Publications by authors named "Baiying Lei"

74 Publications

Virtual Adversarial Training based Deep Feature Aggregation Network from Dynamic Effective Connectivity for MCI Identification.

IEEE Trans Med Imaging 2021 Sep 7;PP. Epub 2021 Sep 7.

Dynamic functional connectivity (dFC) network inferred from resting-state fMRI reveals macroscopic dynamic neural activity patterns for brain disease identification. However, dFC methods ignore the causal influence between the brain regions. Furthermore, due to the complex non-Euclidean structure of brain networks, advanced deep neural networks are difficult to be applied for learning high-dimensional representations from brain networks. In this paper, a group constrained Kalman filter (gKF) algorithm is proposed to construct dynamic effective connectivity (dEC), where the gKF provides a more comprehensive understanding of the directional interaction within the dynamic brain networks than the dFC methods. Then, a novel virtual adversarial training convolutional neural network (VAT-CNN) is employed to extract the local features of dEC. The VAT strategy improves the robustness of the model to adversarial perturbations, and therefore avoids the overfitting problem effectively. Finally, we propose the high-order connectivity weight-guided graph attention networks (cwGAT) to aggregate features of dEC. By injecting the weight information of high-order connectivity into the attention mechanism, the cwGAT provides more effective high-level feature representations than the conventional GAT. The high-level features generated from the cwGAT are applied for binary classification and multiclass classification tasks of mild cognitive impairment (MCI). Experimental results indicate that the proposed framework achieves the classification accuracy of 90.9%, 89.8%, and 82.7% for normal control (NC) vs. early MCI (EMCI), EMCI vs. late MCI (LMCI), and NC vs. EMCI vs. LMCI classification respectively, outperforming the state-of-the-art methods significantly.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3110829DOI Listing
September 2021

Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis.

IEEE Trans Med Imaging 2021 Aug 24;PP. Epub 2021 Aug 24.

Fusing multi-modality medical images, such as magnetic resonance (MR) imaging and positron emission tomography (PET), can provide various anatomical and functional information about the human body. However, PET data is not always available for several reasons, such as high cost, radiation hazard, and other limitations. This paper proposes a 3D end-to-end synthesis network called Bidirectional Mapping Generative Adversarial Networks (BMGAN). Image contexts and latent vectors are effectively used for brain MR-to-PET synthesis. Specifically, a bidirectional mapping mechanism is designed to embed the semantic information of PET images into the high-dimensional latent space. Moreover, the 3D Dense-UNet generator architecture and the hybrid loss functions are further constructed to improve the visual quality of cross-modality synthetic images. The most appealing part is that the proposed method can synthesize perceptually realistic PET images while preserving the diverse brain structures of different subjects. Experimental results demonstrate that the performance of the proposed method outperforms other competitive methods in terms of quantitative measures, qualitative displays, and evaluation metrics for classification.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3107013DOI Listing
August 2021

High-intensity focused ultrasound (HIFU) ablation versus surgical interventions for the treatment of symptomatic uterine fibroids: a meta-analysis.

Eur Radiol 2021 Aug 1. Epub 2021 Aug 1.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518060, China.

Objectives: To compare the treatment success and safety of ultrasound- and MR-guided high-intensity focused ultrasound (HIFU) with surgery for treating symptomatic uterine fibroids.

Methods: We searched studies comparing HIFU with surgery for fibroids in different databases from January 2000 to July 2020. The mean difference (MD) or relative risk (RR) with 95% confidence interval (CI) for different outcome parameters was synthesized.

Results: We included 10 studies involving 4450 women. Compared with the surgery group, the decrease in uterine fibroid severity score at 6- and 12-month follow-up was higher in the HIFU group (MD - 4.16, 95% CI - 7.39 to - 0.94, and MD - 2.44, 95% CI - 3.67 to - 1.20, p < 0.05). The increase in quality-of-life (QoL) score at 6- and 12-month follow-up was higher in the HIFU group (MD 2.13, 95% CI 0.86 to 3.14, and MD 2.34, 95% CI 0.82 to 3.85, p < 0.05). The duration of hospital stay and the time to return to work was shorter in the HIFU group (MD - 3.41 days, 95% CI - 5.11 to - 1.70, and MD - 11.61 days, 95% CI - 19.73 to - 3.50, p < 0.05). The incidence of significant complications was lower in the HIFU group (RR 0.33, 95% CI 0.13 to 0.81, p < 0.05). The differences in the outcomes of adverse events, symptom recurrence, re-intervention, and pregnancy were not statistically significant (p > 0.05).

Conclusions: HIFU is superior to surgery in terms of symptomatic relief, improvement in QoL, recovery, and significant complications. However, HIFU showed comparable effects to surgery regarding the incidence of adverse events, symptom recurrence, re-intervention, and pregnancy.

Key Points: • HIFU ablation is superior to surgery in terms of symptomatic relief, improvement in QoL, recovery, and significant complications. • HIFU has comparable effects to surgery in terms of symptom recurrence rate, re-intervention rate, and pregnancy rate, indicating that HIFU is a promising non-invasive therapy that seems not to raise the risk of recurrence and re-intervention or deteriorate fertility compared to surgical approaches in women with fibroids. • There is still a lack of good-quality comparative data and further randomized studies are necessary to provide sufficient and reliable data, especially on re-intervention rate and pregnancy outcome.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00330-021-08156-6DOI Listing
August 2021

Quality evaluation of induced pluripotent stem cell colonies by fusing multi-source features.

