S.R. (2023). Improving Right Ventricle Contouring in Cardiac MR Images Using Integrated Approach for Small Datasets. In: Pandit, M., Gaur, M.K., Kumar, S. (eds) Artificial Intelligence and Sustainable Computing. ICSISCET 2022. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-99-1431-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-1431-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1430-2
Online ISBN: 978-981-99-1431-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)