Search

This paper presents an optimal model integration framework to robustly localize the optic cup in fundus images for glaucoma detection. This work is based on the existing superpixel classification approach and makes two major contributions. First, it addresses the issues of classification performance variations due to repeated random selection of training samples, and offers a better localization solution. Second, multiple superpixel resolutions are integrated and unified for better cup boundary adherence. Compared to the state-of-the-art intra-image learning approach, we demonstrate improvements in optic cup localization accuracy with full cup-to-disc ratio range, while incurring only minor increase in computing cost. [ABSTRACT FROM AUTHOR]

• We design a MCI-graph framework which integrates both non-image information and image information. We use LWCC to extract the feature to avoid the high dimensional features. • We devise various parallel GCN layers using multiple inputs from the random walk embedding theory, which is able to identify the essential MCI information from the GCN graph embedding. • The random walk embeddings on the graph can explore the high order similarity of features. • We fuse the information from the functional networks and structural networks using a MSE-GCN model to improve prediction performance. As an early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) is able to be detected by analyzing the brain connectivity networks. For this reason, we devise a new framework via multi-scale enhanced graph convolutional network (MSE-GCN) for MCI detection, which integrates the structural and functional information from the diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (R-fMRI), respectively. Specifically, both information in the brain connective networks is first integrated based on the local weighted clustering coefficients (LWCC), which is concatenated as the feature vector for representing a population graph's vertice. Simultaneously, the gender and age information in each subject are integrated with the structural and functional features to construct a sparse graph. Then, various parallel graph convolutional network (GCN) layers with multiple inputs are designed from the embedding from random walk embeddings in the GCN to identify the essential MCI graph information. Finally, all GCN layers' outputs are concatenated via the fully connection layer to perform disease detection. The experimental results on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) database show that our method is promising to detect MCI and superior to other competing algorithms, with a mean classification accuracy of 90.39% in the detection tasks. [ABSTRACT FROM AUTHOR]

Growing evidence indicates that silibinin (SLB), a main component extracted from Chinese herb Silybum marianum , can effectively antagonize doxorubicin (DOX) induced myocardial injury (DIMI), but the specific molecular mechanism is still unelucidated. Herein, DOX induced human AC16 cardiomyocyte injury model and Network Pharmacology are used to predict and verify the potential mechanism. The analysis results of the core PPI network of SLB against DIMI show that JAK/STAT signaling pathway and autophagy are significantly enriched. Molecular docking results indicate that SLB has stronger binding ability to signaling key proteins IL6ST, JAK2 and STAT3 (affinity ≤ −7.0 kcal/mol). The detection results of pathway activation and autophagy level demonstrate that SLB significantly alleviates DOX induced IL6ST/JAK2/STAT3 signaling pathway inhibition and autophagy inhibition, reduces the death rate of cardiomyocytes. This protective effect of SLB is eliminated when key pathway proteins (IL6ST, JAK2, STAT3) are knocked down or autophagy is inhibited (3-MA or Beclin1 knockdown). These results suggest that the regulation of IL6ST/JAK2/STAT3 signaling pathway and autophagy may be important mechanism for SLB's protective effect on DOX injured cardiomyocytes. Further experimental results prove that knockdown of IL6ST, JAK2 and STAT3 eliminate the mitochondrial ROS scavenging effect and autophagy promoting effect of SLB. In sum, SLB can decrease the mitochondrial ROS and restore autophagy to antagonize DOX-induced cardiomyocyte injury by activating IL6ST/JAK2/STAT3 signaling pathway. [Display omitted] [ABSTRACT FROM AUTHOR]

