2024
Diagnostic performance of neural network algorithms in skull fracture detection on CT scans: a systematic review and meta-analysis
Sharifi G, Hajibeygi R, Zamani S, Easa A, Bahrami A, Eshraghi R, Moafi M, Ebrahimi M, Fathi M, Mirjafari A, Chan J, Dixe de Oliveira Santo I, Anar M, Rezaei O, Tu L. Diagnostic performance of neural network algorithms in skull fracture detection on CT scans: a systematic review and meta-analysis. Emergency Radiology 2024, 32: 97-111. PMID: 39680295, DOI: 10.1007/s10140-024-02300-7.Peer-Reviewed Original ResearchConceptsConvolutional neural networkArea under the receiver operating characteristic curveConvolutional neural network modelCT scanSkull fractureComputed tomographyDeep learningProspective clinical trialMeta-analysisReceiver operating characteristic curvePublication biasSkull fracture detectionSystematic reviewNeural network algorithmDetecting skull fracturesImprove diagnosis accuracyDiagnostic hurdlesShortage of radiologistsAutomated diagnostic toolTransfer learningDiagnostic performanceDiagnostic accuracyClinical trialsModel architectureNeural networkUsing clinical entity recognition for curating an interface terminology to aid fast skimming of EHRs
Kollapally N, Dehkordi M, Perl Y, Geller J, Deek F, Liu H, Keloth V, Elhanan G, Einstein A, Zhou S. Using clinical entity recognition for curating an interface terminology to aid fast skimming of EHRs. 2024, 00: 6427-6434. DOI: 10.1109/bibm62325.2024.10822845.Peer-Reviewed Original ResearchElectronic health recordsEntity recognitionVolume of electronic health recordsEHR interoperabilityClinical entity recognitionClinical terminologyNeural network modelClinical NERTransfer learningSNOMED CT conceptsInterface terminologyNetwork modelSNOMED CTHealth recordsHigher granularityCT conceptsOverworked physiciansHealthcare providersDense volumeRecognitionInteroperabilityCurationGranularityCardiology patientsNERTensor dictionary-based heterogeneous transfer learning to study emotion-related gender differences in brain
Yang L, Qiao C, Kanamori T, Calhoun V, Stephen J, Wilson T, Wang Y. Tensor dictionary-based heterogeneous transfer learning to study emotion-related gender differences in brain. Neural Networks 2024, 183: 106974. PMID: 39657530, DOI: 10.1016/j.neunet.2024.106974.Peer-Reviewed Original ResearchFeature spaceClassification performanceHeterogeneous transfer learningTensor dictionary learningHeterogeneous knowledge sharingTransfer learning frameworkReduce training costsDictionary learningKnowledge sharing strategyHeterogeneous transferGender classificationTransfer learningLearning frameworkConnectivity dataHeterogeneous dataHeterogeneous knowledgeBrain activity dataPriori knowledgeTraining costsSharing strategyProblem of insufficient sample sizeKnowledge sharingEEG dataExperimental resultsDictionaryAugmenting biomedical named entity recognition with general-domain resources
Yin Y, Kim H, Xiao X, Wei C, Kang J, Lu Z, Xu H, Fang M, Chen Q. Augmenting biomedical named entity recognition with general-domain resources. Journal Of Biomedical Informatics 2024, 159: 104731. PMID: 39368529, DOI: 10.1016/j.jbi.2024.104731.Peer-Reviewed Original ResearchBioNER datasetsMulti-task learningNER datasetsEntity typesBiomedical datasetsBaseline modelGeneral domain datasetsBiomedical language modelNeural network-basedYield performance improvementsBioNER modelsEntity recognitionBiomedical corporaHuman annotatorsLabel ambiguityLanguage modelTransfer learningF1 scoreBioNERHuman effortNetwork-basedBiomedical resourcesPerformance improvementDatasetSuperior performanceEfficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning
Holste G, Oikonomou E, Mortazavi B, Wang Z, Khera R. Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning. Communications Medicine 2024, 4: 133. PMID: 38971887, PMCID: PMC11227494, DOI: 10.1038/s43856-024-00538-3.Peer-Reviewed Original ResearchSelf-supervised learningTransfer learningTraining dataEchocardiogram videosPortion of labelled dataStandard transfer learning approachContrastive self-supervised learningSelf-supervised learning approachLearning approachImage recognition tasksState-of-the-artContrastive learning approachFine-tuningTransfer learning approachMedical image diagnosisCardiac disease diagnosisContrastive learningVideo framesLabeled datasetLabeled dataExpert labelsClassification performanceMedical imagesRecognition taskVideoCross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis
Ellis C, Miller R, Calhoun V. Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis. 2024, 00: 1-5. DOI: 10.1109/isbi56570.2024.10635743.Peer-Reviewed Original ResearchTransfer learningDeep learning classifier’s performanceEarly convolutional layersConvolutional neural networkDeep learning modelsDeep learning studiesConvolutional layersClassifier performanceDiagnosis tasksExplainability analysisNeural networkSleep datasetsRaw electroencephalographyLearning modelsIncreased robustnessDatasetChannel lossSampling rateModel accuracyMDD modelLearningRepresentationTaskLearning studiesElectroencephalographyDeveloping deep learning-based strategies to predict the risk of hepatocellular carcinoma among patients with nonalcoholic fatty liver disease from electronic health records
Li Z, Lan L, Zhou Y, Li R, Chavin K, Xu H, Li L, Shih D, Zheng W. Developing deep learning-based strategies to predict the risk of hepatocellular carcinoma among patients with nonalcoholic fatty liver disease from electronic health records. Journal Of Biomedical Informatics 2024, 152: 104626. PMID: 38521180, DOI: 10.1016/j.jbi.2024.104626.Peer-Reviewed Original ResearchDeep learning modelsElectronic health recordsHCC risk predictionHealth recordsTime-varying covariatesLearning modelsElectronic health record dataRisk predictionHealth record dataAccuracy of deep learning modelsDeep learning-based strategyCovariate imbalanceDisease prediction tasksLearning-based strategyDeep learning performanceDisease risk predictionEHR databaseClassification problemLength of follow-upTransfer learningFatty liver diseasePrediction taskCarcinoma riskModel trainingRecord data
2023
Using annotation for computerized support for fast skimming of cardiology electronic health record notes
Dehkordi M, Einstein A, Zhou S, Elhanan G, Perl Y, Keloth V, Geller J, Liu H. Using annotation for computerized support for fast skimming of cardiology electronic health record notes. 2023, 00: 4043-4050. DOI: 10.1109/bibm58861.2023.10385289.Peer-Reviewed Original ResearchElectronic health recordsElectronic health record notesNamed Entity RecognitionTraining dataMining conceptsInterface terminologyMachine learningSNOMED CTEntity recognitionHealth recordsHealthcare professionalsTransfer learningPatient careCurrent healthcareMining techniquesMining phrasesArt techniquesRecord notesSNOMED conceptsMedical specialtiesComputer-SupportedMedical professionalsReference terminologyCritical informationAnnotationImproving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder via Transfer Learning with Single Channel Sleep Stage Data*
Ellis C, Sattiraju A, Miller R, Calhoun V. Improving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder via Transfer Learning with Single Channel Sleep Stage Data*. 2023, 00: 2466-2473. DOI: 10.1109/bibm58861.2023.10385424.Peer-Reviewed Original ResearchDeep learning methodsLearning methodsTransfer learningEEG datasetManually engineered featuresTransfer learning approachDeep learning modelsDeep learning performanceMachine learning methodsClassification datasetsLearned representationsElectroencephalography classifierDeep learningEEG classificationResting-state electroencephalographyDiagnosis of major depressive disorderRaw electroencephalographyLearning approachLearning modelsMajor depressive disorder diagnosisMajor depressive disorderLearning performanceClassifierDatasetEngineering featuresBioREx: Improving biomedical relation extraction by leveraging heterogeneous datasets
