Constraint-Based Unsupervised Domain Adaptation Network for Multi-Modality Cardiac Image Segmentation.

The cardiac CT and MRI images depict the various structures of the heart, which are very valuable for analyzing heart function. However, due to the difference in the shape of the cardiac images and imaging techniques, automatic segmentation is challenging. To solve this challenge, in this paper, we propose a new constraint-based unsupervised domain adaptation network. This network first performs mutual translation of images between different domains, it can provide training data for the segmentation model, and ensure domain invariance at the image level. Then, we input the target domain into the source domain segmentation model to obtain pseudo-labels and introduce cross-domain self-supervised learning between the two segmentation models. Here, a new loss function is designed to ensure the accuracy of the pseudo-labels. In addition, a cross-domain consistency loss is also introduced. Finally, we construct a multi-level aggregation segmentation network to obtain more refined target domain information. We validate our method on the public whole heart image segmentation challenge dataset and obtain experimental results of 82.9% and 5.5 on dice and average symmetric surface distance (ASSD), respectively. These experimental results prove that our method can provide important assistance in the clinical evaluation of unannotated cardiac datasets.

An integrated deep learning framework for joint segmentation of blood pool and myocardium.

Simultaneous and automatic segmentation of the blood pool and myocardium is an important precondition for early diagnosis and pre-operative planning in patients with complex congenital heart disease. However, due to the high diversity of cardiovascular structures and changes in mechanical properties caused by cardiac defects, the segmentation task still faces great challenges. To overcome these challenges, in this study we propose an integrated multi-task deep learning framework based on the dilated residual and hybrid pyramid pooling network (DRHPPN) for joint segmentation of the blood pool and myocardium. The framework consists of three closely connected progressive sub-networks. An inception module is used to realize the initial multi-level feature representation of cardiovascular images. A dilated residual network (DRN), as the main body of feature extraction and pixel classification, preliminary predicts segmentation regions. A hybrid pyramid pooling network (HPPN) is designed for facilitating the aggregation of local information to global information, which complements DRN. Extensive experiments on three-dimensional cardiovascular magnetic resonance (CMR) images (the available dataset of the MICCAI 2016 HVSMR challenge) demonstrate that our approach can accurately segment the blood pool and myocardium and achieve competitive performance compared with state-of-the-art segmentation methods.

Segmentation and visualization of left atrium through a unified deep learning framework.

PURPOSE: Left atrium segmentation and visualization serve as a fundamental and crucial role in clinical analysis and understanding of atrial fibrillation. However, most of the existing methods are directly transmitting information, which may cause redundant information to be passed to affect segmentation performance. Moreover, they did not further consider atrial visualization after segmentation, which leads to a lack of understanding of the essential atrial anatomy. METHODS: We propose a novel unified deep learning framework for left atrium segmentation and visualization simultaneously. At first, a novel dual-path module is used to enhance the expressiveness of cardiac image representation. Then a multi-scale context-aware module is designed to effectively handle complex appearance and shape variations of the left atrium and associated pulmonary veins. The generated multi-scale features are feed to gated bidirectional message passing module to remove irrelevant information and extract discriminative features. Finally, the features after message passing are efficiently combined via a deep supervision mechanism to produce the final segmentation result and reconstruct 3D volumes. RESULTS: Our approach primarily against the 2018 left atrium segmentation challenge dataset, which consists of 100 3D gadolinium-enhanced magnetic resonance images. Our method achieves an average dice of 0.936 in segmenting the left atrium via fivefold cross-validation, which outperforms state-of-the-art methods. CONCLUSIONS: The performance demonstrates the effectiveness and advantages of our network for the left atrium segmentation and visualization. Therefore, our proposed network could potentially improve the clinical diagnosis and treatment of atrial fibrillation.

DeepCQ: Deep multi-task conditional quantification network for estimation of left ventricle parameters.

BACKGROUND AND OBJECTIVE: Automatic cardiac left ventricle (LV) quantification plays an important role in assessing cardiac function. Although many advanced methods have been put forward to quantify related LV parameters, automatic cardiac LV quantification is still a challenge task due to the anatomy construction complexity of heart. METHODS: In this work, we propose a novel deep multi-task conditional quantification learning model (DeepCQ) which contains Segmentation module, Quantification encoder, and Dynamic analysis module. Besides, we also use task uncertainty loss function to update the parameters of the network in training. RESULTS: The proposed framework is validated on the dataset from Left Ventricle Full Quantification Challenge MICCAI 2018 (https://lvquan18.github.io/). The experimental results show that DeepCQ outperforms the other advanced methods. CONCLUSIONS: It illustrates that our method has a great potential in comprehensive cardiac function assessment and could play an auxiliary role in clinicians' diagnosis.