Comput Methods Programs Biomed 2021 Sep 22;208:106235. Epub 2021 Jun 22.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China. Electronic address:

Background And Objective: Induced pluripotent stem cells (iPSCs) have great potential as the basis of regenerative medicine. In this paper, we propose an automatic quality evaluation model based on multi-source feature ensemble learning to divide the iPSC colonies into three categories: good, medium and bad.

Methods: First, we obtained iPSCs samples using a Sendai virus reprogramming method. Second, we collected the bright field-images of iPSC colonies and processed them with adaptive gamma transform and data enhancement. The evaluation for the iPSC colony quality was further verified with living cell fluorescent staining, currently accepted as the optimal biological method. Third, multi-source features were extracted using three deep convolutional neural networks (DCNNs) and four traditional feature descriptors. Finally, we utilized a support vector machine (SVM) to perform classification. Before feeding into the SVM, the features were processed by principal component analysis algorithm to save computational cost and training time.

Results: Experimental results on the collected iPSC dataset (46,500 images) show that the proposed method could obtain 95.55% classification accuracy.

Conclusions: Our study could provide a method to efficiently and quickly judge the biological quality of a single iPSC colony or populations and facilitate the large-scale iPSC manufacturing.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2021.106235DOI Listing
September 2021

Ultrasound-guided Microwave Ablation in the Management of Symptomatic Uterine Myomas: A Systematic Review and Meta-analysis.

J Minim Invasive Gynecol 2021 Jun 28. Epub 2021 Jun 28.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China (all authors).. Electronic address:

Objective: This systematic review and meta-analysis aimed to evaluate the clinical effects and safety of ultrasound-guided microwave ablation (MWA) for the treatment of symptomatic uterine myomas.

Data Sources: We searched PubMed, Web of Science Core Collection, Cochrane Library, Embase, Scopus, and Google Scholar for studies from January 2000 to January 2021.

Methods Of Study Selection: We included all studies that reported the clinical outcomes of ultrasound-guided MWA in women with symptomatic uterine myomas. Two researchers conducted the study selection according to the screening criteria.

Tabulation, Integration, And Results: We evaluated the risk of bias and evidence quality using the Newcastle-Ottawa scale. Two researchers independently extracted information from the included studies. We extracted the standardized mean difference (SMD) and pooled proportion with a 95% confidence interval (CI) for the outcome measures of interest. A total of 10 studies representing 671 patients were included. The Uterine Fibroid Symptom and Quality of Life (UFS-QoL) questionnaire was used to assess the clinical effects. Compared with baseline, the UFS scores decreased significantly (SMD 3.37; 95% CI, 2.27-4.47; p <.001; reduction rate 65.9%), QoL scores increased significantly (SMD -3.12; 95% CI, -3.93 to -2.30; p <.001; rate of increase 72.0%), and hemoglobin concentration increased significantly (SMD -2.13; 95% CI, -3.44 to -0.81; p = .002; rate of increase 30.3%) at follow-up. The mean operation time was 34.48 minutes (95% CI, 22.82-46.13; p <.001). The rate of reduction in myoma volume after MWA was 85.3% (95% CI, 82.7%-88.0%, p <.001). No major adverse event was reported, and the incidence of minor adverse events was 21.1% (95% CI, 15.1%-27.0%, p <.001).

Conclusion: Ultrasound-guided MWA is an effective and safe minimally invasive therapy for symptomatic uterine myomas.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jmig.2021.06.020DOI Listing
June 2021

Image-guided thermal ablation in the management of symptomatic adenomyosis: a systematic review and meta-analysis.

Int J Hyperthermia 2021 ;38(1):948-962

School of Biomedical Engineering, Health Science Center, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen University, Shenzhen, China.

Objective: To evaluate the clinical effects of image-guided thermal ablation for the treatment of symptomatic adenomyosis (AD).

Data Sources: We searched PubMed, Web of Science, Cochrane Library, EMBASE, ClinicalTrials.gov and Google Scholar for literature from January 2000 to September 2020.

Methods Of Study Selection: We included all studies reporting clinical outcomes of image-guided thermal ablation for AD, involving high-intensity focused ultrasound (HIFU), percutaneous microwave ablation (PMWA) and radiofrequency ablation (RFA). Two independent researchers performed study selection according to the screening criteria.

Results: A total of 38 studies representing 15,908 women were included. Compared with those at baseline, the visual analog scale scores, the symptom severity scores and the menorrhagia severity scores decreased significantly after these thermal ablation therapies. The mean ablation time was 92.18 min, 24.15 min and 31.93 min during HIFU, PMWA and RFA, respectively. The non-perfused volume ratio of AD was 68.3% for HIFU, 82.5% for PMWA and 79.2% for RFA. The reduction rates of uterine volume were 33.6% (HIFU), 46.8% (PMWA) and 44.0% (RFA). The reduction rates of AD volume were 45.1% (HIFU), 74.9% (PMWA) and 61.3% (RFA). The relief rates of dysmenorrhea were 84.2% (HIFU), 89.7% (PMWA) and 89.2% (RFA). The incidence of minor adverse events was 39.0% (HIFU), 51.3% (PMWA) and 3.6% (RFA). The re-intervention rates were 4.0% (HIFU) and 28.7% (RFA). The recurrence rate was 10.2% after HIFU. The pregnancy rates were 16.7% (HIFU), 4.93% (PMWA) and 35.8% (RFA).

Conclusion: Image-guided HIFU, PMWA and RFA may be effective and safe minimally invasive therapies for symptomatic AD.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/02656736.2021.1939443DOI Listing
July 2021

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor.

Front Oncol 2021 20;11:618496. Epub 2021 May 20.

School of Biomedical Engineering, Shenzhen University, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Shenzhen, China.

