A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images

• Published in: Computers in biology and medicine Vol. 160; p. 106954
• Main Authors: Zhu, Fubao, Li, Longxi, Zhao, Jinyu, Zhao, Chen, Tang, Shaojie, Nan, Jiaofen, Li, Yanting, Zhao, Zhongqiang, Shi, Jianzhou, Chen, Zenghong, Han, Chuang, Jiang, Zhixin, Zhou, Weihua
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2023; Elsevier Limited
• Subjects: Accuracy; Algorithms; Cardiovascular disease; Cicatrix; Contours; Correlation coefficients; Datasets; Deep Learning; Dynamic programming; Epicardium; Heart; Heart Ventricles - diagnostic imaging; Heart Ventricles - pathology; Humans; Image processing; Image segmentation; Internal Medicine; Ischemia; Left ventricle; Myocardial perfusion SPECT; Myocardium; Other; Performance evaluation; Perfusion; Quantitative analysis; Retrospective Studies; Segmentation; Single photon emission computed tomography; Software; Stroke Volume; Tomography, Emission-Computed, Single-Photon - methods; Training; V-Net; Ventricle; Ventricular Function, Left; CNN; Segmentation; CAD; Myocardial perfusion SPECT; LVEF; ESV; LV; DP; STN; ROI; Left ventricle; Deep learning; MPS; DSC; EDV; V-Net; DP-ST-V-Net; HD; coronary artery disease; left ventricular ejection fraction; end-diastolic volume; spatial transform network; convolutional neural network; dynamic programming; end-systolic volume; shape-transformation VNet with dynamic programming; Hausdorff distance; region of interest; Dice similarity coefficient
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106954

Accurate segmentation of the left ventricle (LV) is crucial for evaluating myocardial perfusion SPECT (MPS) and assessing LV functions. In this study, a novel method combining deep learning with shape priors was developed and validated to extract the LV myocardium and automatically measure LV functional parameters. The method integrates a three-dimensional (3D) V-Net with a shape deformation module that incorporates shape priors generated by a dynamic programming (DP) algorithm to guide its output during training. A retrospective analysis was performed on an MPS dataset comprising 31 subjects without or with mild ischemia, 32 subjects with moderate ischemia, and 12 subjects with severe ischemia. Myocardial contours were manually annotated as the ground truth. A 5-fold stratified cross-validation was used to train and validate the models. The clinical performance was evaluated by measuring LV end-systolic volume (ESV), end-diastolic volume (EDV), left ventricular ejection fraction (LVEF), and scar burden from the extracted myocardial contours. There were excellent agreements between segmentation results by our proposed model and those from the ground truth, with a Dice similarity coefficient (DSC) of 0.9573 ± 0.0244, 0.9821 ± 0.0137, and 0.9903 ± 0.0041, as well as Hausdorff distances (HD) of 6.7529 ± 2.7334 mm, 7.2507 ± 3.1952 mm, and 7.6121 ± 3.0134 mm in extracting the LV endocardium, myocardium, and epicardium, respectively. Furthermore, the correlation coefficients between LVEF, ESV, EDV, stress scar burden, and rest scar burden measured from our model results and the ground truth were 0.92, 0.958, 0.952, 0.972, and 0.958, respectively. The proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV functions. [Display omitted] •Our approach incorporates prior knowledge of myocardial contours generated by a dynamic programing algorithm into a V-Net.•Shape prior in spatial transform network leads to a significant improvement in the accuracy of left-ventricular segmentation.•Our results confirmed the effectiveness of incorporating prior knowledge with deep learning for medical image segmentation.