Embedding Tasks Into the Latent Space: Cross-Space Consistency for Multi-Dimensional Analysis in Echocardiography.

Multi-dimensional analysis in echocardiography has attracted attention due to its potential for clinical indices quantification and computer-aided diagnosis. It can utilize various information to provide the estimation of multiple cardiac indices. However, it still has the challenge of inter-task conflict. This is owing to regional confusion, global abnormalities, and time-accumulated errors. Task mapping methods have the potential to address inter-task conflict. However, they may overlook the inherent differences between tasks, especially for multi-level tasks (e.g., pixel-level, image-level, and sequence-level tasks). This may lead to inappropriate local and spurious task constraints. We propose cross-space consistency (CSC) to overcome the challenge. The CSC embeds multi-level tasks to the same-level to reduce inherent task differences. This allows multi-level task features to be consistent in a unified latent space. The latent space extracts task-common features and constrains the distance in these features. This constrains the task weight region that satisfies multiple task conditions. Extensive experiments compare the CSC with fifteen state-of-the-art echocardiographic analysis methods on five datasets (10,908 patients). The result shows that the CSC can provide left ventricular (LV) segmentation, (DSC = 0.932), keypoint detection (MAE = 3.06mm), and keyframe identification (accuracy = 0.943). These results demonstrate that our method can provide a multi-dimensional analysis of cardiac function and is robust in large-scale datasets.

Dynamic low-count PET image reconstruction using spatio-temporal primal dual network.

Objective.Dynamic positron emission tomography (PET) imaging, which can provide information on dynamic changes in physiological metabolism, is now widely used in clinical diagnosis and cancer treatment. However, the reconstruction from dynamic data is extremely challenging due to the limited counts received in individual frame, especially in ultra short frames. Recently, the unrolled model-based deep learning methods have shown inspiring results for low-count PET image reconstruction with good interpretability. Nevertheless, the existing model-based deep learning methods mainly focus on the spatial correlations while ignore the temporal domain.Approach.In this paper, inspired by the learned primal dual (LPD) algorithm, we propose the spatio-temporal primal dual network (STPDnet) for dynamic low-count PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability.Main results.The experiments of both simulation data and real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization, spatio-temporal kernel method, LPD and FBPnet.Significance.Experimental results show STPDnet better reconstruction performance in the low count situation, which makes the proposed method particularly suitable in whole-body dynamic imaging and parametric PET imaging that require extreme short frames and usually suffer from high level of noise.

Distilling sub-space structure across views for cardiac indices estimation.

Cardiac indices estimation in multi-view images attracts great attention due to its capability for cardiac function assessment. However, the variation of the cardiac indices across views causes that most cardiac indices estimation methods can only be trained separately in each view, resulting in low data utilization. To solve this problem, we have proposed distilling the sub-space structure across views to explore the multi-view data fully for cardiac indices estimation. In particular, the sub-space structure is obtained via building a n×n covariance matrix to describe the correlation between the output dimensions of all views. Then, an alternate convex search algorithm is proposed to optimize the cross-view learning framework by which: (i) we train the model with regularization of sub-space structure in each view; (ii) we update the sub-space structure based on the learned parameters from all views. In the end, we have conducted a series of experiments to verify the effectiveness of our proposed framework. The model is trained on three views (short axis, 2-chamber view and 4-chamber view) with two modalities (magnetic resonance imaging and computed tomography). Compared to the state-of-the-art methods, our method has demonstrated superior performance on cardiac indices estimation tasks.

Phylogenetic Analyses of Hydnobolites and New Species from China.

Hydnobolites is an ectomycorrhizal fungal genus with hypogeous ascomata in the family Pezizaceae (Pezizales). Molecular analyses of Hydnobolites using both single (ITS) and concatenated gene datasets (ITS-nLSU) showed a total of 223 sequences, including 92 newly gained sequences from Chinese specimens. Phylogenetic results based on these two datasets revealed seven distinct phylogenetic clades. Among them, the ITS phylogenetic tree confirmed the presence of at least 42 phylogenetic species in Hydnobolites. Combined the morphological observations with molecular analyses, five new species of Hydnobolites translucidus sp. nov., H. subrufus sp. nov., H. lini sp. nov., H. sichuanensis sp. nov. and H. tenuiperidius sp. nov., and one new record species of H. cerebriformis Tul., were illustrated from Southwest China. Macro- and micro-morphological analyses of ascomata revealed a few, but diagnostic differences between the H. cerebriformis complex, while the similarities of the ITS sequences ranged from 94.4 to 97.2% resulting in well-supported clades.

Multitask Learning for Estimating Multitype Cardiac Indices in MRI and CT Based on Adversarial Reverse Mapping.

The estimation of multitype cardiac indices from cardiac magnetic resonance imaging (MRI) and computed tomography (CT) images attracts great attention because of its clinical potential for comprehensive function assessment. However, the most exiting model can only work in one imaging modality (MRI or CT) without transferable capability. In this article, we propose the multitask learning method with the reverse inferring for estimating multitype cardiac indices in MRI and CT. Different from the existing forward inferring methods, our method builds a reverse mapping network that maps the multitype cardiac indices to cardiac images. The task dependencies are then learned and shared to multitask learning networks using an adversarial training approach. Finally, we transfer the parameters learned from MRI to CT. A series of experiments were conducted in which we first optimized the performance of our framework via ten-fold cross-validation of over 2900 cardiac MRI images. Then, the fine-tuned network was run on an independent data set with 2360 cardiac CT images. The results of all the experiments conducted on the proposed adversarial reverse mapping show excellent performance in estimating multitype cardiac indices.

Pyramid feature adaptation for semi-supervised cardiac bi-ventricle segmentation.

Cardiac bi-ventricle segmentation (BVS) is an essential task for assessing cardiac indices, such as the ejection fraction and volume of the left ventricle (LV) and right ventricle (RV). However, BVS is extremely challenging due to the high variability of the bi-ventricle structure and lack of labeled data. In this paper, we propose a pyramid feature adaptation based semi-supervised method (PABVS) for cardiac bi-ventricle segmentation. The PABVS first extracts the multiscale pyramid features of bi-ventricle structure to cope with the high variability of bi-ventricle structure. Then, a weighted pyramid feature adaptation strategy is proposed to ensure a smooth feature space among labeled data and unlabeled data. In particular, the PABVS performs weighted feature adaptation at each level of a multiscale pyramid feature based on adversarial learning. It gives less importance to outlier feature layers of labeled data and more importance to representative layers. The experimental results on magnetic resonance images show that our proposed PABVS can achieve Dice values 0.915 for EpiLV with 40% labeled data and the Dice values 0.976 for EpiLV with all labeled data, which outperforms mainstream semi-supervised methods. This endows our PABVS with great potential for the effective clinical application of BVS.