This study aims to improve Left Ventricle (LV) quantification accuracy and efficiency in cardiac disease diagnosis using automated image analysis.
Methods:
We propose XNet, a deep learning framework based on an extended convolutional network with multi-task learning. XNet segments LV structures estimates Regional Wall Thickness (RWT) and classifies cardiac phases (systole/diastole) from 2D Positron Emission Tomography (PET) sequences. The model integrates spatial and temporal features and is trained on augmented PET datasets.
Results:
XNet outperformed existing methods, achieving a mean absolute error of 1.5 mm, classification accuracy of 98.5%, validation accuracy of 97.2%, and a loss of 0.048. It showed strong performance in low-contrast and varied-quality image conditions, reducing myocardial area estimation error by 38.6% compared to baseline models.
Conclusion:
XNet provides a robust, accurate, and fully automated solution for LV quantification, offering a reliable tool to support clinical diagnosis and treatment planning in cardiovascular care.
PengPLekadirKGooyaA, et al.A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. Magn Reson Mater Phys Biol Med2016; 29: 155–195.
2.
TavakoliVAminiAA. A survey of shaped-based registration and segmentation techniques for cardiac images. Comput Vis Image Understand2013; 117: 966–989.
3.
GreenspanHVan GinnekenBSummersRM. Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique. IEEE Trans Med Imaging2016; 35: 1153–1159.
4.
MazurowskiMABudaMSahaA, et al.Deep learning in radiology: an overview of the concepts and a survey of the state of the art focusing on MRI. J Magn Reson Imaging2019; 49: 939–954.
5.
KarimRHousdenRJBalasubramaniamM, et al.Evaluation of current algorithms for segmentation of scar tissue from late gadolinium enhancement cardiovascular magnetic resonance of the left atrium: an open-access grand challenge. J Cardiovasc Magn Reson2013; 15: 1–12.
6.
KarimRBhagirathPClausP, et al.Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late gadolinium enhancement MR images. Med Image Anal2016; 30: 95–107.
7.
PaceDFDalcaAVGevaT, et al.Interactive whole-heart segmentation in congenital heart disease. Med Image Comput Comput Assist Interv2015; 9350: 80–88.
8.
BernardOLalandeAZottiC, et al.Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: are the problem solved?. IEEE TransMed Imaging2018; 37: 2514–2525.
9.
ZhuangXLiLPayerC, et al.Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Med Image Anal2019; 58: 1–21.
10.
BernardOBoschJGHeydeB, et al.Standardized evaluation system for left ventricular segmentation algorithms in 3D echocardiography. IEEE Trans Med Imaging2016; 35: 967–977.
11.
TranPV. A fully convolutional neural network for cardiac segmentation in short-axis MRI. Arxiv, 2016.
12.
DuanJBelloGSchlemperJ, et al.Automatic 3D bi-ventricular segmentation of cardiac images by a shape-constrained multi-task deep learning approach. IEEE Trans Med Imaging2019; 38: 2151–2164.
13.
DouQOuyangCChenC, et al.Unsupervised cross-modality domain adaptation of ConvNets for biomedical image segmentations with adversarial loss. In: International joint conferences on artificial intelligence, 2018.
14.
DouQOuyangCChenC, et al.PnPAdaNet: plug-and-play adversarial domain adaptation network at unpaired cross-modality cardiac segmentation. IEEE Access2019; 7: 99065–99076.
15.
ÇiçekÖAbdulkadirALienkampSS, et al.3D UNet: learning dense volumetric segmentation from sparse annotation. In: 19th international conference on medical image computing and computer-assisted intervention—MICCAI, 2016, Cham: Springer.
16.
LongJShelhamerEDarrellT. Fully convolutional networks for semantic segmentation. In: Conference on computer vision and pattern recognition. Boston, MA, USA: IEEE. 2015.
17.
HuJShenLSunG. Squeeze-and-excitation networks. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR, 2018. Salt Lake City, UT: IEEE Computer Society, 2018.
18.
ChenSMaKZhengY. Med3D: transfer learning for 3D medical image analysis. arxiv, 2019.
19.
ZhengQDelingetteHAyacheN. Explainable cardiac pathology classification on cine MRI with motion characterization by semisupervised learning of apparent flow. Med Image Anal2019; 56: 80–95.
20.
YangHSunJLiH, et al.Deep fusion net for multi-atlas segmentation: application to cardiac MR images. In: 19th international conference on medical image computing and computer-assisted intervention— MICCAI (eds S Ourselin, L Joskowicz, MR Sabuncu, GB Ünal and W Wells), 2016. Athens: Springer International Publishing, 2016.
21.
XiongZFedorovVVFuX, et al.Fully automatic left atrium segmentation from late gadolinium-enhanced magnetic resonance imaging using a dual fully convolutional neural network. IEEE Trans Med Imaging2019; 38: 515–524.
22.
YangGZhuangXKhanH, et al.Fully automatic segmentation and objective assessment of atrial scars for long-standing persistent atrial fibrillation patients using late gadolinium-enhanced MRI. Med Phys2018; 45: 1562–1576.
23.
XuCXuLGaoZ, et al.Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture. Med Image Anal2018; 50: 82–94.
24.
ZhengQDelingetteHDuchateauN, et al.3-D consistent and robust segmentation of cardiac images by deep learning with spatial propagation. IEEE Trans Med Imaging2018; 37: 2137–2148.
25.
BaiWSuzukiHQinC, et al.Recurrent neural networks for aortic image sequence segmentation with sparse annotations. In: 21st international conference on medical image computing and computer assisted intervention—MICCAI, 2018. Cham: Springer.
26.
YuLChengJZDouQ, et al.Automatic 3D cardiovascular MR segmentation with densely connected volumetric ConvNets. In: 20th international conference on medical image computing and computer assisted intervention—MICCAI, 2017.
27.
ZreikMLeinerTDe VosBD, et al.Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks. In: International symposium on biomedical imaging, 2016, Piscataway, NJ, USA: IEEE.
28.
MoeskopsPWolterinkJMVan Der VeldenBH, et al.Deep learning for multi-task medical image segmentation in multiple modalities. Med Image Comput Comput Assist Interv2016; 19: 478–486. Springer International Publishing.
29.
WolterinkJMLeinerTde VosBD, et al.Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks. Med Image Anal2016; 34: 123–136.
30.
LeclercSSmistadEPedrosaJ, et al.Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging2019; 38: 2198–2210.
31.
CarneiroGNascimentoJC. Combining multiple dynamic models and deep learning architectures for tracking the left ventricle endocardium in ultrasound data. IEEE Trans Pattern Anal Mach Intell2013; 35: 2591–2603.
32.
HuangMZouJZhangY, et al.Efficient click-based interactive segmentation for medical images with improved Plain-ViT. IEEE J Biomed Health Inform2024; 28: 1362–1374.
33.
HuangMZhangXSBhattiUA, et al.An interpretable approach using hybrid graph networks and explainable AI for intelligent diagnosis recommendations in chronic disease care. Biomed Signal Process Control2024; 91: 105913.
34.
NizamaniAHChenZNizamaniAA, et al.Advance brain tumor segmentation using feature fusion methods with deep U-Net model with CNN for MRI data. J King Saud Univ Comput Inf Sci2023; 35: 101793.
35.
BhattiUAHuangMNeira-MolinaH, et al.MFFCG – multi-feature fusion for hyperspectral image classification using graph attention network. Expert Syst Appl2023; 229: 120496.
36.
BhattiUATangHWuG, et al.Deep learning with graph convolutional networks: an overview and latest applications in computational intelligence. Int J Intell Syst2023; 2023: 8342104.
