Search results for "Machine learning"

showing 10 items of 1464 documents

Variable neighborhood descent for the incremental graph drawing

2017

Abstract Graphs are used to represent reality in several areas of knowledge. Drawings of graphs have many applications, from project scheduling to software diagrams. The main quality desired for drawings of graphs is readability, and crossing reduction is a fundamental aesthetic criterion for a good representation of a graph. In this paper we target the edge crossing reduction in the context of incremental graph drawing, in which we want to preserve the layout of a graph over successive drawings. We propose a hybrid method based on the GRASP (Greedy Randomized Adaptive Search Procedure) and VND (Variable Neighborhood Descent) methodologies and compare it with previous methods via simulation.

021103 operations researchTheoretical computer sciencebusiness.industryApplied MathematicsGRASP0211 other engineering and technologies010103 numerical & computational mathematics02 engineering and technologyMachine learningcomputer.software_genre01 natural sciencesReadabilitySoftwareGraph drawingDiscrete Mathematics and CombinatoricsArtificial intelligenceForce-directed graph drawing0101 mathematicsbusinessGraph operationsMetaheuristiccomputerGreedy randomized adaptive search procedureMathematicsofComputing_DISCRETEMATHEMATICSMathematicsElectronic Notes in Discrete Mathematics
researchProduct

Intelligence artificielle : quel avenir en anatomie pathologique ?

2019

Resume Les techniques d’intelligence artificielle et en particulier les reseaux de neurones profonds (Deep Learning) sont en pleine emergence dans le domaine biomedical. Les reseaux de neurones s’inspirent du modele biologique, ils sont interconnectes entre eux et suivent des modeles mathematiques. Lors de l’utilisation des reseaux de neurones artificiels, deux phases sont necessaires : une phase d’apprentissage et une phase d’exploitation. Les deux principales applications sont la classification et la regression. Des outils informatiques comme les processeurs graphiques accelerateurs de calcul ou des bibliotheques de developpement specifiques ont donne un nouveau souffle a ces techniques. …

0301 basic medicine03 medical and health sciences030104 developmental biology0302 clinical medicine[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]030220 oncology & carcinogenesisComputingMilieux_MISCELLANEOUS3. Good healthPathology and Forensic MedicineAnnales de Pathologie
researchProduct

Assessment of tumor-infiltrating TCRV γ 9V δ 2 γδ lymphocyte abundance by deconvolution of human cancers microarrays

2017

Most human blood γδ cells are cytolytic TCRVγ9Vδ2+lymphocytes with antitumor activity. They are currently investigated in several clinical trials of cancer immunotherapy but so far, their tumor infiltration has not been systematically explored across human cancers. Novel algorithms allowing the deconvolution of bulk tumor transcriptomes to find the relative proportions of infiltrating leucocytes, such as CIBERSORT, should be appropriate for this aim but in practice they fail to accurately recognize γδ T lymphocytes. Here, by implementing machine learning from microarray data, we first improved the computational identification of blood-derived TCRVγ9Vδ2+γδ lymphocytes and then appl…

0301 basic medicineAcute promyelocytic leukemia[SDV.MHEP.HEM] Life Sciences [q-bio]/Human health and pathology/Hematologylcsh:Immunologic diseases. AllergyArtificial intelligenceMicroarrayLymphocytemedicine.medical_treatmentImmunologyInflammationchemical and pharmacologic phenomenagamma delta lymphocyteBiologydeconvolutionlcsh:RC254-28203 medical and health sciences0302 clinical medicineCancer immunotherapymedicineImmunology and AllergycancerOriginal ResearchTumor-infiltrating lymphocytesAntigen processingMyeloid leukemiahemic and immune systems[SDV.MHEP.HEM]Life Sciences [q-bio]/Human health and pathology/Hematologydata miningmedicine.diseaselcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogens3. Good health030104 developmental biologymedicine.anatomical_structuremachine learningOncology030220 oncology & carcinogenesisImmunologymedicine.symptomlcsh:RC581-607microarraytranscriptome
researchProduct

Effects of Study Population, Labeling and Training on Glaucoma Detection Using Deep Learning Algorithms

