2025
Improving the Robustness of Deep-Learning Models in Predicting Hematoma Expansion from Admission Head CT.
Tran A, Karam G, Zeevi D, Qureshi A, Malhotra A, Majidi S, Murthy S, Park S, Kontos D, Falcone G, Sheth K, Payabvash S. Improving the Robustness of Deep-Learning Models in Predicting Hematoma Expansion from Admission Head CT. American Journal Of Neuroradiology 2025, ajnr.a8650. PMID: 39794133, DOI: 10.3174/ajnr.a8650.Peer-Reviewed Original ResearchFast Gradient Sign MethodDeep learning modelsRobustness of deep learning modelsAdversarial attacksAdversarial imagesAdversarial trainingSign MethodModel robustnessDeploying deep learning modelsDeep learning model performanceConvolutional neural networkImprove model robustnessAcute intracerebral hemorrhageHematoma expansionMulti-threshold segmentationReceiver operating characteristicIntracerebral hemorrhageGradient descentType attacksData perturbationNeural networkProjected GradientTraining setAntihypertensive Treatment of Acute Cerebral HemorrhageThreshold-based segmentation
2024
A Case Demonstration of the Open Health Natural Language Processing Toolkit From the National COVID-19 Cohort Collaborative and the Researching COVID to Enhance Recovery Programs for a Natural Language Processing System for COVID-19 or Postacute Sequelae of SARS CoV-2 Infection: Algorithm Development and Validation
Wen A, Wang L, He H, Fu S, Liu S, Hanauer D, Harris D, Kavuluru R, Zhang R, Natarajan K, Pavinkurve N, Hajagos J, Rajupet S, Lingam V, Saltz M, Elowsky C, Moffitt R, Koraishy F, Palchuk M, Donovan J, Lingrey L, Stone-DerHagopian G, Miller R, Williams A, Leese P, Kovach P, Pfaff E, Zemmel M, Pates R, Guthe N, Haendel M, Chute C, Liu H, Collaborative C, Initiative T. A Case Demonstration of the Open Health Natural Language Processing Toolkit From the National COVID-19 Cohort Collaborative and the Researching COVID to Enhance Recovery Programs for a Natural Language Processing System for COVID-19 or Postacute Sequelae of SARS CoV-2 Infection: Algorithm Development and Validation. JMIR Medical Informatics 2024, 12: e49997. PMID: 39250782, PMCID: PMC11420592, DOI: 10.2196/49997.Peer-Reviewed Original ResearchNatural language processingNatural language processing algorithmsNatural language processing toolkitNatural language processing systemsProcessing toolkitNatural language processing tasksUnified Medical Language SystemClinical natural language processingAlgorithm developmentMedical Language SystemLanguage processing systemDevelopment approachNLP tasksTime-critical natureHuman expertsNatural language processing resultsExpert annotationsLanguage processingTraining setClinical narrativesNatural language processing extractsTest setAlgorithmPostacute sequelae of SARS-CoV-2 infectionProcessing systemEvaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data*
Ellis C, Miller R, Calhoun V. Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data*. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-5. PMID: 40039441, DOI: 10.1109/embc53108.2024.10782103.Peer-Reviewed Original ResearchConceptsAugmented training setData augmentationTraining setDA methodsDeep learning methodsDA approachNeuropsychiatric disorder diagnosisModel performanceTraining dataDeep learningEEG datasetDataset sizeLearning methodsAugmentation approachImprove model performanceDepressive disorder diagnosisDA efficacyDatasetDisorder diagnosisCompare performanceMajor depressive disorder diagnosisPerformanceBaseline setDeepChannelSpeech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI
Liu X, Xing F, Zhuo J, Stone M, Prince J, El Fakhri G, Woo J. Speech motion anomaly detection via cross-modal translation of 4D motion fields from tagged MRI. Proceedings Of SPIE--the International Society For Optical Engineering 2024, 12926: 129262w-129262w-5. PMID: 39238547, PMCID: PMC11377028, DOI: 10.1117/12.3006874.Peer-Reviewed Original ResearchCross-modal translationHealthy individualsTongue cancer patientsMotion fieldOut-of-distributionOne-class SVMPatient dataAnomaly detectionAnomaly detectorCancer patientsTagged MRISpeech-related disordersGeneralization capabilityReconstruction qualitySpeech qualityArticulatory-acoustic relationsPatientsSpeech waveformTraining setInnovative treatmentsMRITest setMotion patternsArticulatory featuresTraining translators
2023
QUOTAS: A New Research Platform for the Data-driven Discovery of Black Holes