Automatic segmentation of gastric tumor not only provides image-guided clinical diagnosis but also assists radiologists to read images and improve the diagnostic accuracy. However, due to the inhomogeneous intensity distribution of gastric tumors in CT scans, the ambiguous/missing boundaries, and the highly variable shapes of gastric tumors, it is quite challenging to develop an automatic solution. This study designs a novel 3D improved feature pyramidal network (3D IFPN) to automatically segment gastric tumors in computed tomography (CT) images. To meet the challenges of this extremely difficult task, the proposed 3D IFPN makes full use of the complementary information within the low and high layers of deep convolutional neural networks, which is equipped with three types of feature enhancement modules: 3D adaptive spatial feature fusion (ASFF) module, single-level feature refinement (SLFR) module, and multi-level feature refinement (MLFR) module. The 3D ASFF module adaptively suppresses the feature inconsistency in different levels and hence obtains the multi-level features with high feature invariance. Then, the SLFR module combines the adaptive features and previous multi-level features at each level to generate the multi-level refined features by skip connection and attention mechanism. The MLFR module adaptively recalibrates the channel-wise and spatial-wise responses by adding the attention operation, which improves the prediction capability of the network. Furthermore, a stage-wise deep supervision (SDS) mechanism and a hybrid loss function are also embedded to enhance the feature learning ability of the network. CT volumes dataset collected in three Chinese medical centers was used to evaluate the segmentation performance of the proposed 3D IFPN model. Experimental results indicate that our method outperforms state-of-the-art segmentation networks in gastric tumor segmentation. Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fonc.2021.618496DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8173118PMC
May 2021

Unsupervised Domain Adaptation Based Image Synthesis and Feature Alignment for Joint Optic Disc and Cup Segmentation.

IEEE J Biomed Health Inform 2021 Jun 1;PP. Epub 2021 Jun 1.

Due to the discrepancy of different devices for fundus image collection, a well-trained neural network is usually unsuitable for another new dataset. To solve this problem, the unsupervised domain adaptation strategy attracts a lot of attentions. In this paper, we propose an unsupervised domain adaptation method based image synthesis and feature alignment (ISFA) method to segment optic disc and cup on the fundus image. The GAN-based image synthesis (IS) mechanism along with the boundary information of optic disc and cup is utilized to generate target-like query images, which serves as the intermediate latent space between source domain and target domain images to alleviate the domain shift problem. Specifically, we use content and style feature alignment (CSFA) to ensure the feature consistency among source domain images, target-like query images and target domain images. The adversarial learning is used to extract domain invariant features for output-level feature alignment (OLFA). To enhance the representation ability of domain-invariant boundary structure information, we introduce the edge attention module (EAM) for low-level feature maps. Eventually, we train our proposed method on the training set of the REFUGE challenge dataset and test it on Drishti-GS and RIM-ONE_r3 datasets. On the Drishti-GS dataset, our method achieves about 3% improvement of Dice on optic cup segmentation over the next best method. We comprehensively discuss the robustness of our method for small dataset domain adaptation. The experimental results also demonstrate the effectiveness of our method. Our code is available at https://github.com/thinkobj/ISFA.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2021.3085770DOI Listing
June 2021

Cross-attention multi-branch network for fundus diseases classification using SLO images.

Med Image Anal 2021 07 10;71:102031. Epub 2021 Mar 10.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China. Electronic address:

Fundus diseases classification is vital for the health of human beings. However, most of existing methods detect diseases by means of single angle fundus images, which lead to the lack of pathological information. To address this limitation, this paper proposes a novel deep learning method to complete different fundus diseases classification tasks using ultra-wide field scanning laser ophthalmoscopy (SLO) images, which have an ultra-wide field view of 180-200˚. The proposed deep model consists of multi-branch network, atrous spatial pyramid pooling module (ASPP), cross-attention and depth-wise attention module. Specifically, the multi-branch network employs the ResNet-34 model as the backbone to extract feature information, where the ResNet-34 model with two-branch is followed by the ASPP module to extract multi-scale spatial contextual features by setting different dilated rates. The depth-wise attention module can provide the global attention map from the multi-branch network, which enables the network to focus on the salient targets of interest. The cross-attention module adopts the cross-fusion mode to fuse the channel and spatial attention maps from the ResNet-34 model with two-branch, which can enhance the representation ability of the disease-specific features. The extensive experiments on our collected SLO images and two publicly available datasets demonstrate that the proposed method can outperform the state-of-the-art methods and achieve quite promising classification performance of the fundus diseases.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2021.102031DOI Listing
July 2021

Dual attention enhancement feature fusion network for segmentation and quantitative analysis of paediatric echocardiography.

Med Image Anal 2021 07 20;71:102042. Epub 2021 Mar 20.

School of Biomedical Engineering, Health Science Centers, Shenzhen University, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Marshall Laboratory of Biomedical Engineering, AI Research Center for Medical Image Analysis and Diagnosis, Shenzhen, China, 518060. Electronic address:

Paediatric echocardiography is a standard method for screening congenital heart disease (CHD). The segmentation of paediatric echocardiography is essential for subsequent extraction of clinical parameters and interventional planning. However, it remains a challenging task due to (1) the considerable variation of key anatomic structures, (2) the poor lateral resolution affecting accurate boundary definition, (3) the existence of speckle noise and artefacts in echocardiographic images. In this paper, we propose a novel deep network to address these challenges comprehensively. We first present a dual-path feature extraction module (DP-FEM) to extract rich features via a channel attention mechanism. A high- and low-level feature fusion module (HL-FFM) is devised based on spatial attention, which selectively fuses rich semantic information from high-level features with spatial cues from low-level features. In addition, a hybrid loss is designed to deal with pixel-level misalignment and boundary ambiguities. Based on the segmentation results, we derive key clinical parameters for diagnosis and treatment planning. We extensively evaluate the proposed method on 4,485 two-dimensional (2D) paediatric echocardiograms from 127 echocardiographic videos. The proposed method consistently achieves better segmentation performance than other state-of-the-art methods, whichdemonstratesfeasibility for automatic segmentation and quantitative analysis of paediatric echocardiography. Our code is publicly available at https://github.com/end-of-the-century/Cardiac.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2021.102042DOI Listing
July 2021

Tensorizing GAN With High-Order Pooling for Alzheimer's Disease Assessment.