2020

Author(s): Christopher, Mark; Nakahara, Kenichi; Bowd, Christopher; Proudfoot, James A; Belghith, Akram; Goldbaum, Michael H; Rezapour, Jasmin; Weinreb, Robert N; Fazio, Massimo A; Girkin, Christopher A; Liebmann, Jeffrey M; De Moraes, Gustavo; Murata, Hiroshi; Tokumo, Kana; Shibata, Naoto; Fujino, Yuri; Matsuura, Masato; Kiuchi, Yoshiaki; Tanito, Masaki; Asaoka, Ryo; Zangwill, Linda M | Abstract: PurposeTo compare performance of independently developed deep learning algorithms for detecting glaucoma from fundus photographs and to evaluate strategies for incorporating new data into models.MethodsTwo fundus photograph datasets from the Diagnostic Innovations in Glaucoma Study/African Descent…

0301 basic medicineAginggenetic structuresFundus OculiAfrican descentPopulationBiomedical EngineeringGlaucomaPrimary careNeurodegenerativeoptic disc03 medical and health sciences0302 clinical medicineDeep LearningOpthalmology and OptometryArtificial IntelligencemedicineHumanseducationMild diseaseeducation.field_of_studyReceiver operating characteristicbusiness.industrySpecial IssueDeep learningimagingartificial intelligencemedicine.diseaseeye diseasesOphthalmology030104 developmental biologyglaucomamachine learning030221 ophthalmology & optometryPopulation studyArtificial intelligencebusinessPsychologyAlgorithmAlgorithmsTranslational Vision Science & Technology
researchProduct

Risk Assessment of Hip Fracture Based on Machine Learning

2020

[EN] Identifying patients with high risk of hip fracture is a great challenge in osteoporosis clinical assessment. Bone Mineral Density (BMD) measured by Dual-Energy X-Ray Absorptiometry (DXA) is the current gold standard in osteoporosis clinical assessment. However, its classification accuracy is only around 65%. In order to improve this accuracy, this paper proposes the use of Machine Learning (ML) models trained with data from a biomechanical model that simulates a sideways-fall. Machine Learning (ML) models are models able to learn and to make predictions from data. During a training process, ML models learn a function that maps inputs and outputs without previous knowledge of the probl…

0301 basic medicineArticle SubjectProcess (engineering)Computer scienceQH301-705.5INGENIERIA MECANICAmedia_common.quotation_subjectOsteoporosisBiomedical EngineeringMedicine (miscellaneous)030209 endocrinology & metabolismBioengineeringMachine learningcomputer.software_genreRisk AssessmentMachine Learning03 medical and health sciencesHip Fracture0302 clinical medicinemedicine03.- Garantizar una vida saludable y promover el bienestar para todos y todas en todas las edadesSensitivity (control systems)Biology (General)media_commonHip fractureVariablesbusiness.industryGold standard (test)medicine.diseaseRandom forest030104 developmental biologyArtificial intelligenceRisk assessmentbusinessLENGUAJES Y SISTEMAS INFORMATICOScomputerTP248.13-248.65Research ArticleBiotechnologyApplied Bionics and Biomechanics
researchProduct

Deep learning in next-generation sequencing

2020

Highlights • Machine learning increasingly important for NGS. • Deep learning can improve many NGS applications.

0301 basic medicineBiomedical ResearchComputer scienceContext (language use)ComputerApplications_COMPUTERSINOTHERSYSTEMSReviewMachine learningcomputer.software_genre03 medical and health sciences0302 clinical medicineDeep LearningGene to ScreenDrug DiscoveryHumansPharmacologyFeature detection (web development)Network architectureArtificial neural networkbusiness.industryDeep learningHigh-Throughput Nucleotide SequencingMedical research030104 developmental biologyMetagenomics030220 oncology & carcinogenesisUnsupervised learningArtificial intelligenceMetagenomicsNeural Networks ComputerbusinesscomputerDrug Discovery Today
researchProduct

A Pan-Cancer Approach to Predict Responsiveness to Immune Checkpoint Inhibitors by Machine Learning

