Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
57,381
result(s) for
"Yu, Cheng"
Sort by:
A Sleep Apnea Detection System Based on a One-Dimensional Deep Convolution Neural Network Model Using Single-Lead Electrocardiogram
Many works in recent years have been focused on developing a portable and less expensive system for diagnosing patients with obstructive sleep apnea (OSA), instead of using the inconvenient and expensive polysomnography (PSG). This study proposes a sleep apnea detection system based on a one-dimensional (1D) deep convolutional neural network (CNN) model using the single-lead 1D electrocardiogram (ECG) signals. The proposed CNN model consists of 10 identical CNN-based feature extraction layers, a flattened layer, 4 identical classification layers mainly composed of fully connected networks, and a softmax classification layer. Thirty-five released and thirty-five withheld ECG recordings from the MIT PhysioNet Apnea-ECG Database were applied to train the proposed CNN model and validate its accuracy for the detection of the apnea events. The results show that the proposed model achieves 87.9% accuracy, 92.0% specificity, and 81.1% sensitivity for per-minute apnea detection, and 97.1% accuracy, 100% specificity, and 95.7% sensitivity for per-recording classification. The proposed model improves the accuracy of sleep apnea detection in comparison with several feature-engineering-based and feature-learning-based approaches.
Journal Article
An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping.
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole slide images (WSIs), which requires researchers to adopt patch-based methods and laborious free-hand contouring. Here, the authors develop a whole-slide training method to classify types of lung cancers using slide-level diagnoses with deep learning.
Journal Article
التحول الأخضر للمدن الصينية : تحديات التغير المناخي وآليات استجابة بكين
يتناول كتاب (التحول الأخضر للمدن لصينية : تحديات التغير المناخي وآليات استجابة بكين) والذي قام بتأليفه (دو شوو خو) في حوالي (334) صفحة من القطع المتوسط موضوع (التنمية الاقتصادية الصينية) مستعرضا المحتويات في الأبواب التالية : الأول : تحديات تغير المناخ وسبل الاستجابة لها، الباب الثاني : التنمية المستدامة للبيئة الإيكولوجية الحضرية، الباب الثالث : حماية ومعالجة البيئة الجوية الحضرية، الباب الرابع : بناء نظم مؤشرات تقييم مدن \"النوع الثالث\"
Book
Cancer-Derived Exosomes: Their Role in Cancer Biology and Biomarker Development
Exosomes are a subset of tiny extracellular vesicles manufactured by all cells and are present in all body fluids. They are produced actively in tumor cells, which are released and utilized to facilitate tumor growth. Their characteristics enable them to assist major cancer hallmarks, leveraged by cancer cells in fostering cancer growth and spread while implementing ways to escape elimination from the host environment. This review updates on the latest progress on the roles of cancer-derived exosomes, of 30-100 nm in size, in deregulating paracrine trafficking in the tumor microenvironment and circulation. Thus, exosomes are being exploited in diagnostic biomarker development, with its potential in clinical applications as therapeutic targets utilized in exosome-based nanoparticle drug delivery strategies for cancer therapy. Ongoing studies were retrieved from PubMed[R] and Scopus database and ClinicalTrials.gov registry for review, highlighting how cancer cells from entirely different cell lines rely on genetic information carried by their exosomes for homotypic and heterotypic intercellular communications in the microenvironment to favor proliferation and invasion, while establishing a pre-metastatic niche in welcoming cancer cells' arrival. We will elaborate on the trafficking of tumor-derived exosomes in fostering cancer proliferation, invasion, and metastasis in hematopoietic (leukemia and myeloma), epithelial (breast cancer), and mesenchymal (soft tissue sarcoma and osteosarcoma) cancers. Cancer-derived exosomal trafficking is observed in several types of liquid or solid tumors, confirming their role as cancer hallmark enabler. Their enriched genetic signals arising from their characteristic DNA, RNA, microRNA, and lncRNA, along with specific gene expression profiles, protein, or lipid composition carried by the exosomal cargo shed into blood, saliva, urine, ascites, and cervicovaginal lavage, are being studied as a diagnostic, prognostic, or predictive cancer biomarker. We reveal the latest research efforts in exploiting the use of nanoparticles to improve the overall cancer diagnostic capability in the clinic. Keywords: tumor-released exosomes, carcinoma-associated fibroblasts, exosome cargo, exosome-induced chemoresistance, hallmarks of cancer, tumor-stromal communications
Journal Article
Logistic regression was as good as machine learning for predicting major chronic diseases
To evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for the prediction of risk of cardiovascular diseases (CVDs), chronic kidney disease (CKD), diabetes (DM), and hypertension (HTN) and in a prospective cohort study using simple clinical predictors.