IEEE Trans Neural Netw Learn Syst 2021 Mar 17;PP. Epub 2021 Mar 17.

It is of great significance to apply deep learning for the early diagnosis of Alzheimer's disease (AD). In this work, a novel tensorizing GAN with high-order pooling is proposed to assess mild cognitive impairment (MCI) and AD. By tensorizing a three-player cooperative game-based framework, the proposed model can benefit from the structural information of the brain. By incorporating the high-order pooling scheme into the classifier, the proposed model can make full use of the second-order statistics of holistic magnetic resonance imaging (MRI). To the best of our knowledge, the proposed Tensor-train, High-order pooling and Semisupervised learning-based GAN (THS-GAN) is the first work to deal with classification on MR images for AD diagnosis. Extensive experimental results on Alzheimer's disease neuroimaging initiative (ADNI) data set are reported to demonstrate that the proposed THS-GAN achieves superior performance compared with existing methods, and to show that both tensor-train and high-order pooling can enhance classification performance. The visualization of generated samples also shows that the proposed model can generate plausible samples for semisupervised learning purpose.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2021.3063516DOI Listing
March 2021

SCS-Net: A Scale and Context Sensitive Network for Retinal Vessel Segmentation.

Med Image Anal 2021 05 4;70:102025. Epub 2021 Mar 4.

Center for Smart Health, School of Nursing, The Hong Kong Polytechnic University, Hong Kong.

Accurately segmenting retinal vessel from retinal images is essential for the detection and diagnosis of many eye diseases. However, it remains a challenging task due to (1) the large variations of scale in the retinal vessels and (2) the complicated anatomical context of retinal vessels, including complex vasculature and morphology, the low contrast between some vessels and the background, and the existence of exudates and hemorrhage. It is difficult for a model to capture representative and distinguishing features for retinal vessels under such large scale and semantics variations. Limited training data also make this task even harder. In order to comprehensively tackle these challenges, we propose a novel scale and context sensitive network (a.k.a., SCSNet) for retinal vessel segmentation. We first propose a scale-aware feature aggregation (SFA) module, aiming at dynamically adjusting the receptive fields to effectively extract multi-scale features. Then, an adaptive feature fusion (AFF) module is designed to guide efficient fusion between adjacent hierarchical features to capture more semantic information. Finally, a multi-level semantic supervision (MSS) module is employed to learn more distinctive semantic representation for refining the vessel maps. We conduct extensive experiments on the six mainstream retinal image databases (DRIVE, CHASEDB1, STARE, IOSTAR, HRF, and LES-AV). The experimental results demonstrate the effectiveness of the proposed SCS-Net, which is capable of achieving better segmentation performance than other state-of-the-art approaches, especially for the challenging cases with large scale variations and complex context environments.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2021.102025DOI Listing
May 2021

3D Multi-Attention Guided Multi-Task Learning Network for Automatic Gastric Tumor Segmentation and Lymph Node Classification.

IEEE Trans Med Imaging 2021 06 1;40(6):1618-1631. Epub 2021 Jun 1.

Automatic gastric tumor segmentation and lymph node (LN) classification not only can assist radiologists in reading images, but also provide image-guided clinical diagnosis and improve diagnosis accuracy. However, due to the inhomogeneous intensity distribution of gastric tumor and LN in CT scans, the ambiguous/missing boundaries, and highly variable shapes of gastric tumor, it is quite challenging to develop an automatic solution. To comprehensively address these challenges, we propose a novel 3D multi-attention guided multi-task learning network for simultaneous gastric tumor segmentation and LN classification, which makes full use of the complementary information extracted from different dimensions, scales, and tasks. Specifically, we tackle task correlation and heterogeneity with the convolutional neural network consisting of scale-aware attention-guided shared feature learning for refined and universal multi-scale features, and task-aware attention-guided feature learning for task-specific discriminative features. This shared feature learning is equipped with two types of scale-aware attention (visual attention and adaptive spatial attention) and two stage-wise deep supervision paths. The task-aware attention-guided feature learning comprises a segmentation-aware attention module and a classification-aware attention module. The proposed 3D multi-task learning network can balance all tasks by combining segmentation and classification loss functions with weight uncertainty. We evaluate our model on an in-house CT images dataset collected from three medical centers. Experimental results demonstrate that our method outperforms the state-of-the-art algorithms, and obtains promising performance for tumor segmentation and LN classification. Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge. Our implementation is released at https://github.com/infinite-tao/MA-MTLN.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3062902DOI Listing
June 2021

Parkinson's Disease Classification and Clinical Score Regression via United Embedding and Sparse Learning From Longitudinal Data.

IEEE Trans Neural Netw Learn Syst 2021 Feb 3;PP. Epub 2021 Feb 3.