2019

Immunotherapy by using immune checkpoint inhibitors (ICI) has dramatically improved the treatment options in various cancers, increasing survival rates for treated patients. Nevertheless, there are heterogeneous response rates to ICI among different cancer types, and even in the context of patients affected by a specific cancer. Thus, it becomes crucial to identify factors that predict the response to immunotherapeutic approaches. A comprehensive investigation of the mutational and immunological aspects of the tumor can be useful to obtain a robust prediction. By performing a pan-cancer analysis on gene expression data from the Cancer Genome Atlas (TCGA, 8055 cases and 29 cancer types), we …

0301 basic medicineCancer ResearchImmune checkpoint inhibitorsmedicine.medical_treatmentimmunology-pancancerimmune checkpoint inhibitorContext (language use)Machine learningcomputer.software_genrelcsh:RC254-282Article03 medical and health sciences0302 clinical medicinemedicineExtreme gradient boostingPan cancerbusiness.industryCancerImmunotherapylcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogensMatthews correlation coefficientmedicine.diseaseSupport vector machine030104 developmental biologymachine learningOncology030220 oncology & carcinogenesisArtificial intelligencebusinesscomputerCancers
researchProduct

Molecular pathway activation – New type of biomarkers for tumor morphology and personalized selection of target drugs

2018

Anticancer target drugs (ATDs) specifically bind and inhibit molecular targets that play important roles in cancer development and progression, being deeply implicated in intracellular signaling pathways. To date, hundreds of different ATDs were approved for clinical use in the different countries. Compared to previous chemotherapy treatments, ATDs often demonstrate reduced side effects and increased efficiency, but also have higher costs. However, the efficiency of ATDs for the advanced stage tumors is still insufficient. Different ATDs have different mechanisms of action and are effective in different cohorts of patients. Personalized approaches are therefore needed to select the best ATD…

0301 basic medicineCancer ResearchSystems biologymutation profilingAntineoplastic AgentsComputational biologyProteomics03 medical and health sciencesNeoplasmsmicroRNABiomarkers TumorHumanscancerMedicineMolecular Targeted TherapyEpigeneticsPrecision MedicineBiomedicinebusiness.industryGene Expression ProfilingCancerbioinformaticsmedicine.diseasePrecision medicinesignaling pathwaysGene Expression Regulation NeoplasticGene expression profilingmachine learning030104 developmental biologyCommentarybusinessSignal TransductionSeminars in Cancer Biology
researchProduct

Disease–Genes Must Guide Data Source Integration in the Gene Prioritization Process

2019

One of the main issues in detecting the genes involved in the etiology of genetic human diseases is the integration of different types of available functional relationships between genes. Numerous approaches exploited the complementary evidence coded in heterogeneous sources of data to prioritize disease-genes, such as functional profiles or expression quantitative trait loci, but none of them to our knowledge posed the scarcity of known disease-genes as a feature of their integration methodology. Nevertheless, in contexts where data are unbalanced, that is, where one class is largely under-represented, imbalance-unaware approaches may suffer a strong decrease in performance. We claim that …

0301 basic medicineClass (computer programming)Boosting (machine learning)Computer scienceProcess (engineering)media_common.quotation_subjectComputational biologyScarcity03 medical and health sciencesComputingMethodologies_PATTERNRECOGNITION030104 developmental biologyExpression quantitative trait lociKey (cryptography)Feature (machine learning)Gene prioritizationmedia_common
researchProduct

Application of Graph Clustering and Visualisation Methods to Analysis of Biomolecular Data

2018

In this paper we present an approach based on integrated use of graph clustering and visualisation methods for semi-supervised discovery of biologically significant features in biomolecular data sets. We describe several clustering algorithms that have been custom designed for analysis of biomolecular data and feature an iterated two step approach involving initial computation of thresholds and other parameters used in clustering algorithms, which is followed by identification of connected graph components, and, if needed, by adjustment of clustering parameters for processing of individual subgraphs.

0301 basic medicineComputer scienceComputationcomputer.software_genreVisualization03 medical and health sciencesIdentification (information)ComputingMethodologies_PATTERNRECOGNITION030104 developmental biology0302 clinical medicineGraph drawingFeature (machine learning)Data miningCluster analysiscomputer030217 neurology & neurosurgeryConnectivityClustering coefficient
researchProduct