Lai P, Wei C, Luo L, Chen Q, Lu Z. BioREx: Improving biomedical relation extraction by leveraging heterogeneous datasets. Journal Of Biomedical Informatics 2023, 146: 104487. PMID: 37673376, DOI: 10.1016/j.jbi.2023.104487.Peer-Reviewed Original ResearchBiomedical relation extractionRelation extractionRE tasksNatural language processing researchData-centric approachKnowledge graph constructionMulti-task learningLanguage processing researchIndividual datasetsLiterature-based discoveryChemical-induced disease relationsDataset annotationDomain knowledgeTransfer learningTraining dataHeterogeneous datasetsArt methodsNovel frameworkGraph constructionFree textData heterogeneityLarge datasetsBiomedical conceptsProcessing researchDatasetMorphological Parameters and Associated Uncertainties for 8 Million Galaxies in the Hyper Suprime-Cam Wide Survey
Ghosh A, Urry C, Mishra A, Perreault-Levasseur L, Natarajan P, Sanders D, Nagai D, Tian C, Cappelluti N, Kartaltepe J, Powell M, Rau A, Treister E. Morphological Parameters and Associated Uncertainties for 8 Million Galaxies in the Hyper Suprime-Cam Wide Survey. The Astrophysical Journal 2023, 953: 134. DOI: 10.3847/1538-4357/acd546.Peer-Reviewed Original ResearchSource codeMachine-learning algorithmsMachine-learning frameworkData setsTransfer learningEstimation networkPrevious stateProfile fitting algorithmReal dataNancy Grace Roman Space TelescopeRoman Space TelescopeLarge imaging surveysAlgorithmFitting algorithmUncertainty quantificationSimulations of galaxiesBayesian posteriorPosterior distributionExternal cataloguesFirst trainingSpace TelescopeGalaxy bulgesLight ratioSignificant improvementGalaxiesDeep Generative Transfer Learning Predicts Conversion To Alzheimer’S Disease From Neuroimaging Genomics Data
Dolci G, Rahaman M, Galazzo I, Cruciani F, Abrol A, Chen J, Fu Z, Duan K, Menegaz G, Calhoun V. Deep Generative Transfer Learning Predicts Conversion To Alzheimer’S Disease From Neuroimaging Genomics Data. 2023, 00: 1-5. DOI: 10.1109/icasspw59220.2023.10193683.Peer-Reviewed Original Research
2022
Class-Aware Adversarial Transformers for Medical Image Segmentation.
You C, Zhao R, Liu F, Dong S, Chinchali S, Topcu U, Staib L, Duncan J. Class-Aware Adversarial Transformers for Medical Image Segmentation. Advances In Neural Information Processing Systems 2022, 35: 29582-29596. PMID: 37533756, PMCID: PMC10395073.Peer-Reviewed Original ResearchMedical image segmentationImage segmentationMedical image analysis domainMedical image analysis tasksImage analysis domainMedical image datasetsImage analysis tasksModel’s inner workingsTransformer-based approachTransformer-based modelsAdversarial training strategyRich semantic contextSegmentation label mapsLong-range dependenciesMulti-scale representationAnalysis tasksImage datasetsTransfer learningFeature representationInner workingsSegmentation accuracyCorrelated contentTransformer moduleLabel mapsInformation lossTracing and Forecasting Metabolic Indices of Cancer Patients Using Patient-Specific Deep Learning Models
Hou J, Deng J, Li C, Wang Q. Tracing and Forecasting Metabolic Indices of Cancer Patients Using Patient-Specific Deep Learning Models. Journal Of Personalized Medicine 2022, 12: 742. PMID: 35629164, PMCID: PMC9147215, DOI: 10.3390/jpm12050742.Peer-Reviewed Original ResearchShort-term memory recurrent neural networkLong short-term memory recurrent neural networkTransfer learningRecurrent neural networkDeep learning modelsReduced training timeNeural networkLearning modelTraining timeDynamical system modelLearningShort-term predictionNormsMore cancer patientsComparable levelsPhysiological modelPatient-specific modelsscJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning
Lin Y, Wu T, Wan S, Yang J, Wong W, Wang Y. scJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning. Nature Biotechnology 2022, 40: 703-710. PMID: 35058621, PMCID: PMC9186323, DOI: 10.1038/s41587-021-01161-6.Peer-Reviewed Original ResearchConceptsData modalitiesTransfer learning methodDifferent data modalitiesSingle-cell multiomics dataTransfer learningUnlabeled dataMultimodal datasetLeverage informationNeural networkLearning methodsData compositionLabel transferLabel accuracyJoint visualizationHeterogeneous collectionPromising resultsUnprecedented paceVisualizationFrameworkMultiomics dataScRNA-seq dataDatasetNetworkScATAC-seq dataCell atlases