• We develop an RIR block by incorporating the prior clinical knowledge, which can construct the dependencies among channels and adaptively recalibrate the relative importance of feature map region information, like top-half and bottom-half regions. • We construct an RIR-Net to accurately discriminate opacity information for classifying NC into three severity levels, built on multiple Residual-RIR modules to emphasize meaningful regional feature representations and alleviate the gradient vanishing problem. The results show that our RIR-Net outperforms strong baselines and previous state-of-the-art methods on a clinical AS-OCT dataset and the other two OCT datasets. We also demonstrate that the uneven opacity distributions in top half- and bottom half- regions affect NC classification results on AS-OCT images by using CNNs experimentally, which is consistent with clinical research. • This paper not only uses the CAM technique to localize what and where RIR-Net focuses on but also analyzes attention weights of the RIR block in-depth, examining the validity of our method in adjusting the relative importance of feature map regions. [Display omitted] Nuclear cataract (NC) is a leading eye disease for blindness and vision impairment globally. Accurate and objective NC grading/classification is essential for clinically early intervention and cataract surgery planning. Anterior segment optical coherence tomography (AS-OCT) images are capable of capturing the nucleus region clearly and measuring the opacity of NC quantitatively. Recently, clinical research has suggested that the opacity correlation and repeatability between NC severity levels and the average nucleus density on AS-OCT images is high with the interclass and intraclass analysis. Moreover, clinical research has suggested that opacity distribution is uneven on the nucleus region, indicating that the opacities from different nucleus regions may play different roles in NC diagnosis. Motivated by the clinical priors, this paper proposes a simple yet effective region-based integration-and-recalibration attention (RIR), which integrates multiple feature map region representations and recalibrates the weights of each region via softmax attention adaptively. This region recalibration strategy enables the network to focus on high contribution region representations and suppress less useful ones. We combine the RIR block with the residual block to form a Residual-RIR module, and then a sequence of Residual-RIR modules are stacked to a deep network named region-based integration-and-recalibration network (RIR-Net), to predict NC severity levels automatically. The experiments on a clinical AS-OCT image dataset and two OCT datasets demonstrate that our method outperforms strong baselines and previous state-of-the-art methods. Furthermore, attention weight visualization analysis and ablation studies verify the capability of our RIR-Net for adjusting the relative importance of different regions in feature maps dynamically, agreeing with the clinical research. [ABSTRACT FROM AUTHOR]

• This work is the first attempt to classify anterior chamber angles into open, appositional- and synechial- angle-closure, by Anterior Segment Optical Coherence Tomography (AS-OCT), rather than the conventional gonioscopic examination. • We introduced a Multi-Sequence Deep Network (MSDN), which learns to identify discriminative representations from a sequence of AS-OCT images, especially with a view to improving performance in separating appositional-angle from its occludable angle forms. • We have constructed a AS-OCT dataset for which the AS-OCT of each eye were acquired under both dark and bright illumination conditions. We take advantage of the resulting changes in pupil size to simulate the pressure of the goniolens, which can push the angle open and help determine the true angle configuration. Precise characterization and analysis of anterior chamber angle (ACA) are of great importance in facilitating clinical examination and diagnosis of angle-closure disease. Currently, the gold standard for diagnostic angle assessment is observation of ACA by gonioscopy. However, gonioscopy requires direct contact between the gonioscope and patients' eye, which is uncomfortable for patients and may deform the ACA, leading to false results. To this end, in this paper, we explore a potential way for grading ACAs into open-, appositional- and synechial angles by Anterior Segment Optical Coherence Tomography (AS-OCT), rather than the conventional gonioscopic examination. The proposed classification schema can be beneficial to clinicians who seek to better understand the progression of the spectrum of angle-closure disease types, so as to further assist the assessment and required treatment at different stages of angle-closure disease. To be more specific, we first use an image alignment method to generate sequences of AS-OCT images. The ACA region is then localized automatically by segmenting an important biomarker - the iris - as this is a primary structural cue in identifying angle-closure disease. Finally, the AS-OCT images acquired in both dark and bright illumination conditions are fed into our Multi-Sequence Deep Network (MSDN) architecture, in which a convolutional neural network (CNN) module is applied to extract feature representations, and a novel ConvLSTM-TC module is employed to study the spatial state of these representations. In addition, a novel time-weighted cross-entropy loss (TC) is proposed to optimize the output of the ConvLSTM, and the extracted features are further aggregated for the purposes of classification. The proposed method is evaluated across 66 eyes, which include 1584 AS-OCT sequences, and a total of 16,896 images. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy. [ABSTRACT FROM AUTHOR]

• We propose a novel generative adversarial network for skin lesion segmentation. • We construct a UNet-SCDC module as a generator model to produce segmentation masks. • A dual discrimination strategy is proposed to improve the recognition. 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. Image, graphical abstract [ABSTRACT FROM AUTHOR]

• A network estimation method can automatically calibrate data quality and integrate modula prior. • A multi-task feature learning method is developed using multi-modal data. • A joint non-convex regularizer is designed for subspace learning. • Our method has achieved good automatic diagnosis and classification performance. 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. Image, graphical abstract [ABSTRACT FROM AUTHOR]