Parkinson's disease (PD) is known as an irreversible neurodegenerative disease that mainly affects the patient's motor system. Early classification and regression of PD are essential to slow down this degenerative process from its onset. In this article, a novel adaptive unsupervised feature selection approach is proposed by exploiting manifold learning from longitudinal multimodal data. Classification and clinical score prediction are performed jointly to facilitate early PD diagnosis. Specifically, the proposed approach performs united embedding and sparse regression, which can determine the similarity matrices and discriminative features adaptively. Meanwhile, we constrain the similarity matrix among subjects and exploit the l2,p norm to conduct sparse adaptive control for obtaining the intrinsic information of the multimodal data structure. An effective iterative optimization algorithm is proposed to solve this problem. We perform abundant experiments on the Parkinson's Progression Markers Initiative (PPMI) data set to verify the validity of the proposed approach. The results show that our approach boosts the performance on the classification and clinical score regression of longitudinal data and surpasses the state-of-the-art approaches.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2021.3052652DOI Listing
February 2021

Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction.

Med Image Anal 2021 04 31;69:101947. Epub 2020 Dec 31.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Centre, Shenzhen University, Shenzhen, 518060, China. Electronic address:

Graph convolution networks (GCN) have been successfully applied in disease prediction tasks as they capture interactions (i.e., edges and edge weights on the graph) between individual elements. The interactions in existing works are constructed by fusing similarity between imaging information and distance between non-imaging information, whereas disregarding the disease status of those individuals in the training set. Besides, the similarity is being evaluated by computing the correlation distance between feature vectors, which limits prediction performance, especially for predicting significant memory concern (SMC) and mild cognitive impairment (MCI). In this paper, we propose three mechanisms to improve GCN, namely similarity-aware adaptive calibrated GCN (SAC-GCN), for predicting SMC and MCI. First, we design a similarity-aware graph using different receptive fields to consider disease status. The labelled subjects on the graph are only connected with those labelled subjects with the same status. Second, we propose an adaptive mechanism to evaluate similarity. Specifically, we construct initial GCN with evaluating similarity by using traditional correlation distance, then pre-train the initial GCN by using training samples and use it to score all subjects. Then, the difference between these scores replaces correlation distance to update similarity. Last, we devise a calibration mechanism to fuse functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) information into edges. The proposed method is tested on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results demonstrate that our proposed method is useful to predict disease-induced deterioration and superior to other related algorithms, with a mean classification accuracy of 86.83% in our prediction tasks.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101947DOI Listing
April 2021

Automated left ventricular segmentation from cardiac magnetic resonance images via adversarial learning with multi-stage pose estimation network and co-discriminator.

Med Image Anal 2021 02 11;68:101891. Epub 2020 Nov 11.

College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China, 518060.

Left ventricular (LV) segmentation is essential for the early diagnosis of cardiovascular diseases, which has been reported as the leading cause of death all over the world. However, automated LV segmentation from cardiac magnetic resonance images (CMRI) using the traditional convolutional neural networks (CNNs) is still a challenging task due to the limited labeled CMRI data and low tolerances to irregular scales, shapes and deformations of LV. In this paper, we propose an automated LV segmentation method based on adversarial learning by integrating a multi-stage pose estimation network (MSPN) and a co-discrimination network. Different from existing CNNs, we use a MSPN with multi-scale dilated convolution (MDC) modules to enhance the ranges of receptive field for deep feature extraction. To fully utilize both labeled and unlabeled CMRI data, we propose a novel generative adversarial network (GAN) framework for LV segmentation by combining MSPN with co-discrimination networks. Specifically, the labeled CMRI are first used to initialize our segmentation network (MSPN) and co-discrimination network. Our GAN training includes two different kinds of epochs fed with both labeled and unlabeled CMRI data alternatively, which are different from the traditional CNNs only relied on the limited labeled samples to train the segmentation networks. As both ground truth and unlabeled samples are involved in guiding training, our method not only can converge faster but also obtain a better performance in LV segmentation. Our method is evaluated using MICCAI 2009 and 2017 challenge databases. Experimental results show that our method has obtained promising performance in LV segmentation, which also outperforms the state-of-the-art methods in terms of LV segmentation accuracy from the comparison results.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101891DOI Listing
February 2021

Uterine Artery Embolization Compared with High-intensity Focused Ultrasound Ablation for the Treatment of Symptomatic Uterine Myomas: A Systematic Review and Meta-analysis.

J Minim Invasive Gynecol 2021 02 14;28(2):218-227. Epub 2020 Nov 14.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China (all authors).. Electronic address:

Objective: This study aimed to compare the clinical effects of uterine artery embolization (UAE) with those of high-intensity focused ultrasound (HIFU) ablation for the treatment of symptomatic uterine myomas.

Data Sources: We searched PubMed, EMBASE, Web of Science, Cochrane Library, Google Scholar, and ClinicalTrials.gov for studies from January 2000 to August 2020. Related articles and relevant references of the included studies were also searched.

Methods Of Study Selection: Two researchers independently performed the data selection. We included comparative studies that compared the clinical outcomes of UAE with those of HIFU ablation in women with myomas.

Tabulation, Integration, And Results: We assessed the study quality using the Cochrane Handbook for Systematic Reviews of Interventions for evaluating the risk of bias. Two independent researchers performed the article selection according to the screening criteria and rated the quality of evidence for each article. We calculated pooled mean difference with 95% confidence interval (CI) for continuous data and relative risk (RR) with 95% CI for dichotomous data. The systematic review registration number is CRD42020199630 on the International Prospective Register of Systematic Reviews. A total of 7 articles (5 trials), involving 4592 women with symptomatic uterine myomas, were included in the meta-analysis. Compared with the HIFU ablation group, the decrease in "uterine fibroid symptom" scores as well as the increase in quality-of-life scores at the time of follow-up were higher in the UAE group, with overall mean difference 19.54 (95% CI, 15.21-23.87; p <.001) and 15.72 (95% CI, 8.30-23.13; p <.001), respectively. The women in the UAE group had a significantly lower reintervention rate (RR 0.25; 95% CI, 0.15-0.42; p <.001). The women undergoing UAE had a significantly lower pregnancy rate than those undergoing HIFU ablation (RR 0.06; 95% CI, 0.01-0.45; p = .006). The difference in the incidence of adverse events between the 2 groups was not statistically significant (p = .53).

