Publications by authors named "Ling Shao"

221 Publications

Learning Efficient Hash Codes for Fast Graph-Based Data Similarity Retrieval.

IEEE Trans Image Process 2021 13;30:6321-6334. Epub 2021 Jul 13.

Traditional operations, e.g. graph edit distance (GED), are no longer suitable for processing the massive quantities of graph-structured data now available, due to their irregular structures and high computational complexities. With the advent of graph neural networks (GNNs), the problems of graph representation and graph similarity search have drawn particular attention in the field of computer vision. However, GNNs have been less studied for efficient and fast retrieval after graph representation. To represent graph-based data, and maintain fast retrieval while doing so, we introduce an efficient hash model with graph neural networks (HGNN) for a newly designed task (i.e. fast graph-based data retrieval). Due to its flexibility, HGNN can be implemented in both an unsupervised and supervised manner. Specifically, by adopting a graph neural network and hash learning algorithms, HGNN can effectively learn a similarity-preserving graph representation and compute pair-wise similarity or provide classification via low-dimensional compact hash codes. To the best of our knowledge, our model is the first to address graph hashing representation in the Hamming space. Our experimental results reach comparable prediction accuracy to full-precision methods and can even outperform traditional models in some cases. In real-world applications, using hash codes can greatly benefit systems with smaller memory capacities and accelerate the retrieval speed of graph-structured data. Hence, we believe the proposed HGNN has great potential in further research.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3093387DOI Listing
July 2021

DONet: Dual-Octave Network for Fast MR Image Reconstruction.

IEEE Trans Neural Netw Learn Syst 2021 Jul 1;PP. Epub 2021 Jul 1.

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose the dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of dual-octave convolutions (Dual-OctConvs), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary) and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intragroup information updating and intergroup information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: 1) it encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity; 2) the dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse; and 3) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2021.3090303DOI Listing
July 2021

Medulloblastoma uses GABA transaminase to survive in the cerebrospinal fluid microenvironment and promote leptomeningeal dissemination.

Cell Rep 2021 Jun;35(13):109302

Department of Neurological Surgery, Keck School of Medicine, University of Southern California, Los Angeles, CA 90089, USA; Norris Comprehensive Cancer Center, University of Southern California, Los Angeles, CA 90089, USA; USC Brain Tumor Center, University of Southern California, Los Angeles, CA 90089, USA. Electronic address:

Medulloblastoma (MB) is a malignant pediatric brain tumor arising in the cerebellum. Although abnormal GABAergic receptor activation has been described in MB, studies have not yet elucidated the contribution of receptor-independent GABA metabolism to MB pathogenesis. We find primary MB tumors globally display decreased expression of GABA transaminase (ABAT), the protein responsible for GABA metabolism, compared with normal cerebellum. However, less aggressive WNT and SHH subtypes express higher ABAT levels compared with metastatic G3 and G4 tumors. We show that elevated ABAT expression results in increased GABA catabolism, decreased tumor cell proliferation, and induction of metabolic and histone characteristics mirroring GABAergic neurons. Our studies suggest ABAT expression fluctuates depending on metabolite changes in the tumor microenvironment, with nutrient-poor conditions upregulating ABAT expression. We find metastatic MB cells require ABAT to maintain viability in the metabolite-scarce cerebrospinal fluid by using GABA as an energy source substitute, thereby facilitating leptomeningeal metastasis formation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.celrep.2021.109302DOI Listing
June 2021

SCG: Saliency and Contour Guided Salient Instance Segmentation.

IEEE Trans Image Process 2021 28;30:5862-5874. Epub 2021 Jun 28.

Different from conventional instance segmentation, salient instance segmentation (SIS) faces two difficulties. The first is that it involves segmenting salient instances only while ignoring background, and the second is that it targets generic object instances without pre-defined object categories. In this paper, based on the state-of-the-art Mask R-CNN model, we propose to leverage complementary saliency and contour information to handle these two challenges. We first improve Mask R-CNN by introducing an interleaved execution strategy and proposing a novel mask head network to incorporate global context within each RoI. Then we add two branches to Mask R-CNN for saliency and contour detection, respectively. We fuse the Mask R-CNN features with the saliency and contour features, where the former supply pixel-wise saliency information to help with identifying salient regions and the latter provide a generic object contour prior to help detect and segment generic objects. We also propose a novel multiscale global attention model to generate attentive global features from multiscale representative features for feature fusion. Experimental results demonstrate that all our proposed model components can improve SIS performance. Finally, our overall model outperforms state-of-the-art SIS methods and Mask R-CNN by more than 6% and 3%, respectively. By using additional multitask training data, we can further improve the model performance on the ILSO dataset.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3088282DOI Listing
June 2021

Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing.

IEEE Trans Image Process 2021 Jun 17;PP. Epub 2021 Jun 17.