We conducted analyses in a population-based cohort study in Asian adults (n = 6,762). Five different ML models were considered—single-hidden-layer neural network, support vector machine, random forest, gradient boosting machine, and k-nearest neighbor—and were compared with standard logistic regression.
The incidences at 6 years of CVD, CKD, DM, and HTN cases were 4.0%, 7.0%, 9.2%, and 34.6%, respectively. Logistic regression reached the highest area under the receiver operating characteristic curve for CKD (0.905 [0.88, 0.93]) and DM (0.768 [0.73, 0.81]) predictions. For CVD and HTN, the best models were neural network (0.753 [0.70, 0.81]) and support vector machine (0.780 [0.747, 0.812]), respectively. However, the differences with logistic regression were small (less than 1%) and nonsignificant. Logistic regression, gradient boosting machine, and neural network were systematically ranked among the best models.
Logistic regression yields as good performance as ML models to predict the risk of major chronic diseases with low incidence and simple clinical predictors.
•Low-dimensional settings include low number of events and predictors.•In such settings, logistic regression yields as good performance as ML models.•ML techniques may not be warranted in such cases.
Journal Article
Neutrophils in Psoriasis
Neutrophils are the most abundant innate immune cells. The pathogenic roles of neutrophils are related to chronic inflammation and autoimmune diseases. Psoriasis is a chronic systemic inflammatory disease affecting ~2-3% of the world population. The abundant presence of neutrophils in the psoriatic skin lesions serves as a typical histopathologic hallmark of psoriasis. Recent reports indicated that oxidative stress, granular components, and neutrophil extracellular traps from psoriatic neutrophils are related to the initial and maintenance phases of psoriasis. This review provides an overview on the recent (up to 2019) advances in understanding the role of neutrophils in the pathophysiology of psoriasis, including the effects of respiratory burst, degranulation, and neutrophil extracellular trap formation on psoriatic immunity and the clinical relationships.
Journal Article
Tunable photonic heat transport in a quantum heat valve
Quantum thermodynamics is emerging both as a topic of fundamental research and as a means to understand and potentially improve the performance of quantum devices1–10. A prominent platform for achieving the necessary manipulation of quantum states is superconducting circuit quantum electrodynamics (QED)11. In this platform, thermalization of a quantum system12–15 can be achieved by interfacing the circuit QED subsystem with a thermal reservoir of appropriate Hilbert dimensionality. Here we study heat transport through an assembly consisting of a superconducting qubit16 capacitively coupled between two nominally identical coplanar waveguide resonators, each equipped with a heat reservoir in the form of a normal-metal mesoscopic resistor termination. We report the observation of tunable photonic heat transport through the resonator–qubit–resonator assembly, showing that the reservoir-to-reservoir heat flux depends on the interplay between the qubit–resonator and the resonator–reservoir couplings, yielding qualitatively dissimilar results in different coupling regimes. Our quantum heat valve is relevant for the realization of quantum heat engines17 and refrigerators, which can be obtained, for example, by exploiting the time-domain dynamics and coherence of driven superconducting qubits18,19. This effort would ultimately bridge the gap between the fields of quantum information and thermodynamics of mesoscopic systems.
Journal Article
Alternations of Metabolic Profile and Kynurenine Metabolism in the Plasma of Parkinson’s Disease
The pathogenesis of Parkinson’s disease (PD) remains to be elucidated. Metabolomic analysis has the potential to identify biochemical pathways and metabolic profiles that are involved in PD pathogenesis. Here, we performed a targeted metabolomics to quantify the plasma levels of 184 metabolites in a discovery cohort including 82 PD patients and 82 normal controls (NCs) and found two up-regulated (dopamine, putrescine/ornithine ratio) and four down-regulated (octadecadienylcarnitine C18:2, asymmetric dimethylarginine, tryptophan, and kynurenine (KYN)) metabolites in the plasma of PD patients. We then measured the plasma levels of a panel of metabolic products of KYN pathway in an independent validation cohort including 118 PD patients, 22 Huntington’s disease (HD) patients, and 37 NCs. Lower kynurenic acid (KA)/KYN ratio, higher quinolinic acid (QA) level, and QA/KA ratio were observed in PD patients compared to HD patients and NCs. PD patients at advanced stage (Hoehn-Yahr stage > 2) showed lower KA and KA/KYN ratio, as well as higher QA and QA/KA ratio compared to PD patients at early stage (Hoehn-Yahr stage ≤ 2) and NCs. Levels of KA and QA, as well as the ratios of KA/KYN and QA/KA between PD patients with and without psychiatric symptoms, dementia, or levodopa-induced dyskinesia in the advanced PD were similar. This metabolomic analyses demonstrate a number of plasma biomarker candidates for PD, suggesting a shift toward neurotoxic QA synthesis and away from neuroprotective KA production in KYN pathway.
Journal Article