2021
Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients
Deng Y, Lu L, Aponte L, Angelidi A, Novak V, Karniadakis G, Mantzoros C. Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients. Npj Digital Medicine 2021, 4: 109. PMID: 34262114, PMCID: PMC8280162, DOI: 10.1038/s41746-021-00480-x.Peer-Reviewed Original ResearchData augmentationTransfer learningNetwork architectureData augmentation techniquesNeural network architectureTransfer-learning strategyDeep-learning methodsDeep learning modelsDeep transfer learningTransfer-learning methodsSame network architectureDifferent loss functionsFuture glucose levelsAccurate predictive modelsH prediction horizonPublic datasetsGenerative modelGlucose level predictionAugmentation techniquesLoss functionPrediction accuracyDatasetLevel predictionPrediction horizonArchitectureTITAN: T-cell receptor specificity prediction with bimodal attention networks
Weber A, Born J, Martínez M. TITAN: T-cell receptor specificity prediction with bimodal attention networks. Bioinformatics 2021, 37: i237-i244. PMID: 34252922, PMCID: PMC8275323, DOI: 10.1093/bioinformatics/btab294.Peer-Reviewed Original ResearchConceptsK-nearest neighborAttention networkLeverage transfer learningState-of-the-artK-nearest-neighbor (KNN) classifierInput data spaceK-NN classifierBimodal neural networkSMILES sequencesTransfer learningData augmentationAttention heatmapsCompetitive performanceNeural networkData spaceT cell receptorBoost performanceT-cell receptor sequencingClassifierNetworkImproved performanceT cellsPrediction of specificityPerformanceSequencing of T-cell receptorOn the feasibility of deep learning applications using raw mass spectrometry data
Cadow J, Manica M, Mathis R, Reddel R, Robinson P, Wild P, Hains P, Lucas N, Zhong Q, Guo T, Aebersold R, Martínez M. On the feasibility of deep learning applications using raw mass spectrometry data. Bioinformatics 2021, 37: i245-i253. PMID: 34252933, PMCID: PMC8275322, DOI: 10.1093/bioinformatics/btab311.Peer-Reviewed Original ResearchConceptsRaw mass spectrometry dataDeep learning modelsRaw MS dataMass spectrometry dataClassification performanceDeep learningMS dataMass spectrometryLearning modelsSpectrometry dataApplication of deep learningMS imagesNatural image classificationDeep learning applicationsPrivacy of individualsTransfer learning techniqueData-independent-acquisitionMS2 spectraClassification taskData processing pipelinesClassification labelsImage classificationFeature vectorTransfer learningSample sparsity
2019
Transfer Learning for a Multimodal Hybrid EEG-fTCD Brain–Computer Interface
Dagois E, Khalaf A, Sejdic E, Akcakaya M. Transfer Learning for a Multimodal Hybrid EEG-fTCD Brain–Computer Interface. IEEE Sensors Letters 2019, 3: 1-4. DOI: 10.1109/lsens.2018.2879466.Peer-Reviewed Original ResearchFunctional transcranial Doppler ultrasoundTransfer learningClass-conditional distributionsQuadratic discriminant analysisLinear discriminant analysisCalibration sessionHybrid BCIConditional probabilistic distributionsBetter classification performanceElectrical brain activityBrain-computer interface (BCI) researchMotor imagery tasksTraining dataDifferent classifiersClassification performanceProbabilistic similarityVector machineImagery tasksComputer interfaceBrain activityControl accessDimensionality reductionFinal classificationBCI systemSpecific tasks
2014
A Transfer-Learning Approach to Exploit Noisy Information for Classification and Its Application on Sentiment Detection
Lin W, Kuo T, Huang Y, Lu W, Lin S. A Transfer-Learning Approach to Exploit Noisy Information for Classification and Its Application on Sentiment Detection. Lecture Notes In Computer Science 2014, 8916: 262-273. DOI: 10.1007/978-3-319-13987-6_25.Peer-Reviewed Original Research
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply