Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline [1]. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net [2], FCN [3], and Mask- RCNN [4] were popularly used, typically based on ResNet [5] or VGG [6] base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.
Background:Static nature of performance reporting systems in health care sector has resulted in inconsistent, incomparable, time consuming, and static performance reports that are not able to transparently reflect a round picture of performance and effectively support healthcare managers’ decision makings. So, the healthcare sector needs interactive performance management tools such as performance dashboards to measure, monitor, and manage performance more effectively. The aim of this article was to identify key issues that need to be addressed for developing high-quality performance dashboards in healthcare sector.Methods:A literature review was established to search electronic research databases, e-journals collections, and printed journals, books, dissertations, and theses for relevant articles. The search strategy interchangeably used the terms of “dashboard”, “performance measurement system”, and “executive information system” with the term of “design” combined with operator “AND”. Search results (n=250) were adjusted for duplications, screened based on their abstract relevancy and full-text availability (n=147) and then assessed for eligibility (n=40). Eligible articles were included if they had explicitly focused on dashboards, performance measurement systems or executive information systems design. Finally, 28 relevant articles included in the study.Results:Creating high-quality performance dashboards requires addressing both performance measurement and executive information systems design issues. Covering these two fields, identified contents were categorized to four main domains: KPIs development, Data Sources and data generation, Integration of dashboards to source systems, and Information presentation issues.Conclusion:This study implies the main steps to develop dashboards for the purpose of performance management. Performance dashboards developed on performance measurement and executive information systems principles and supported by proper back-end infrastructure will result in creation of dynamic reports that help healthcare managers to consistently measure the performance, continuously detect outliers, deeply analyze causes of poor performance, and effectively plan for the future.
Application of computational methods in drug discovery has received increased attention in recent years as a way to accelerate drug target prediction. Based on 443 sequence-derived protein features, we applied the most commonly used machine learning methods to predict whether a protein is druggable as well as to opt for superior algorithm in this task. In addition, feature selection procedures were used to provide the best performance of each classifier according to the optimum number of features. When run on all features, Neural Network was the best classifier, with 89.98% accuracy, based on a k-fold cross-validation test. Among all the algorithms applied, the optimum number of most-relevant features was 130, according to the Support Vector Machine-Feature Selection (SVM-FS) algorithm. This study resulted in the discovery of new drug target which potentially can be employed in cell signaling pathways, gene expression, and signal transduction. The DrugMiner web tool was developed based on the findings of this study to provide researchers with the ability to predict druggable proteins. DrugMiner is freely available at www.DrugMiner.org.
Therapeutic activities of drugs are often influenced by co-administration of drugs that may cause inevitable drug-drug interactions (DDIs) and inadvertent side effects. Prediction and identification of DDIs are extremely vital for the patient safety and success of treatment modalities. A number of computational methods have been employed for the prediction of DDIs based on drugs structures and/or functions. Here, we report on a computational method for DDIs prediction based on functional similarity of drugs. The model was set based on key biological elements including carriers, transporters, enzymes and targets (CTET). The model was applied for 2189 approved drugs. For each drug, all the associated CTETs were collected, and the corresponding binary vectors were constructed to determine the DDIs. Various similarity measures were conducted to detect DDIs. Of the examined similarity methods, the inner product-based similarity measures (IPSMs) were found to provide improved prediction values. Altogether, 2,394,766 potential drug pairs interactions were studied. The model was able to predict over 250,000 unknown potential DDIs. Upon our findings, we propose the current method as a robust, yet simple and fast, universal in silico approach for identification of DDIs. We envision that this proposed method can be used as a practical technique for the detection of possible DDIs based on the functional similarities of drugs.
Background:In most countries chronic diseases lead to high health care costs and reduced productivity of people in society. The best way to reduce costs of health sector and increase the empowerment of people is prevention of chronic diseases and appropriate health activities management through monitoring of patients. To enjoy the full benefits of E-health, making use of methods and modern technologies is very important.Methods:this literature review articles were searched with keywords like Patient monitoring, Mobile Health, and Chronic Disease in Science Direct, Google Scholar and Pub Med databases without regard to the year of publications.Results:Applying remote medical diagnosis and monitoring system based on mobile health systems can help significantly to reduce health care costs, correct performance management particularly in chronic disease management. Also some challenges are in patient monitoring in general and specific aspects like threats to confidentiality and privacy, technology acceptance in general and lack of system interoperability with electronic health records and other IT tools, decrease in face to face communication between doctor and patient, sudden interruptions of telecommunication networks, and device and sensor type in specific aspect.Conclusions:It is obvious identifying the opportunities and challenges of mobile technology and reducing barriers, strengthening the positive points will have a significant role in the appropriate planning and promoting the achievements of the health care systems based on mobile and helps to design a roadmap for improvement of mobile health.
BackgroundIn recent years, mobile-based applications have become important technologies to the delivery of healthcare around the world. Mobile-based self-management systems with standard features for providing, evaluating, and improving HIV care are significantly required in developing countries.ObjectiveTo determine the common elements of a mobile-based self-management system for people living with HIV (PLWH).MethodsThis cross-sectional study was done in two main phases in 2017. In the first phase, a review was conducted in relevant databases such as; PubMed, Scopus, Up To Date, and Web of Science. The keywords used to search for resources were as follows; Self-care, Self-management, Data elements, Minimum data set, Mobile application, Mobile health, and HIV/AIDS. In the second phase, the infectious diseases specialists and health information managers affiliated with Tehran University of Medical Sciences were consulted to score identified elements by a questionnaire. Frequency and mean of collected data were calculated using SPSS software (version 19).ResultsBy full-text reviewing of 9 related articles, the identified elements were justified in 3 main categories and 37 subcategories including: clinical data elements (17), technical capabilities (12) and demographic data elements (8). According to the findings, among the clinical category, 11 data elements were selected by the statistical population. Among the identified technical capabilities, 11 features were selected. Moreover, 6 data elements were selected as the demographic category.ConclusionWe obtained data elements and technical capabilities of a mobile-based self-management system for people living with HIV. Using these elements and features, designing of self-management system architecture will be possible. Self-management skills of PLWH and their communication with healthcare providers will improve by using this system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.