Natarajan P, Tang K, McGibbon R, Khochfar S, Nord B, Sigurdsson S, Tricot J, Cappelluti N, George D, Hidary J. QUOTAS: A New Research Platform for the Data-driven Discovery of Black Holes. The Astrophysical Journal 2023, 952: 146. DOI: 10.3847/1538-4357/acd9ce.Peer-Reviewed Original ResearchMachine-learning algorithmsSloan Digital Sky Survey (SDSS) quasarsResearch platformLarge data setsBlack hole populationKaggle platformComputational environmentQuasar populationBaryonic physicsOccupation statisticsBlack holesTraining setNovel research platformNew research platformCosmic epochsHalo populationData-driven investigationHole populationHost galaxiesHalo propertiesData setsSimulation volumeFirst science resultsQuasarsPlatformA pipeline for the retrieval and extraction of domain-specific information with application to COVID-19 immune signatures
Newton A, Chartash D, Kleinstein S, McDougal R. A pipeline for the retrieval and extraction of domain-specific information with application to COVID-19 immune signatures. BMC Bioinformatics 2023, 24: 292. PMID: 37474900, PMCID: PMC10357743, DOI: 10.1186/s12859-023-05397-8.Peer-Reviewed Original ResearchConceptsDomain-specific informationDocument embeddingsSVM classifierSemi-structured representationsTraining setWeb-based formKnowledge repositoryInformation modelAutomatic analysisClassifier predictionsClassifierSignature informationAutomated systemBiomedical publicationsPaper authorsEmbeddingIncomplete information modelLiterature miningIterative processSpecific informationSuch informationInformationLimited setSetQueriesDeep neuroevolution to predict astrocytoma grade from functional brain networks
Stember J, Jenabi M, Pasquini L, Peck K, Holodny A, Shalu H. Deep neuroevolution to predict astrocytoma grade from functional brain networks. 2023, 00: 1-6. DOI: 10.1109/imip57114.2023.00008.Peer-Reviewed Original ResearchConvolutional neural networkDeep neuroevolutionArtificial intelligenceAccurate convolutional neural networkAdjacency matrixNoisy training setSaliency mapNeural networkBrain tumor typesFunctional MRITraining setData typesMedical dataNeuroevolutionNetworkInformation-richNuanced tasksComplex featuresAdjacencyFunctional brain networksTrained radiologistsBrain networksFunctional connectivityNeural activityAnatomical MRI
2022
Development and Validation of a Model to Identify Critical Brain Injuries Using Natural Language Processing of Text Computed Tomography Reports
Torres-Lopez VM, Rovenolt GE, Olcese AJ, Garcia GE, Chacko SM, Robinson A, Gaiser E, Acosta J, Herman AL, Kuohn LR, Leary M, Soto AL, Zhang Q, Fatima S, Falcone GJ, Payabvash MS, Sharma R, Struck AF, Sheth KN, Westover MB, Kim JA. Development and Validation of a Model to Identify Critical Brain Injuries Using Natural Language Processing of Text Computed Tomography Reports. JAMA Network Open 2022, 5: e2227109. PMID: 35972739, PMCID: PMC9382443, DOI: 10.1001/jamanetworkopen.2022.27109.Peer-Reviewed Original ResearchConceptsNatural language processingF-scoreTest data setsLanguage processingIndependent test data setsData setsBidirectional Encoder RepresentationsAcute brain injuryLarge data setsHead CTBrain injuryNLP toolsF1 scoreNER modelTransformer architectureClinical textEncoder RepresentationsNLP algorithmNLP modelsCT reportsCustom dictionaryTraining setCross-validation performancePerformance metricsAvailable new tools
2021
Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study
Chen Q, Rankine A, Peng Y, Aghaarabi E, Lu Z. Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study. JMIR Medical Informatics 2021, 9: e27386. PMID: 34967748, PMCID: PMC8759018, DOI: 10.2196/27386.Peer-Reviewed Original ResearchSemantic textual similarityConvolutional neural networkDeep learning modelsReal-time applicationsDL modelsSentence pairsNeural networkTextual similarityBERT modelNational Natural Language Processing Clinical ChallengesLearning modelNatural language processingAverage Pearson correlationData setsDifferent similarity levelsInference timeGeneralization capabilityManual annotationLanguage processingPearson correlationEnsemble modelWord orderTime efficiencyNegation termsTraining setFixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators
Tong A, Wolf G, Krishnaswamy S. Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators. Journal Of Signal Processing Systems 2021, 94: 229-243. DOI: 10.1007/s11265-021-01715-6.Peer-Reviewed Original ResearchAnomaly detectionTraining dataReconstruction-based anomaly detectionAutoencoder reconstruction errorDeep learning methodsReconstruction-based methodsOriginal data spaceGraph dataLearning methodsData spaceUnseen anomaliesReconstruction errorImproved performanceIrregular graphsTraining setHealth recordsHealth record dataWasserstein distanceLow errorDiscriminatorImagesCIFAR10MNISTUndesirable resultsRecord data
2019
An open source automated tumor infiltrating lymphocyte algorithm for prognosis in melanoma