Conclusion: Compared with HIFU ablation, UAE provided more significant alleviation of symptoms and improvement in quality of life, lower postoperative reintervention rate, and lower pregnancy rate for women with uterine myomas. However, we cannot conclude that HIFU ablation is more favorable for desired pregnancy than UAE because of the confounding factors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jmig.2020.11.004DOI Listing
February 2021

AMD-GAN: Attention encoder and multi-branch structure based generative adversarial networks for fundus disease detection from scanning laser ophthalmoscopy images.

Neural Netw 2020 Dec 17;132:477-490. Epub 2020 Sep 17.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China. Electronic address:

The scanning laser ophthalmoscopy (SLO) has become an important tool for the determination of peripheral retinal pathology, in recent years. However, the collected SLO images are easily interfered by the eyelash and frame of the devices, which heavily affect the key feature extraction of the images. To address this, we propose a generative adversarial network called AMD-GAN based on the attention encoder (AE) and multi-branch (MB) structure for fundus disease detection from SLO images. Specifically, the designed generator consists of two parts: the AE and generation flow network, where the real SLO images are encoded by the AE module to extract features and the generation flow network to handle the random Gaussian noise by a series of residual block with up-sampling (RU) operations to generate fake images with the same size as the real ones, where the AE is also used to mine features for generator. For discriminator, a ResNet network using MB is devised by copying the stage 3 and stage 4 structures of the ResNet-34 model to extract deep features. Furthermore, the depth-wise asymmetric dilated convolution is leveraged to extract local high-level contextual features and accelerate the training process. Besides, the last layer of discriminator is modified to build the classifier to detect the diseased and normal SLO images. In addition, the prior knowledge of experts is utilized to improve the detection results. Experimental results on the two local SLO datasets demonstrate that our proposed method is promising in detecting the diseased and normal SLO images with the experts labeling.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2020.09.005DOI Listing
December 2020

Glioma Growth Prediction via Generative Adversarial Learning from Multi-Time Points Magnetic Resonance Images.

Annu Int Conf IEEE Eng Med Biol Soc 2020 07;2020:1750-1753

Gliomas are the most dominant and lethal type of brain tumors. Growth prediction is significant to quantify tumor aggressiveness, improve therapy planning, and estimate patients' survival time. This is commonly addressed in literature using mathematical models guided by multi-time point scans of multi/single-modal data for the same subject. However, these models are mechanism-based and heavily rely on complicated mathematical formulations of partial differential equations with few parameters that are insufficient to capture different patterns and other characteristics of gliomas. In this paper, we propose a 3D generative adversarial networks (GANs) for glioma growth prediction. Specifically, we stack 2 GANs with conditional initialization of segmented feature maps. Furthermore, we employ Dice loss in our objective function and devised 3D U-Net architecture for better image generation. The proposed method is trained and validated using 3D patch-based strategy on real magnetic resonance images of 9 subjects with 3 time points. Experimental results show that the proposed method can be successfully used for glioma growth prediction with satisfactory performance.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC44109.2020.9175817DOI Listing
July 2020

Attention-Guided Multi-Branch Convolutional Neural Network for Mitosis Detection From Histopathological Images.

IEEE J Biomed Health Inform 2021 02 5;25(2):358-370. Epub 2021 Feb 5.

Mitotic count is an important indicator for assessing the invasiveness of breast cancers. Currently, the number of mitoses is manually counted by pathologists, which is both tedious and time-consuming. To address this situation, we propose a fast and accurate method to automatically detect mitosis from the histopathological images. The proposed method can automatically identify mitotic candidates from histological sections for mitosis screening. Specifically, our method exploits deep convolutional neural networks to extract high-level features of mitosis to detect mitotic candidates. Then, we use spatial attention modules to re-encode mitotic features, which allows the model to learn more efficient features. Finally, we use multi-branch classification subnets to screen the mitosis. Compared to existing related methods in literature, our method obtains the best detection results on the dataset of the International Pattern Recognition Conference (ICPR) 2012 Mitosis Detection Competition. Code has been made available at: https://github.com/liushaomin/MitosisDetection.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2020.3027566DOI Listing
February 2021

GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images.

Neural Netw 2020 Dec 17;132:321-332. Epub 2020 Sep 17.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518060, China. Electronic address:

Brain tumors are one of the major common causes of cancer-related death, worldwide. Growth prediction of these tumors, particularly gliomas which are the most dominant type, can be quite useful to improve treatment planning, quantify tumor aggressiveness, and estimate patients' survival time towards precision medicine. Studying tumor growth prediction basically requires multiple time points of single or multimodal medical images of the same patient. Recent models are based on complex mathematical formulations that basically rely on a system of partial differential equations, e.g. reaction diffusion model, to capture the diffusion and proliferation of tumor cells in the surrounding tissue. However, these models usually have small number of parameters that are insufficient to capture different patterns and other characteristics of the tumors. In addition, such models consider tumor growth independently for each subject, not being able to get benefit from possible common growth patterns existed in the whole population under study. In this paper, we propose a novel data-driven method via stacked 3D generative adversarial networks (GANs), named GP-GAN, for growth prediction of glioma. Specifically, we use stacked conditional GANs with a novel objective function that includes both l and Dice losses. Moreover, we use segmented feature maps to guide the generator for better generated images. Our generator is designed based on a modified 3D U-Net architecture with skip connections to combine hierarchical features and thus have a better generated image. The proposed method is trained and tested on 18 subjects with 3 time points (9 subjects from collaborative hospital and 9 subjects from BRATS 2014 dataset). Results show that our proposed GP-GAN outperforms state-of-the-art methods for glioma growth prediction and attain average Jaccard index and Dice coefficient of 78.97% and 88.26%, respectively.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2020.09.004DOI Listing
December 2020

High tissue contrast image synthesis via multistage attention-GAN: Application to segmenting brain MR scans.

