Unsupervised dual-domain disentangled network for removal of rigid motion artifacts in MRI.

Motion artifacts in magnetic resonance imaging (MRI) have always been a serious issue because they can affect subsequent diagnosis and treatment. Supervised deep learning methods have been investigated for the removal of motion artifacts; however, they require paired data that are difficult to obtain in clinical settings. Although unsupervised methods are widely proposed to fully use clinical unpaired data, they generally focus on anatomical structures generated by the spatial domain while ignoring phase error (deviations or inaccuracies in phase information that are possibly caused by rigid motion artifacts during image acquisition) provided by the frequency domain. In this study, a 2D unsupervised deep learning method named unsupervised disentangled dual-domain network (UDDN) was proposed to effectively disentangle and remove unwanted rigid motion artifacts from images. In UDDN, a dual-domain encoding module was presented to capture different types of information from the spatial and frequency domains to enrich the information. Moreover, a cross-domain attention fusion module was proposed to effectively fuse information from different domains, reduce information redundancy, and improve the performance of motion artifact removal. UDDN was validated on a publicly available dataset and a clinical dataset. Qualitative and quantitative experimental results showed that our method could effectively remove motion artifacts and reconstruct image details. Moreover, the performance of UDDN surpasses that of several state-of-the-art unsupervised methods and is comparable with that of the supervised method. Therefore, our method has great potential for clinical application in MRI, such as real-time removal of rigid motion artifacts.

Semi-supervised hybrid spine network for segmentation of spine MR images.

Automatic segmentation of vertebral bodies (VBs) and intervertebral discs (IVDs) in 3D magnetic resonance (MR) images is vital in diagnosing and treating spinal diseases. However, segmenting the VBs and IVDs simultaneously is not trivial. Moreover, problems exist, including blurry segmentation caused by anisotropy resolution, high computational cost, inter-class similarity and intra-class variability, and data imbalances. We proposed a two-stage algorithm, named semi-supervised hybrid spine network (SSHSNet), to address these problems by achieving accurate simultaneous VB and IVD segmentation. In the first stage, we constructed a 2D semi-supervised DeepLabv3+ by using cross pseudo supervision to obtain intra-slice features and coarse segmentation. In the second stage, a 3D full-resolution patch-based DeepLabv3+ was built. This model can be used to extract inter-slice information and combine the coarse segmentation and intra-slice features provided from the first stage. Moreover, a cross tri-attention module was applied to compensate for the loss of inter-slice and intra-slice information separately generated from 2D and 3D networks, thereby improving feature representation ability and achieving satisfactory segmentation results. The proposed SSHSNet was validated on a publicly available spine MR image dataset, and remarkable segmentation performance was achieved. Moreover, results show that the proposed method has great potential in dealing with the data imbalance problem. Based on previous reports, few studies have incorporated a semi-supervised learning strategy with a cross attention mechanism for spine segmentation. Therefore, the proposed method may provide a useful tool for spine segmentation and aid clinically in spinal disease diagnoses and treatments. Codes are publicly available at: https://github.com/Meiyan88/SSHSNet.

2D-3D cascade network for glioma segmentation in multisequence MRI images using multiscale information.

BACKGROUND AND OBJECTIVE: Glioma segmentation is an important procedure for the treatment plan and follow-up evaluation of patients with glioma. UNet-based networks are widely used in medical image segmentation tasks and have achieved state-of-the-art performance. However, context information along the third dimension is ignored in 2D convolutions, whereas difference between z-axis and in-plane resolutions is large in 3D convolutions. Moreover, an original UNet structure cannot capture fine details because of the reduced resolution of feature maps near bottleneck layers. METHODS: To address these issues, a novel 2D-3D cascade network with multiscale information module is proposed for the multiclass segmentation of gliomas in multisequence MRI images. First, a 2D network is applied to fully exploit potential intra-slice features. A variational autoencoder module is incorporated into 2D DenseUNet to regularize a shared encoder, extract useful information, and represent glioma heterogeneity. Second, we integrated 3D DenseUNet with the 2D network in cascade mode to extract useful inter-slice features and alleviate the influence of large difference between z-axis and in-plane resolutions. Moreover, a multiscale information module is used in the 2D and 3D networks to further capture the fine details of gliomas. Finally, the whole 2D-3D cascade network is trained in an end-to-end manner, where the intra-slice and inter-slice features are fused and optimized jointly to take full advantage of 3D image information. RESULTS: Our method is evaluated on publicly available and clinical datasets and achieves competitive performance in these two datasets. CONCLUSIONS: These results indicate that the proposed method may be a useful tool for glioma segmentation.