Deep learning has recently been intensively studied in the context of image compressive sensing (CS) to discover and represent complicated image structures. These approaches, however, either suffer from nonflexibility for an arbitrary sampling ratio or lack an explicit deep-learned regularization term. This paper aims to solve the CS reconstruction problem by combining the deep-learned regularization term and proximal operator. We first introduce a regularization term using a carefully designed residual-regressive net, which can measure the distance between a corrupted image and a clean image set and accurately identify to which subspace the corrupted image belongs. We then address a proximal operator with a tailored dilated residual channel attention net, which enables the learned proximal operator to map the distorted image into the clean image set. We adopt an adaptive proximal selection strategy to embed the network into the loop of the CS image reconstruction algorithm. Moreover, a self-ensemble strategy is presented to improve CS recovery performance. We further utilize state evolution to analyze the effectiveness of the designed networks. Extensive experiments also demonstrate that our method can yield superior accurate reconstruction (PSNR gain over 1 dB) compared to other competing approaches while achieving the current state-of-the-art image CS reconstruction performance. The test code is available at https://github.com/zjut-gwl/CSDRCANet.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3088611DOI Listing
June 2021

Photoprotection of Arabidopsis leaves under short-term high light treatment: The antioxidant capacity is more important than the anthocyanin shielding effect.

Plant Physiol Biochem 2021 Jun 8;166:258-269. Epub 2021 Jun 8.

Guangzhou Key Laboratory of Subtropical Biodiversity and Biomonitoring, Guangdong Provincial Key Laboratory of Biotechnology for Plant Development, School of Life Sciences, South China Normal University, Guangzhou, 510631, PR China. Electronic address:

Photoprotection strategies that have evolved in plants to cope with high light (HL) stress provide plants with the ability to resist HL. However, it has not been clearly confirmed which photoprotection strategy is the major HL resistance mechanism. To reveal the major photoprotection mechanism against short-term high light (STHL), the physiological and biochemical responses of three Arabidopsis mutants (Col, chi and ans) under STHL were analyzed in this study. After STHL treatment, the most serious photosynthetic pigment damage was observed in chi plants. At the same time, the degrees of membrane and Rubisco damage in chi was the highest, followed by Col, and ans was the smallest. The results showed that ans with high antioxidant capacity showed higher resistance to STHL treatment than Col containing anthocyanins, while chi with no anthocyanin accumulation and small antioxidant capacity had the lowest resistance. In addition, the gene expression results showed that plants tend to synthesize anthocyanin precursor flavonoids with antioxidant capacity under STHL stress. To further determine the major mechanism of photoprotection under STHL, we also analyzed Arabidopsis lines (Col, CHS1, CHS2 and tt4) that had the same anthocyanin content but different antioxidant capacities. It was found that CHS2 with high antioxidant capacity had higher cell viability, smaller maximal quantum yield of PSII photochemistry (F/F) reduction and less reactive oxygen species (ROS) accumulation under HL treatment of their mesophyll protoplasts. Therefore, the antioxidant capacity provided by antioxidant substances was the major mechanism of plant photoprotection under STHL treatment.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.plaphy.2021.06.006DOI Listing
June 2021

Concealed Object Detection.

IEEE Trans Pattern Anal Mach Intell 2021 Jun 1;PP. Epub 2021 Jun 1.

We present the first systematic study on concealed object detection (COD), which aims to identify objects that are ?perfectly? embedded in their background. The high intrinsic similarities between the concealed objects and their background make COD far more challenging than traditional object detection/segmentation. To better understand this task, we collect a large-scale dataset, called COD10K, which consists of 10,000 images covering concealed objects in diverse real-world scenarios from 78 object categories. Further, we provide rich annotations including object categories, object boundaries, challenging attributes, object-level labels, and instance-level annotations. Our COD10K enables comprehensive concealed object understanding and can even be used to help progress several other vision tasks, such as detection, segmentation, classification etc. We also design a simple but strong baseline for COD, termed the Search Identification Network (SINet). Without any bells and whistles, SINet outperform 12 cutting-edge baselines on all datasets tested, making them robust, general architectures that could serve as catalysts for future research in COD. Finally, we provide some interesting findings, and highlight several potential applications and future directions. To spark research in this new field, our code, dataset, and online demo are available at our project page: http://mmcheng.net/cod.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2021.3085766DOI Listing
June 2021

SCUBE3 serves as an independent poor prognostic factor in breast cancer.

Cancer Cell Int 2021 May 18;21(1):268. Epub 2021 May 18.

Biobank, Institute of Translational Medicine, Shenzhen Second People's Hospital, First Affiliated Hospital of Shenzhen University, Shenzhen, 518035, China.

Background: Accumulating evidences indicate that the signal peptide-CUB-EGF-like domain-containing protein 3 (SCUBE3) plays a key role in the development and progression of many human cancers. However, the underlying mechanism and prognosis value of SCUBE3 in breast cancer are still unclear.

