Cardiac pathology classification (CPC) based on the volumetric features of three key heart structures can be extracted from segmented cardiac cine magnetic resonance imaging (CMRI) sequences. Machine learning models have recently become very effective tools for handling these problems. Hybrid quantum methods can be employed to enhance the capacities of classical machine learning models. Here, we propose a hybrid quantum multiclass cardiac pathologies classification (HQMC-CPC) model. In the proposed model, discriminative features are extracted to characterize the shape and function of the heart, combining the clinical features, patient features, and radiomics features. In the proposed quantum circuits, all variational parameters are trainable, and the enhanced variational quantum circuit is employed for efficient neural network learning. Using only thirty feature values as input, we propose a hybrid quantum multiclass cardiac pathologies classification (HQMC-CPC) model based on the proposed modified hardware efficient ansatz (MHEA). The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset. Experimental results showed that the proposed HQMC-CPC model is able to classify different cardiac pathologies with an average minimum performance gap of 3.19%. The average maximum improvement in terms of accuracy in cardiac pathology classification is 7.77%. Moreover, the proposed HQMC-CPC speeds up the testing process by around 60% and 40% compared to the classical classifiers and well-established HEA respectively.

Cardiac image segmentation is a critical step in the early detection of cardiovascular disease. The segmentation of the biventricular is a prerequisite for evaluating cardiac function in cardiac magnetic resonance imaging (CMRI). In this paper, a cascaded model CAT-Seg is proposed for segmentation of 3D-CMRI volumes. CAT-Seg addresses the problem of biventricular confusion with other regions and localized the region of interest (ROI) to reduce the scope of processing. A modified DeepLabv3+ variant integrating SqueezeNet (SqueezeDeepLabv3+) is proposed as a part of CAT-Seg. SqueezeDeepLabv3+ handles the different shapes of the biventricular through the different cardiac phases, as the biventricular only accounts for small portion of the volume slices. Also, CAT-Seg presents a segmentation approach that integrates attention mechanisms into 3D Residual UNet architecture (3D-ResUNet) called 3D-ARU to improve the segmentation results of the three major structures (left ventricle (LV), Myocardium (Myo), and right ventricle (RV)). The integration of the spatial attention mechanism into ResUNet handles the fuzzy edges of the three structures. The proposed model achieves promising results in training and testing with the Automatic Cardiac Diagnosis Challenge (ACDC 2017) dataset and the external validation using MyoPs. CAT-Seg demonstrates competitive performance with state-of-the-art models. On ACDC 2017, CAT-Seg is able to segment LV, Myo, and RV with an average minimum dice symmetry coefficient (DSC) performance gap of 1.165%, 4.36%, and 3.115% respectively. The average maximum improvement in terms of DSC in segmenting LV, Myo and RV is 4.395%, 6.84% and 7.315% respectively. On MyoPs external validation, CAT-Seg outperformed the state-of-the-art in segmenting LV, Myo, and RV with an average minimum performance gap of 6.13%, 5.44%, and 2.912% respectively.