Neural Netw 2020 Dec 18;132:43-52. Epub 2020 Aug 18.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518060, China. Electronic address:

Magnetic resonance imaging (MRI) presents a detailed image of the internal organs via a magnetic field. Given MRI's non-invasive advantage in repeated imaging, the low-contrast MR images in the target area make segmentation of tissue a challenging problem. This study shows the potential advantages of synthetic high tissue contrast (HTC) images through image-to-image translation techniques. Mainly, we use a novel cycle generative adversarial network (Cycle-GAN), which provides a mechanism of attention to increase the contrast within the tissue. The attention block and training on HTC images are beneficial to our model to enhance tissue visibility. We use a multistage architecture to concentrate on a single tissue as a preliminary and filter out the irrelevant context in every stage in order to increase the resolution of HTC images. The multistage architecture reduces the gap between source and target domains and alleviates synthetic images' artefacts. We apply our HTC image synthesising method to two public datasets. In order to validate the effectiveness of these images we use HTC MR images in both end-to-end and two-stage segmentation structures. The experiments on three segmentation baselines on BraTS'18 demonstrate that joining the synthetic HTC images in the multimodal segmentation framework develops the average Dice similarity scores (DSCs) of 0.8%, 0.6%, and 0.5% respectively on the whole tumour (WT), tumour core (TC), and enhancing tumour (ET) while removing one real MRI channels from the segmentation pipeline. Moreover, segmentation of infant brain tissue in T1w MR slices through our framework improves DSCs approximately 1% in cerebrospinal fluid (CSF), grey matter (GM), and white matter (WM) compared to state-of-the-art segmentation techniques. The source code of synthesising HTC images is publicly available.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2020.08.014DOI Listing
December 2020

Maximum Correntropy Criterion-Based Hierarchical One-Class Classification.

IEEE Trans Neural Netw Learn Syst 2021 Aug 3;32(8):3748-3754. Epub 2021 Aug 3.

Due to the effectiveness of anomaly/outlier detection, one-class algorithms have been extensively studied in the past. The representatives include the shallow-structure methods and deep networks, such as the one-class support vector machine (OC-SVM), one-class extreme learning machine (OC-ELM), deep support vector data description (Deep SVDD), and multilayer OC-ELM (ML-OCELM/MK-OCELM). However, existing algorithms are generally built on the minimum mean-square-error (mse) criterion, which is robust to the Gaussian noises but less effective in dealing with large outliers. To alleviate this deficiency, a robust maximum correntropy criterion (MCC)-based OC-ELM (MC-OCELM) is first proposed and then further extended to a hierarchical network to enhance its capability in characterizing complex and large data (named HC-OCELM). The gradient derivation combining with a fixed-point iterative updation scheme is adopted for the output weight optimization. Experiments on many benchmark data sets are conducted for effectiveness validation. Comparisons to many state-of-the-art approaches are provided for the superiority demonstration.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2020.3015356DOI Listing
August 2021

Diagnosis of early Alzheimer's disease based on dynamic high order networks.

Brain Imaging Behav 2021 Feb;15(1):276-287

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong Province, 518000, People's Republic of China.

Machine learning methods have been widely used for early diagnosis of Alzheimer's disease (AD) via functional connectivity networks (FCNs) analysis from neuroimaging data. The conventional low-order FCNs are obtained by time-series correlation of the whole brain based on resting-state functional magnetic resonance imaging (R-fMRI). However, FCNs overlook inter-region interactions, which limits application to brain disease diagnosis. To overcome this drawback, we develop a novel framework to exploit the high-level dynamic interactions among brain regions for early AD diagnosis. Specifically, a sliding window approach is employed to generate some R-fMRI sub-series. The correlations among these sub-series are then used to construct a series of dynamic FCNs. High-order FCNs based on the topographical similarity between each pair of the dynamic FCNs are then constructed. Afterward, a local weight clustering method is used to extract effective features of the network, and the least absolute shrinkage and selection operation method is chosen for feature selection. A support vector machine is employed for classification, and the dynamic high-order network approach is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our experimental results demonstrate that the proposed approach not only achieves promising results for AD classification, but also successfully recognizes disease-related biomarkers.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11682-019-00255-9DOI Listing
February 2021

Self-co-attention neural network for anatomy segmentation in whole breast ultrasound.

Med Image Anal 2020 08 12;64:101753. Epub 2020 Jun 12.

Shanghai United Imaging Intelligence Co., Ltd. (UII), Shanghai, China. Electronic address:

The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101753DOI Listing
August 2020

Skin lesion segmentation via generative adversarial networks with dual discriminators.

Med Image Anal 2020 08 23;64:101716. Epub 2020 May 23.