Methods: The clinical data of 137 patients with breast cancer who underwent surgical resection in Taizhou Hospital of Zhejiang Province were retrospectively analyzed. We first conducted a comprehensive study on the expression pattern of SCUBE3 using the Tumor Immune Estimation Resource (TIMER) and UALCAN databases. In addition, the expression of SCUBE3 in breast tumor tissues was confirmed by immunohistochemistry. The protein-protein interaction analysis and functional enrichment analysis of SCUBE3 were analyzed using the STRING and Enrichr databases. Moreover, tissue microarray (TMA) was used to analyze the relationship between SCUBE3 expression levels and clinical-pathological parameters, such as histological type, grade, the status of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor (HER2). We further supplemented and identified the above results using the UALCAN and bc-GenExMiner v4.4 databases from TCGA data. The correlation between the expression of SCUBE3 and survival was calculated by multivariate Cox regression analysis to investigate whether SCUBE3 expression may be an independent prognostic factor of breast cancer.

Results: We found that the expression level of SCUBE3 was significantly upregulated in breast cancer tissue compared with adjacent normal tissues. The results showed that the distribution of breast cancer patients in the high expression group and the low expression group was significantly different in ER, PR, HER2, E-cadherin, and survival state (p < 0.05), but there was no significant difference in histologic grade, histologic type, tumor size, lymph node metastasis, TMN stage, subtypes, or recurrence (p > 0.05). In addition, the high expression of SCUBE3 was associated with relatively poor prognosis of ER- (p = 0.012), PR- (p = 0.029), HER2 + (p = 0.007). The multivariate Cox regression analysis showed that the hazard ratio (HR) was 2.80 (95% CI 1.20-6.51, p = 0.0168) in individuals with high SCUBE3 expression, and HR was increased by 1.86 (95% CI 1.06-3.25, p = 0.0300) for per 1-point increase of SCUBE3 expression.

Conclusions: These findings demonstrate that the high expression of SCUBE3 indicates poor prognosis in breast cancer. SCUBE3 expression may serve as a potential diagnostic indicator of breast cancer.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s12935-021-01947-3DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8130162PMC
May 2021

Semi-supervised Perception Augmentation for Aerial Photo Topologies Understanding.

IEEE Trans Image Process 2021 May 18;PP. Epub 2021 May 18.

Intelligently understanding the sophisticated topological structures from aerial photographs is a useful technique in aerial image analysis. Conventional methods cannot fulfill this task due to the following challenges: 1) the topology number of an aerial photo increases exponentially with the topology size, which requires a fine-grained visual descriptor to discriminatively represent each topology; 2) identifying visually/semantically salient topologies within each aerial photo in a weakly-labeled context, owing to the unaffordable human resources required for pixel-level annotation; and 3) designing a cross-domain knowledge transferal module to augment aerial photo perception, since multi-resolution aerial photos are taken asynchronistically in practice. To handle the above problems, we propose a unified framework to understand aerial photo topologies, focusing on representing each aerial photo by a set of visually/semantically salient topologies based on human visual perception and further employing them for visual categorization. Specifically, we first extract multiple atomic regions from each aerial photo, and thereby graphlets are built to capture the each aerial photo topologically. Then, a weakly-supervised ranking algorithm selects a few semantically salient graphlets by seamlessly encoding multiple image-level attributes. Toward a visualizable and perception-aware framework, we construct gaze shifting path (GSP) by linking the top-ranking graphlets. Finally, we derive the deep GSP representation, and formulate a semi-supervised and cross-domain SVM to partition each aerial photo into multiple categories. The SVM utilizes the global composition from low-resolution counterparts to enhance the deep GSP features from high-resolution aerial photos which are partially-annotated. Extensive visualization results and categorization performance comparisons have demonstrated the competitiveness of our approach.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3079820DOI Listing
May 2021

Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition.

IEEE Trans Image Process 2021 13;30:4894-4904. Epub 2021 May 13.

Deep convolutional neural networks have largely benefited computer vision tasks. However, the high computational complexity limits their real-world applications. To this end, many methods have been proposed for efficient network learning, and applications in portable mobile devices. In this paper, we propose a novel Moving-Mobile-Network, named MNet, for landmark recognition, equipped each landmark image with located geographic information. We intuitively find that MNet can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy. The above intuition is achieved by our proposed reward function with the input of geo-location and landmarks. We also find that the performance of other portable networks can be improved via our architecture. We construct two landmark image datasets, with each landmark associated with geographic information, over which we conduct extensive experiments to demonstrate that MNet achieves improved recognition accuracy with comparable complexity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3076275DOI Listing
May 2021

From Handcrafted to Deep Features for Pedestrian Detection: A Survey.

IEEE Trans Pattern Anal Mach Intell 2021 Apr 30;PP. Epub 2021 Apr 30.