Prior Knowledge-Aware Fusion Network for Prediction of Macrovascular Invasion in Hepatocellular Carcinoma.

Macrovascular invasion (MaVI) is a major threat to survival in hepatocellular carcinoma (HCC), which should be treated as early as possible to ensure safety and efficacy. In this aspect, MaVI prediction can be helpful. However, MaVI prediction is difficult because of the inter-class similarity and intra-class variation of HCC in computed tomography (CT) images. Moreover, existing methods fail to include clinical priori knowledge associated with HCC, leading to incomprehensive information extraction. In this paper, we proposed a prior knowledge-aware fusion network (PKAFnet) to accurately achieve MaVI prediction in CT images. First, a perception module was presented to extract features related to tumor marginal heterogeneity in the graph domain, which contributed to rotation invariance and captured intensity variations of tumor margin. Second, a tumor segmentation network was built to obtain global information of a 3D tumor image and information associated with tumor internal heterogeneity in the image domain. Finally, multi-domain features associated with the tumor margin and tumor region were combined by using a multi-domain attentional feature fusion module. Thus, by incorporating MaVI-related prior knowledge, our PKAFnet can alleviate overfitting, which can improve the discriminative ability. The proposed PKAFnet was validated on a multi-center dataset, and remarkable performance was achieved in an independent testing set. Moreover, the interpretability of perception module and segmentation network were presented in our paper, which illustrated the effectiveness and credibility of PKAFnet. Therefore, the proposed method showed great application potential for MaVI prediction.

Structure-constrained combination-based nonlinear association analysis between incomplete multimodal imaging and genetic data for biomarker detection of neurodegenerative diseases.

Multimodal imaging data are widely applied in imaging genetic studies to identify associations between imaging and genetic data for the biomarker detection of neurodegenerative diseases (NDs). However, the incomplete multimodal imaging data and complex relationships among imaging and genetic data make it difficult to effectively analyze associations between imaging and genetic data and accurately detect disease-related biomarkers. This study proposed a novel structure-constrained combination-based nonlinear association analysis method to exploit associations between incomplete multimodal imaging and genetic data for potential biomarker detection of NDs. Two types of structure constraints were used in imaging and genetic data. First, a parallel concatenated projection method with multiple constraints was adopted to handle missing data. Modality-shared and modality-specific information could be well captured to obtain latent imaging representations. A locality preserving constraint was applied to the imaging data for retaining structure information before and after projection. A connectivity penalty was also included to capture structure associations among latent imaging representations. Second, a group-induced graph self-expression constraint was incorporated into our method to exploit strong structure correlations among inter- and intra-group of genetic data. Finally, a nonlinear kernel-based method was used to explore the complex associations between latent imaging representations and genetic data for biomarker detection. A set of simulation data and two sets of real ND data, which were obtained from Alzheimer's disease neuroimaging initiative and Parkinson's progression markers initiative databases, were applied to assess the effectiveness of our method. High accuracy of biomarker detection was achieved. Moreover, the identification of disease-related biomarkers was confirmed in previous studies. Therefore, our method may provide a novel way to gain insights into the pathological mechanism of NDs and early prediction of these diseases.

Conductive substrates-based component tailoring via thermal conversion of metal organic framework for enhanced microwave absorption performances.

Component tailoring, especially for the conductive substrates-based composites, acts as a significant role in optimizing the electromagnetic (EM) parameters and improving the EM response capability. Here, Fe-based metal oxides modified rGO microwave absorbers with component evolution were fabricated through hydrothermal treatment and subsequent pyrolysis process. The synergistic effects of the dielectric loss (multi-relaxations) and the magnetic loss (resonance and eddy current) are found to be effective in promoting the microwave absorption property of Fex-1Ox/C/rGO absorbers. As the thermal treatment temperature reaches 500 °C, the as-prepared composite sample shows ideal microwave absorption performance, where the reflection loss value is -25.94 dB, and the effective bandwidth reaches 5.84 GHz at 1.9 mm. In addition, CST simulation was employed to analyze the microwave absorption capability in the actual far field. When the scattering angle is 0° and 20°, the radar cross section (RCS) reduction of S-500/PEC layers is 8.11 dB m2 and 8.80 dB m2, respectively. This study exhibits the importance of component tailoring in enhancing the performances of substrates-based microwave absorption materials.

Multi-task deep learning network to predict future macrovascular invasion in hepatocellular carcinoma.