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 518000, Shenzhen, China. Electronic address:

Skin lesion segmentation from dermoscopy images is a fundamental yet challenging task in the computer-aided skin diagnosis system due to the large variations in terms of their views and scales of lesion areas. We propose a novel and effective generative adversarial network (GAN) to meet these challenges. Specifically, this network architecture integrates two modules: a skip connection and dense convolution U-Net (UNet-SCDC) based segmentation module and a dual discrimination (DD) module. While the UNet-SCDC module uses dense dilated convolution blocks to generate a deep representation that preserves fine-grained information, the DD module makes use of two discriminators to jointly decide whether the input of the discriminators is real or fake. While one discriminator, with a traditional adversarial loss, focuses on the differences at the boundaries of the generated segmentation masks and the ground truths, the other examines the contextual environment of target object in the original image using a conditional discriminative loss. We integrate these two modules and train the proposed GAN in an end-to-end manner. The proposed GAN is evaluated on the public International Skin Imaging Collaboration (ISIC) Skin Lesion Challenge Datasets of 2017 and 2018. Extensive experimental results demonstrate that the proposed network achieves superior segmentation performance to state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101716DOI Listing
August 2020

Self-weighted adaptive structure learning for ASD diagnosis via multi-template multi-center representation.

Med Image Anal 2020 07 1;63:101662. Epub 2020 Feb 1.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China. Electronic address:

As a kind of neurodevelopmental disease, autism spectrum disorder (ASD) can cause severe social, communication, interaction, and behavioral challenges. To date, many imaging-based machine learning techniques have been proposed to address ASD diagnosis issues. However, most of these techniques are restricted to a single template or dataset from one imaging center. In this paper, we propose a novel multi-template multi-center ensemble classification scheme for automatic ASD diagnosis. Specifically, based on different pre-defined templates, we construct multiple functional connectivity (FC) brain networks for each subject based on our proposed Pearson's correlation-based sparse low-rank representation. After extracting features from these FC networks, informative features to learn optimal similarity matrix are then selected by our self-weighted adaptive structure learning (SASL) model. For each template, the SASL method automatically assigns an optimal weight learned from the structural information without additional weights and parameters. Finally, an ensemble strategy based on the multi- template multi-center representations is applied to derive the final diagnosis results. Extensive experiments are conducted on the publicly available Autism Brain Imaging Data Exchange (ABIDE) database to demonstrate the efficacy of our proposed method. Experimental results verify that our proposed method boosts ASD diagnosis performance and outperforms state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101662DOI Listing
July 2020

Deep Spatial-Temporal Feature Fusion From Adaptive Dynamic Functional Connectivity for MCI Identification.

IEEE Trans Med Imaging 2020 09 27;39(9):2818-2830. Epub 2020 Feb 27.

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.2976825DOI Listing
September 2020

Self-calibrated brain network estimation and joint non-convex multi-task learning for identification of early Alzheimer's disease.

Med Image Anal 2020 04 17;61:101652. Epub 2020 Jan 17.

National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518055 China. Electronic address:

Detection of early stages of Alzheimer's disease (AD) (i.e., mild cognitive impairment (MCI)) is important to maximize the chances to delay or prevent progression to AD. Brain connectivity networks inferred from medical imaging data have been commonly used to distinguish MCI patients from normal controls (NC). However, existing methods still suffer from limited performance, and classification remains mainly based on single modality data. This paper proposes a new model to automatically diagnosing MCI (early MCI (EMCI) and late MCI (LMCI)) and its earlier stages (i.e., significant memory concern (SMC)) by combining low-rank self-calibrated functional brain networks and structural brain networks for joint multi-task learning. Specifically, we first develop a new functional brain network estimation method. We introduce data quality indicators for self-calibration, which can improve data quality while completing brain network estimation, and perform correlation analysis combined with low-rank structure. Second, functional and structural connected neuroimaging patterns are integrated into our multi-task learning model to select discriminative and informative features for fine MCI analysis. Different modalities are best suited to undertake distinct classification tasks, and similarities and differences among multiple tasks are best determined through joint learning to determine most discriminative features. The learning process is completed by non-convex regularizer, which effectively reduces the penalty bias of trace norm and approximates the original rank minimization problem. Finally, the most relevant disease features classified using a support vector machine (SVM) for MCI identification. Experimental results show that our method achieves promising performance with high classification accuracy and can effectively discriminate between different sub-stages of MCI.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101652DOI Listing
April 2020

Adaptive sparse learning using multi-template for neurodegenerative disease diagnosis.

Med Image Anal 2020 04 8;61:101632. Epub 2020 Jan 8.

School of Computer Science and Software Engineering, Guangdong Province Engineering Center of China-made High Performance Data Computing System, Shenzhen Key Laboratory of Service Computing and Applications Shenzhen University, Shenzhen 518060, China. Electronic address:

Neurodegenerative diseases are excessively affecting millions of patients, especially elderly people. Early detection and management of these diseases are crucial as the clinical symptoms take years to appear after the onset of neuro-degeneration. This paper proposes an adaptive feature learning framework using multiple templates for early diagnosis. A multi-classification scheme is developed based on multiple brain parcellation atlases with various regions of interest. Different sets of features are extracted and then fused, and a feature selection is applied with an adaptively chosen sparse degree. In addition, both linear discriminative analysis and locally preserving projections are integrated to construct a least square regression model. Finally, we propose a feature space to predict the severity of the disease by the guidance of clinical scores. Our proposed method is validated on both Alzheimer's disease neuroimaging initiative and Parkinson's progression markers initiative databases. Extensive experimental results suggest that the proposed method outperforms the state-of-the-art methods, such as the multi-modal multi-task learning or joint sparse learning. Our method demonstrates that accurate feature learning facilitates the identification of the highly relevant brain regions with significant contribution in the prediction of disease progression. This may pave the way for further medical analysis and diagnosis in practical applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2019.101632DOI Listing
April 2020
-->