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

Background: The assessment of left ventricular (LV) function by myocardial perfusion SPECT (MPS) relies on accurate myocardial segmentation. The purpose of this paper is to develop and validate a new method incorporating deep learning with shape priors to accurately extract the LV myocardium for automatic measurement of LV functional parameters. Methods: A segmentation architecture that integrates a three-dimensional (3D) V-Net with a shape deformation module was developed. Using the shape priors generated by a dynamic programming (DP) algorithm, the model output was then constrained and guided during the model training for quick convergence and improved performance. A stratified 5-fold cross-validation was used to train and validate our models. Results: Results of our proposed method agree well with those from the ground truth. Our proposed model achieved a Dice similarity coefficient (DSC) of 0.9573(0.0244), 0.9821(0.0137), and 0.9903(0.0041), a Hausdorff distances (HD) of 6.7529(2.7334) mm, 7.2507(3.1952) mm, and 7.6121(3.0134) mm in extracting the endocardium, myocardium, and epicardium, respectively. Conclusion: Our proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV function.

Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images

Background. Functional assessment of right ventricles (RV) using gated myocardial perfusion single-photon emission computed tomography (MPS) heavily relies on the precise extraction of right ventricular contours. In this paper, we present a new deep learning model integrating both the spatial and temporal features in SPECT images to perform the segmentation of RV epicardium and endocardium. Methods. By integrating the spatial features from each cardiac frame of gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we develop a Spatial-Temporal V-Net (S-T-V-Net) for automatic extraction of RV endocardial and epicardial contours. In the S-T-V-Net, a V-Net is employed to hierarchically extract spatial features, and convolutional long-term short-term memory (ConvLSTM) units are added to the skip-connection pathway to extract the temporal features. The input of the S-T-V-Net is an ECG-gated sequence of the SPECT images and the output is the probability map of the endocardial or epicardial masks. A Dice similarity coefficient (DSC) loss which penalizes the discrepancy between the model prediction and the ground truth is adopted to optimize the segmentation model. Results. Our segmentation model was trained and validated on a retrospective dataset with 34 subjects, and the cardiac cycle of each subject was divided into 8 gates. The proposed ST-V-Net achieved a DSC of 0.7924 and 0.8227 for the RV endocardium and epicardium, respectively. The mean absolute error, the mean squared error, and the Pearson correlation coefficient of the RV ejection fraction between the ground truth and the model prediction are 0.0907, 0.0130 and 0.8411. Conclusion. The results demonstrate that the proposed ST-V-Net is an effective model for RV segmentation. It has great promise for clinical use in RV functional assessment.