Pedestrian detection is an important but challenging problem in computer vision, especially in human-centric tasks. Over the past decade, significant improvement has been witnessed with the help of handcrafted features and deep features. Here we present a comprehensive survey on recent advances in pedestrian detection. First, we provide a detailed review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches. For handcrafted features based methods, we present an extensive review of approaches and find that handcrafted features with large freedom degrees in shape and space have better performance. In the case of deep features based approaches, we split them into pure CNN based methods and those employing both handcrafted and CNN based features. We give the statistical analysis and tendency of these methods, where feature enhanced, part-aware, and post-processing methods have attracted main attention. In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance. Furthermore, we introduce some related datasets and evaluation metrics, and a deep experimental analysis. We conclude this survey by emphasizing open problems that need to be addressed and highlighting various future directions. Researchers can track an up-to-date list at \url{https://github.com/JialeCao001/PedSurvey}.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2021.3076733DOI Listing
April 2021

Epidemiological investigation and antimicrobial susceptibility analysis of Ureaplasma and Mycoplasma hominis in a teaching hospital in Shenyang, China.

J Infect Chemother 2021 Aug 11;27(8):1212-1216. Epub 2021 Apr 11.

Department of Laboratory Medicine, The People's Hospital of Liaoning Province, Shenyang, China. Electronic address:

Objectives: The aim of this study was to estimate the prevalence and antimicrobial susceptibility of Ureaplasma urealyticum and Mycoplasma hominis in a comprehensive teaching hospital Shenyang, China over the past 4 years.

Methods: A total of 1448 individuals with urogenital symptoms underwent mycoplasma testing between April 2016 and March 2020. Detection, identification and antimicrobial susceptibility testing were carried out using Mycoplasma ID/AST kits.

Results: The total infection rate of genital mycoplasmas was 37.5% (543/1448 cases) with an observed increase over the past 4 years. The positive rates of all three detected infections, as well as overall infection rate, were significantly higher in females than in males (P < 0.05). A higher positive rate of infection was observed in females aged 25-29 (60.5%), and in the 15-19 years age group (57.7%). The changes observed among all age groups of females were statistically significantly different (P < 0.001). The positive rates of U. urealyticum and M. hominis co-infection among the four seasons during which the survey was carried out were also observed to be statistically different (P = 0.01). More than 70% of U. urealyticum isolates were found to be resistant to ciprofloxacin, and more than 80% of M. hominis isolates were resistant to erythromycin, roxithromycin, azithromycin and clarithromycin. Josamycin, doxycycline and minocycline were most effective against U. urealyticum and M. hominis.

Conclusions: Results of this study found increasing rates of U. urealyticum and M. hominis infection over the past 4 years, particularly among younger age groups. U. urealyticum/Mycoplasma hominis screening among younger age cohorts are therefore strongly recommend to preventing the spread of pathogens. Monitoring antimicrobial resistance is important for preventing transmission of resistant strains of infection and for the management of antibiotics.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jiac.2021.03.022DOI Listing
August 2021

VMAN: A Virtual Mainstay Alignment Network for Transductive Zero-Shot Learning.

IEEE Trans Image Process 2021 16;30:4316-4329. Epub 2021 Apr 16.

Transductive zero-shot learning (TZSL) extends conventional ZSL by leveraging (unlabeled) unseen images for model training. A typical method for ZSL involves learning embedding weights from the feature space to the semantic space. However, the learned weights in most existing methods are dominated by seen images, and can thus not be adapted to unseen images very well. In this paper, to align the (embedding) weights for better knowledge transfer between seen/unseen classes, we propose the virtual mainstay alignment network (VMAN), which is tailored for the transductive ZSL task. Specifically, VMAN is casted as a tied encoder-decoder net, thus only one linear mapping weights need to be learned. To explicitly learn the weights in VMAN, for the first time in ZSL, we propose to generate virtual mainstay (VM) samples for each seen class, which serve as new training data and can prevent the weights from being shifted to seen images, to some extent. Moreover, a weighted reconstruction scheme is proposed and incorporated into the model training phase, in both the semantic/feature spaces. In this way, the manifold relationships of the VM samples are well preserved. To further align the weights to adapt to more unseen images, a novel instance-category matching regularization is proposed for model re-training. VMAN is thus modeled as a nested minimization problem and is solved by a Taylor approximate optimization paradigm. In comprehensive evaluations on four benchmark datasets, VMAN achieves superior performances under the (Generalized) TZSL setting.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3070231DOI Listing
April 2021

A Generalized Method for Binary Optimization: Convergence Analysis and Applications.

IEEE Trans Pattern Anal Mach Intell 2021 Apr 2;PP. Epub 2021 Apr 2.

Binary optimization problems (BOPs) arise naturally in many fields, such as information retrieval, computer vision, and machine learning. Most existing binary optimization methods either use continuous relaxation which can cause large quantization errors, or incorporate a highly specific algorithm that can only be used for particular loss functions. To overcome these difficulties, we propose a novel generalized optimization method, named Alternating Binary Matrix Optimization (ABMO), for solving BOPs. ABMO can handle BOPs with/without orthogonality or linear constraints for a large class of loss functions. ABMO involves rewriting the binary, orthogonality and linear constraints for BOPs as an intersection of two closed sets, then iteratively dividing the original problems into several small optimization problems that can be solved as closed forms. To provide a strict theoretical convergence analysis, we add a sufficiently small perturbation and translate the original problem to an approximated problem whose feasible set is continuous. We not only provide rigorous mathematical proof for the convergence to a stationary and feasible point, but also derive the convergence rate of the proposed algorithm. The promising results obtained from four binary optimization tasks validate the superiority and the generality of ABMO compared with the state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2021.3070753DOI Listing
April 2021

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection.