BACKGROUND: Models predicting future macrovascular invasion in hepatocellular carcinoma are constructed to assist timely interventions. METHODS: A total of 366 HCC cases were retrospectively collected from five Chinese hospitals between April 2007 and November 2016: the training dataset comprised 281 patients from four hospitals; the external validation dataset comprised 85 patients from another hospital. Multi-task deep learning network-based models were constructed to predict future macrovascular invasion. The discrimination, calibration, and decision curves were compared to identify the best model. We compared the time to macrovascular invasion and overall survival using the best model and related image heterogeneity scores (H-score). Then, we determined the need for a segmentation subnet or the replacement deep learning algorithm by logistic regression in screening clinical/radiological factors. Finally, an applet was constructed for future application. FINDINGS: The best model combined clinical/radiological factors and radiomic features. It achieved best discrimination (areas under the curve: 0·877 in the training dataset and 0·836 in the validation dataset), calibration, and decision curve. Its performance was not affected by the treatments and disease stages. The subgroups had statistical significance for time to macrovascular invasion (training: hazard ratio [HR] = 0·073, 95% confidence interval [CI]: 0·032-0·167, p < 0·001 and validation: HR = 0·090, 95%CI: 0·022-0·366, p < 0·001) and overall survival (training: HR = 0·344, 95%CI: 0·246-0·547, p < 0·001 and validation: HR = 0·489, 95%CI: 0·279 - 0·859, p = 0·003). Similar results were achieved when the patients were subdivided by the H-score. The subnet for segmentation and end-to-end deep learning algorithms improved the performance of the model. INTERPRETATION: Our multi-task deep learning network-based model successfully predicted future macrovascular invasion. In high-risk populations, besides the current first-line treatments, more therapies may be explored for macrovascular invasion.

Deep-gated recurrent unit and diet network-based genome-wide association analysis for detecting the biomarkers of Alzheimer's disease.

Genome-wide association analysis (GWAS) is a commonly used method to detect the potential biomarkers of Alzheimer's disease (AD). Most existing GWAS methods entail a high computational cost, disregard correlations among imaging data and correlations among genetic data, and ignore various associations between longitudinal imaging and genetic data. A novel GWAS method was proposed to identify potential AD biomarkers and address these problems. A network based on a gated recurrent unit was applied without imputing incomplete longitudinal imaging data to integrate the longitudinal data of variable lengths and extract an image representation. In this study, a modified diet network that can considerably reduce the number of parameters in the genetic network was proposed to perform GWAS between image representation and genetic data. Genetic representation can be extracted in this way. A link between genetic representation and AD was established to detect potential AD biomarkers. The proposed method was tested on a set of simulated data and a real AD dataset. Results of the simulated data showed that the proposed method can accurately detect relevant biomarkers. Moreover, the results of real AD dataset showed that the proposed method can detect some new risk-related genes of AD. Based on previous reports, no research has incorporated a deep-learning model into a GWAS framework to investigate the potential information on super-high-dimensional genetic data and longitudinal imaging data and create a link between imaging genetics and AD for detecting potential AD biomarkers. Therefore, the proposed method may provide new insights into the underlying pathological mechanism of AD.

Imaging Genetics Study Based on a Temporal Group Sparse Regression and Additive Model for Biomarker Detection of Alzheimer's Disease.

Imaging genetics is an effective tool used to detect potential biomarkers of Alzheimer's disease (AD) in imaging and genetic data. Most existing imaging genetics methods analyze the association between brain imaging quantitative traits (QTs) and genetic data [e.g., single nucleotide polymorphism (SNP)] by using a linear model, ignoring correlations between a set of QTs and SNP groups, and disregarding the varied associations between longitudinal imaging QTs and SNPs. To solve these problems, we propose a novel temporal group sparsity regression and additive model (T-GSRAM) to identify associations between longitudinal imaging QTs and SNPs for detection of potential AD biomarkers. We first construct a nonparametric regression model to analyze the nonlinear association between QTs and SNPs, which can accurately model the complex influence of SNPs on QTs. We then use longitudinal QTs to identify the trajectory of imaging genetic patterns over time. Moreover, the SNP information of group and individual levels are incorporated into the proposed method to boost the power of biomarker detection. Finally, we propose an efficient algorithm to solve the whole T-GSRAM model. We evaluated our method using simulation data and real data obtained from AD neuroimaging initiative. Experimental results show that our proposed method outperforms several state-of-the-art methods in terms of the receiver operating characteristic curves and area under the curve. Moreover, the detection of AD-related genes and QTs has been confirmed in previous studies, thereby further verifying the effectiveness of our approach and helping understand the genetic basis over time during disease progression.