RA-SIFA: Unsupervised domain adaptation multi-modality cardiac segmentation network combining parallel attention module and residual attention unit

BACKGROUND: Convolutional neural network has achieved a profound effect on cardiac image segmentation. The diversity of medical imaging equipment brings the challenge of domain shift for cardiac image segmentation. OBJECTIVE: In order to solve the domain shift existed in multi-modality cardiac image segmentation, this study aims to investigate and test an unsupervised domain adaptation network RA-SIFA, which combines a parallel attention module (PAM) and residual attention unit (RAU). METHODS: First, the PAM is introduced in the generator of RA-SIFA to fuse global information, which can reduce the domain shift from the respect of image alignment. Second, the shared encoder adopts the RAU, which has residual block based on the spatial attention module to alleviate the problem that the convolution layer is insensitive to spatial position. Therefore, RAU enables to further reduce the domain shift from the respect of feature alignment. RA-SIFA model can realize the unsupervised domain adaption (UDA) through combining the image and feature alignment, and then solve the domain shift of cardiac image segmentation in a complementary manner. RESULTS: The model is evaluated using MM-WHS2017 datasets. Compared with SIFA, the Dice of our new RA-SIFA network is improved by 8.4%and 3.2%in CT and MR images, respectively, while, the average symmetric surface distance (ASD) is reduced by 3.4 and 0.8mm in CT and MR images, respectively. CONCLUSION: The study results demonstrate that our new RA-SIFA network can effectively improve the accuracy of whole-heart segmentation from CT and MR images.

Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging

Medical imaging is a central part of clinical diagnosis and treatment guidance. Machine learning has increasingly gained relevance because it captures features of disease and treatment response that are relevant for therapeutic decision-making. In clinical practice, the continuous progress of image acquisition technology or diagnostic procedures, the diversity of scanners, and evolving imaging protocols hamper the utility of machine learning, as prediction accuracy on new data deteriorates, or models become outdated due to these domain shifts. We propose a continual learning approach to deal with such domain shifts occurring at unknown time points. We adapt models to emerging variations in a continuous data stream while counteracting catastrophic forgetting. A dynamic memory enables rehearsal on a subset of diverse training data to mitigate forgetting while enabling models to expand to new domains. The technique balances memory by detecting pseudo-domains, representing different style clusters within the data stream. Evaluation of two different tasks, cardiac segmentation in magnetic resonance imaging and lung nodule detection in computed tomography, demonstrate a consistent advantage of the method.

Semantic Cardiac Segmentation in Chest CT Images Using K-Means Clustering and the Mathematical Morphology Method

Whole cardiac segmentation in chest CT images is important to identify functional abnormalities that occur in cardiovascular diseases, such as coronary artery disease (CAD) detection. However, manual efforts are time-consuming and labor intensive. Additionally, labeling the ground truth for cardiac segmentation requires the extensive manual annotation of images by the radiologist. Due to the difficulty in obtaining the annotated data and the required expertise as an annotator, an unsupervised approach is proposed. In this paper, we introduce a semantic whole-heart segmentation combining K-Means clustering as a threshold criterion of the mean-thresholding method and mathematical morphology method as a threshold shifting enhancer. The experiment was conducted on 500 subjects in two cases: (1) 56 slices per volume containing full heart scans, and (2) 30 slices per volume containing about half of the top of heart scans before the liver appears. In both cases, the results showed an average silhouette score of the K-Means method of 0.4130. Additionally, the experiment on 56 slices per volume achieved an overall accuracy (OA) and mean intersection over union (mIoU) of 34.90% and 41.26%, respectively, while the performance for the first 30 slices per volume achieved an OA and mIoU of 55.10% and 71.46%, respectively.

Validation of Automated Biventricular Myocardial Segmentation from Coronary Computed Tomographic Angiography for Multimodality Image Fusion

PurposeImage fusion strategies of myocardial perfusion imaging (MPI) and coronary CT angiography (CCTA) have shown increased diagnostic power. However, their clinical feasibility is hindered by the lack of efficient algorithms for the extraction of cardiac anatomy from CCTA datasets. The aim of this work was to validate our previously published algorithm for automated cardiac segmentation of CCTAs in a larger cohort of subjects while testing its application in clinical settings.MethodsThree borders were automatically and manually extracted on sixty-three clinical CCTAs: left and right endocardia (LV, RV) and the biventricular epicardium (EPI). Impact of image resolutions and inter-operator variability on accuracy and robustness of automated processing were evaluated. Automated algorithm accuracy was assessed with the Dice Similarity Coefficient (DSC) and the surface-to-surface distance metric. Relevant quantities were compared for automated versus manual segmentations: LV and RV volumes, myocardial mass and LV myocardial mass.ResultsLower resolution images offered an acceptable trade-off for accuracy and processing time (45 sec). DSC for LV, RV, EPI borders were 0.88, 0.80 and 0.89. Automated versus manual correlation coefficients for LV and RV vol, myo and LV mass were 0.96, 0.73, 0.84 and 0.67 with inter-operator agreement > 0.93 for three variables. Consistent and improved results were evidenced at higher resolutions.ConclusionOur algorithms allowed efficient automated cardiac segmentation from CT imagery with minimal user intervention, clinically acceptable times and accuracy. The reported results show promise for its use in a clinical environment, specifically in the context of image fusion.