IEEE Trans Image Process 2021 7;30:4046-4056. Epub 2021 Apr 7.

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend to suffer from a shortage of annotated training samples. Moreover, existing methods of feature alignments are not sufficient to learn domain-invariant representations. To address these limitations, we propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training into a unified framework. An intermediate domain image generator is proposed to enhance feature alignments by domain-adversarial training with automatically generated soft domain labels. The synthetic intermediate domain images progressively bridge the domain divergence and augment the annotated source domain training data. A feature pyramid alignment is designed and the corresponding feature discriminator is used to align multi-scale convolutional features of different semantic levels. Last but not least, we introduce a region feature alignment and an instance discriminator to learn domain-invariant features for object proposals. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations. Further extensive experiments verify the effectiveness of each component and demonstrate that the proposed network can learn domain-invariant representations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2021.3066046DOI Listing
April 2021

Can constructed wetlands be more land efficient than centralized wastewater treatment systems? A case study based on direct and indirect land use.

Sci Total Environ 2021 May 23;770:144841. Epub 2021 Jan 23.

Laboratory of Systems Ecology and Sustainability Science, College of Engineering, Peking University, Beijing 100871, China. Electronic address:

Compared with centralized wastewater treatment systems, constructed wetlands are generally regarded as not suitable for wide deployment due to the comparatively larger direct land area. Much of the traditional thinking is based on an onsite perspective, while the offsite information is left out. By a comparative case study with systems accounting of both onsite and offsite land use, this study questioned the traditional picture and found that constructed wetlands can be more land use efficient than centralized wastewater treatment systems. On a unit of wastewater treated basis, the land use induced by a typical constructed wetland in China is revealed to be less than half of that by the case of a centralized wastewater treatment plant or a hybrid system. On a unit removal basis for biological oxygen demand (BOD), chemical oxygen demand (COD), total suspended solid (TSS) and ammonia‑nitrogen (NH-N), the land use induced by a constructed wetland is only around 61%, 67%, 73% and 64% of that by a centralized wastewater treatment system, respectively. Meanwhile, the indirect effect is demonstrated to be significant for these three systems: this magnitude amounts to three times the direct land occupation for a constructed wetland, and one order of magnitude higher of that for the a centralized wastewater treatment system. By a scenario analysis for China in 2017, it is preliminarily estimated that over two billion square meters of land use could be reduced if all the centralized wastewater treatment systems are replaced by constructed wetlands. The outcome may serve a benchmark and offers a new way of thinking for management of wastewater treatment systems.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.scitotenv.2020.144841DOI Listing
May 2021

Chylous Ascites as a Presentation of Lymphangioleiomyomatosis.

ACG Case Rep J 2021 Mar 3;8(3):e00517. Epub 2021 Mar 3.

Department of Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA.

A 35-year-old woman presented to the hospital with a 4-week history of large-volume chylous ascites refractory to paracentesis and new-onset dyspnea. Thoracic computed tomography revealed diffuse pulmonary cystic lesions with pleural effusions, and abdominal computed tomography showed ascites with large bilateral retroperitoneal masses displaying positron emission tomography avidity. Biopsy of the masses demonstrated lymphatic invasion by a perivascular epithelioid cell neoplasm, a smooth muscle tumor. The patient was diagnosed as having the sporadic form of lymphangioleiomyomatosis and was treated with the mammalian target of rapamycin pathway inhibitor sirolumus with clinical improvement.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.14309/crj.0000000000000517DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7932795PMC
March 2021

Bioinspired Scene Classification by Deep Active Learning With Remote Sensing Applications.

IEEE Trans Cybern 2021 Feb 26;PP. Epub 2021 Feb 26.

Accurately classifying sceneries with different spatial configurations is an indispensable technique in computer vision and intelligent systems, for example, scene parsing, robot motion planning, and autonomous driving. Remarkable performance has been achieved by the deep recognition models in the past decade. As far as we know, however, these deep architectures are incapable of explicitly encoding the human visual perception, that is, the sequence of gaze movements and the subsequent cognitive processes. In this article, a biologically inspired deep model is proposed for scene classification, where the human gaze behaviors are robustly discovered and represented by a unified deep active learning (UDAL) framework. More specifically, to characterize objects' components with varied sizes, an objectness measure is employed to decompose each scenery into a set of semantically aware object patches. To represent each region at a low level, a local-global feature fusion scheme is developed which optimally integrates multimodal features by automatically calculating each feature's weight. To mimic the human visual perception of various sceneries, we develop the UDAL that hierarchically represents the human gaze behavior by recognizing semantically important regions within the scenery. Importantly, UDAL combines the semantically salient region detection and the deep gaze shifting path (GSP) representation learning into a principled framework, where only the partial semantic tags are required. Meanwhile, by incorporating the sparsity penalty, the contaminated/redundant low-level regional features can be intelligently avoided. Finally, the learned deep GSP features from the entire scene images are integrated to form an image kernel machine, which is subsequently fed into a kernel SVM to classify different sceneries. Experimental evaluations on six well-known scenery sets (including remote sensing images) have shown the competitiveness of our approach.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCYB.2020.2981480DOI Listing
February 2021

Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation.

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

In supervised learning for medical image analysis, sample selection methodologies are fundamental to attain optimum system performance promptly and with minimal expert interactions (e.g. label querying in an active learning setup). In this paper we propose a novel sample selection methodology based on deep features leveraging information contained in interpretability saliency maps. In the absence of ground truth labels for informative samples, we use a novel self supervised learning based approach for training a classifier that learns to identify the most informative sample in a given batch of images. We demonstrate the benefits of the proposed approach, termed Interpretability-Driven Sample Selection (IDEAL), in an active learning setup aimed at lung disease classification and histopathology image segmentation. We analyze three different approaches to determine sample informativeness from interpretability saliency maps: (i) an observational model stemming from findings on previous uncertainty-based sample selection approaches, (ii) a radiomics-based model, and (iii) a novel data-driven self-supervised approach. We compare IDEAL to other baselines using the publicly available NIH chest X-ray dataset for lung disease classification, and a public histopathology segmentation dataset (GLaS), demonstrating the potential of using interpretability information for sample selection in active learning systems. Results show our proposed self supervised approach outperforms other approaches in selecting informative samples leading to state of the art performance with fewer samples.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3061724DOI Listing
February 2021

Massive-Scale Aerial Photo Categorization by Cross-Resolution Visual Perception Enhancement.

IEEE Trans Neural Netw Learn Syst 2021 Feb 15;PP. Epub 2021 Feb 15.

Categorizing aerial photographs with varied weather/lighting conditions and sophisticated geomorphic factors is a key module in autonomous navigation, environmental evaluation, and so on. Previous image recognizers cannot fulfill this task due to three challenges: 1) localizing visually/semantically salient regions within each aerial photograph in a weakly annotated context due to the unaffordable human resources required for pixel-level annotation; 2) aerial photographs are generally with multiple informative attributes (e.g., clarity and reflectivity), and we have to encode them for better aerial photograph modeling; and 3) designing a cross-domain knowledge transferal module to enhance aerial photograph perception since multiresolution aerial photographs are taken asynchronistically and are mutually complementary. To handle the above problems, we propose to optimize aerial photograph's feature learning by leveraging the low-resolution spatial composition to enhance the deep learning of perceptual features with a high resolution. More specifically, we first extract many BING-based object patches (Cheng et al., 2014) from each aerial photograph. A weakly supervised ranking algorithm selects a few semantically salient ones by seamlessly incorporating multiple aerial photograph attributes. Toward an interpretable aerial photograph recognizer indicative to human visual perception, we construct a gaze shifting path (GSP) by linking the top-ranking object patches and, subsequently, derive the deep GSP feature. Finally, a cross-domain multilabel SVM is formulated to categorize each aerial photograph. It leverages the global feature from low-resolution counterparts to optimize the deep GSP feature from a high-resolution aerial photograph. Comparative results on our compiled million-scale aerial photograph set have demonstrated the competitiveness of our approach. Besides, the eye-tracking experiment has shown that our ranking-based GSPs are over 92% consistent with the real human gaze shifting sequences.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2021.3055548DOI Listing
February 2021

P017 Sarcopenia Defined by Psoas Muscle Thickness is Not a Predictor of Post-Operative Outcomes in IBD Patients.

Am J Gastroenterol 2020 Dec;115(Suppl 1):S4-S5

University of Southern California Keck School of Medicine, Los Angeles, United States.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.14309/01.ajg.0000722864.89464.a2DOI Listing
December 2020

Deep Learning for Person Re-identification: A Survey and Outlook.

IEEE Trans Pattern Anal Mach Intell 2021 Jan 26;PP. Epub 2021 Jan 26.

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for four different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criterion to evaluate the Re-ID system. Finally, some important yet under-investigated open issues are discussed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2021.3054775DOI Listing
January 2021

Generalized Zero-Shot Learning With Multiple Graph Adaptive Generative Networks.

IEEE Trans Neural Netw Learn Syst 2021 Jan 25;PP. Epub 2021 Jan 25.

Generative adversarial networks (GANs) for (generalized) zero-shot learning (ZSL) aim to generate unseen image features when conditioned on unseen class embeddings, each of which corresponds to one unique category. Most existing works on GANs for ZSL generate features by merely feeding the seen image feature/class embedding (combined with random Gaussian noise) pairs into the generator/discriminator for a two-player minimax game. However, the structure consistency of the distributions among the real/fake image features, which may shift the generated features away from their real distribution to some extent, is seldom considered. In this paper, to align the weights of the generator for better structure consistency between real/fake features, we propose a novel multigraph adaptive GAN (MGA-GAN). Specifically, a Wasserstein GAN equipped with a classification loss is trained to generate discriminative features with structure consistency. MGA-GAN leverages the multigraph similarity structures between sliced seen real/fake feature samples to assist in updating the generator weights in the local feature manifold. Moreover, correlation graphs for the whole real/fake features are adopted to guarantee structure correlation in the global feature manifold. Extensive evaluations on four benchmarks demonstrate well the superiority of MGA-GAN over its state-of-the-art counterparts.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2020.3046924DOI Listing
January 2021

Interaction of RIPK1 and A20 modulates MAPK signaling in murine acetaminophen toxicity.

J Biol Chem 2021 Jan-Jun;296:100300. Epub 2021 Jan 16.

Division of Gastrointestinal and Liver Diseases, Department of Medicine, Keck School of Medicine of University of Southern California, Los Angeles, California, USA; USC Research Center for Liver Disease, Keck School of Medicine of University of Southern California, Los Angeles, California, USA. Electronic address:

Acetaminophen (APAP)-induced liver necrosis is a form of regulated cell death (RCD) in which APAP activates the mitogen-activated protein kinases (MAPKs) and specifically the c-Jun-N-terminal kinase (JNK) pathway, leading to necrotic cell death. Previously, we have shown that receptor interacting protein kinase-1 (RIPK1) knockdown is also protective against APAP RCD upstream of JNK. However, whether the kinase or platform function of RIPK1 is involved in APAP RCD is not known. To answer this question, we used genetic mouse models of targeted hepatocyte RIPK1 knockout (RIPK1) or kinase dead knock-in (RIPK1) and adult hepatocyte specific knockout of the cytoprotective protein A20 (A20), known to interact with RIPK1, to study its potential involvement in MAPK signaling. We observed no difference in injury between WT and RIPK mice post APAP. However, RIPK1 was protective. We found that RIPK1 mice had attenuated pJNK activation, while A20 was simultaneously upregulated. Conversely, A20 markedly worsened liver injury from APAP. Mechanistically, we observed a significant upregulation of apoptosis signal-regulating kinase 1 (ASK1) and increased JNK activation in A20 mice compared with littermate controls. We also demonstrated that A20 coimmunoprecipitated (co-IP) with both RIPK1 and ASK1, and that in the presence of RIPK1, there was less A20-ASK1 association than in its absence. We conclude that the kinase-independent platform function of RIPK1 is involved in APAP toxicity. Adult RIPK1 mice are protected against APAP by upregulating A20 and attenuating JNK signaling through ASK1, conversely, A20 worsens injury from APAP.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jbc.2021.100300DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7948960PMC
January 2021

RGB-D salient object detection: A survey.

Comput Vis Media (Beijing) 2021 Jan 7:1-33. Epub 2021 Jan 7.

Inception Institute of Artificial Intelligence (IIAI), Abu Dhabi, United Arab Emirates.

Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at https://github.com/taozh2017/RGBD-SODsurvey.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s41095-020-0199-zDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7788385PMC
January 2021

Improving Single Shot Object Detection With Feature Scale Unmixing.

IEEE Trans Image Process 2021 10;30:2708-2721. Epub 2021 Feb 10.

Due to the advantages of real-time detection and improved performance, single-shot detectors have gained great attention recently. To solve the complex scale variations, single-shot detectors make scale-aware predictions based on multiple pyramid layers. Typically, small objects are detected on shallow layers while large objects are detected on deep layers. However, the features in the pyramid are not scale-aware enough, which limits the detection performance. Two common problems in single-shot detectors caused by object scale variations can be observed: (1) false negative problem, i.e., small objects are easily missed due to the weak features; (2) part-false positive problem, i.e., the salient part of a large object is sometimes detected as an object. With this observation, a new Neighbor Erasing and Transferring (NET) mechanism is proposed for feature scale-unmixing to explore scale-aware features in this paper. In NET, a Neighbor Erasing Module (NEM) is designed to erase the salient features of large objects and emphasize the features of small objects in shallow layers. A Neighbor Transferring Module (NTM) is introduced to transfer the erased features and highlight large objects in deep layers. With this mechanism, a single-shot network called NETNet is constructed for scale-aware object detection. In addition, we propose to aggregate nearest neighboring pyramid features to enhance our NET. Experiments on MS COCO dataset and UAVDT dataset demonstrate the effectiveness of our method. NETNet obtains 38.5% AP at a speed of 27 FPS and 32.0% AP at a speed of 55 FPS on MS COCO dataset. As a result, NETNet achieves a better trade-off for real-time and accurate object detection.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2020.3048630DOI Listing
February 2021

Contrast-Attentive Thoracic Disease Recognition With Dual-Weighting Graph Reasoning.

IEEE Trans Med Imaging 2021 04 1;40(4):1196-1206. Epub 2021 Apr 1.

Automatic thoracic disease diagnosis is a rising research topic in the medical imaging community, with many potential applications. However, the inconsistent appearances and high complexities of various lesions in chest X-rays currently hinder the development of a reliable and robust intelligent diagnosis system. Attending to the high-probability abnormal regions and exploiting the priori of a related knowledge graph offers one promising route to addressing these issues. As such, in this paper, we propose two contrastive abnormal attention models and a dual-weighting graph convolution to improve the performance of thoracic multi-disease recognition. First, a left-right lung contrastive network is designed to learn intra-attentive abnormal features to better identify the most common thoracic diseases, whose lesions rarely appear in both sides symmetrically. Moreover, an inter-contrastive abnormal attention model aims to compare the query scan with multiple anchor scans without lesions to compute the abnormal attention map. Once the intra- and inter-contrastive attentions are weighted over the features, in addition to the basic visual spatial convolution, a chest radiology graph is constructed for dual-weighting graph reasoning. Extensive experiments on the public NIH ChestX-ray and CheXpert datasets show that our model achieves consistent improvements over the state-of-the-art methods both on thoracic disease identification and localization.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3049498DOI Listing
April 2021

Unveiling land footprint of solar power: A pilot solar tower project in China.

J Environ Manage 2021 Feb 23;280:111741. Epub 2020 Dec 23.

Department of Environmental Sciences, COMSATS University Islamabad (CUI), Vehari Campus, Pakistan.

Land occupation by solar power installations has become a rising concern that may cause adverse impacts on natural ecosystems and biodiversity. Existing studies mainly adopt a local perspective to view land use requirements of solar power and forget that the solar-based electricity system is subordinate to the macro economy and nourished by the material, machinery and service support by various economic sectors. To manifest a key aspect of the footprint of solar power on land resources, this study uncovered the extensive industrial land use initiated by the infrastructure of a representative pilot solar-based electricity plant using a systems perspective. The results in this study show that in magnitude, land footprint by the infrastructure of the pilot solar plant amounts to three times as much as the onsite land area. Also, the land footprint calculated is revealed as one order of magnitude larger than a previous finding that includes primary materials only, and four to seven times higher than the onsite land use by coal-based electricity plants. The outcome implies that existing environmental management policies need to be re-evaluated by putting enough emphasis on the land displacement by solar power systems along the production chain.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jenvman.2020.111741DOI Listing
February 2021

DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images.

IEEE J Biomed Health Inform 2020 Dec 17;PP. Epub 2020 Dec 17.

Diabetic retinopathy (DR) is a complication of diabetes that severely affects eyes. It can be graded into five levels of severity according to international protocol. However, optimizing a grading model to have strong generalizability requires a large amount of balanced training data, which is difficult to collect, particularly for the high severity levels. Typical data augmentation methods, including random flipping and rotation, cannot generate data with high diversity. In this paper, we propose a diabetic retinopathy generative adversarial network (DR-GAN) to synthesize high-resolution fundus images which can be manipulated with arbitrary grading and lesion information. Thus, large-scale generated data can be used for more meaningful augmentation to train a DR grading and lesion segmentation model. The proposed retina generator is conditioned on the structural and lesion masks, as well as adaptive grading vectors sampled from the latent grading space, which can be adopted to control the synthesized grading severity. Moreover, a multi-scale spatial and channel attention module is devised to improve the generation ability to synthesize small details. Multi-scale discriminators are designed to operate from large to small receptive fields, and joint adversarial losses are adopted to optimize the whole network in an end-to-end manner. With extensive experiments evaluated on the EyePACS dataset connected to Kaggle, as well as the FGADR dataset, we validate the effectiveness of our method, which can both synthesize highly realistic (1280 × 1280) controllable fundus images and contribute to the DR grading task.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2020.3045475DOI Listing
December 2020

Modeling and Enhancing Low-Quality Retinal Fundus Images.

IEEE Trans Med Imaging 2021 03 2;40(3):996-1006. Epub 2021 Mar 2.

Retinal fundus images are widely used for the clinical screening and diagnosis of eye diseases. However, fundus images captured by operators with various levels of experience have a large variation in quality. Low-quality fundus images increase uncertainty in clinical observation and lead to the risk of misdiagnosis. However, due to the special optical beam of fundus imaging and structure of the retina, natural image enhancement methods cannot be utilized directly to address this. In this article, we first analyze the ophthalmoscope imaging system and simulate a reliable degradation of major inferior-quality factors, including uneven illumination, image blurring, and artifacts. Then, based on the degradation model, a clinically oriented fundus enhancement network (cofe-Net) is proposed to suppress global degradation factors, while simultaneously preserving anatomical retinal structures and pathological characteristics for clinical observation and analysis. Experiments on both synthetic and real images demonstrate that our algorithm effectively corrects low-quality fundus images without losing retinal details. Moreover, we also show that the fundus correction method can benefit medical image analysis applications, e.g., retinal vessel segmentation and optic disc/cup detection.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3043495DOI Listing
March 2021
-->