Acs B, Ahmed FS, Gupta S, Wong P, Gartrell RD, Sarin Pradhan J, Rizk EM, Gould Rothberg BE, Saenger YM, Rimm DL. An open source automated tumor infiltrating lymphocyte algorithm for prognosis in melanoma. Nature Communications 2019, 10: 5440. PMID: 31784511, PMCID: PMC6884485, DOI: 10.1038/s41467-019-13043-2.Peer-Reviewed Original ResearchConceptsOpen sourceOpen source softwareSource softwareTIL scoreTraining setDisease-specific overall survivalHigh TIL scorePoor prognosis cohortsSubset of patientsAlgorithmIndependent prognostic markerBroad adoptionAssessment of tumorOverall survivalFavorable prognosisMelanoma patientsMultivariable analysisValidation cohortIndependent associationPrognostic markerSeparate patientsPrognostic variablesIndependent cohortRetrospective collectionMelanoma
2018
Preference-Based Assistance Prediction for Human-Robot Collaboration Tasks
Grigore E, Roncone A, Mangin O, Scassellati B. Preference-Based Assistance Prediction for Human-Robot Collaboration Tasks. 2018, 00: 4441-4448. DOI: 10.1109/iros.2018.8593716.Peer-Reviewed Original ResearchHuman-robot collaborationHuman workersHuman-RobotHuman peersHuman-robot collaborative tasksHidden state representationsUser studyTraining dataCollaborative tasksAction partsTraining setRobotReal world observationsAssisted predictionState representationTaskWorld observationsBehavioral modelPhysical tasksUsersHMMTrainingBehavioral preferencesRepresentationAssistanceResidual Convolutional Neural Network for Determination of IDH Status in Low- and High-grade Gliomas from MR Imaging
Chang K, Bai HX, Zhou H, Su C, Bi WL, Agbodza E, Kavouridis VK, Senders JT, Boaro A, Beers A, Zhang B, Capellini A, Liao W, Shen Q, Li X, Xiao B, Cryan J, Ramkissoon S, Ramkissoon L, Ligon K, Wen PY, Bindra RS, Woo J, Arnaout O, Gerstner ER, Zhang PJ, Rosen BR, Yang L, Huang RY, Kalpathy-Cramer J. Residual Convolutional Neural Network for Determination of IDH Status in Low- and High-grade Gliomas from MR Imaging. Clinical Cancer Research 2018, 24: clincanres.2236.2017. PMID: 29167275, PMCID: PMC6051535, DOI: 10.1158/1078-0432.ccr-17-2236.Peer-Reviewed Original ResearchMeSH KeywordsAdultAgedAged, 80 and overBrainBrain NeoplasmsDatasets as TopicFemaleGliomaHumansImage Processing, Computer-AssistedIsocitrate DehydrogenaseMagnetic Resonance ImagingMaleMiddle AgedMutationNeoplasm GradingNeural Networks, ComputerPredictive Value of TestsPreoperative PeriodRetrospective StudiesYoung AdultConceptsResidual convolutional neural networkConvolutional neural networkNeural networkDeep learning techniquesTesting setNeural network modelMulti-institutional data setCancer Imaging ArchiveLearning techniquesTesting accuracyNetwork modelTraining setPrediction accuracyPreoperative radiographic dataClin Cancer ResData setsConventional MR imagingHospital of UniversityIsocitrate dehydrogenase (IDH) mutationPreoperative imagingLonger survivalWomen's HospitalGrade IINetworkTreatment decisions
2011
Detecting abbreviations in discharge summaries using machine learning methods.
Wu Y, Rosenbloom S, Denny J, Miller R, Mani S, Giuse D, Xu H. Detecting abbreviations in discharge summaries using machine learning methods. AMIA Annual Symposium Proceedings 2011, 2011: 1541-9. PMID: 22195219, PMCID: PMC3243185.Peer-Reviewed Original ResearchConceptsNatural language processingMachine learning methodsHighest F-measureF-measureClinical natural language processingLexical resourcesClinical abbreviationsTraining setPre-defined featuresRandom forest classifierDomain expertsML algorithmsML classifiersLanguage processingVoting schemeLearning methodsDischarge summariesForest classifierTest setClassifierCorpus-based methodSetResourcesAlgorithmAbbreviations
2007
Fine‐needle aspiration of follicular adenoma versus parathyroid adenoma
Mansoor I, Zalles C, Zahid F, Gossage K, Levenson RM, Rimm DL. Fine‐needle aspiration of follicular adenoma versus parathyroid adenoma. Cancer 2007, 114: 22-26. PMID: 18085636, DOI: 10.1002/cncr.23252.Peer-Reviewed Original ResearchConceptsArtificial intelligence systemsSpatial-spectral featuresSpectral image informationMultispectral image analysisIntelligence systemsImage informationAlgorithmic solutionTraining setImage stacksImaging solutionImage analysisTest casesHuman eyeImagesClassifierSoftwareToolPlatformSolutionTechnologyInformationSet
2004
Reaching through Learned Forward Model
Sun G, Scassellati B. Reaching through Learned Forward Model. 2004, 1: 93-112. DOI: 10.1109/ichr.2004.1442117.Peer-Reviewed Original Research
2002
Prior Shape Models for Boundary Finding
Staib L. Prior Shape Models for Boundary Finding. 2002, 30-33. DOI: 10.1109/isbi.2002.1029185.Peer-Reviewed Original ResearchBoundary findingTraining setAvailable training setPrior shape informationPrior informationPrior shape modelImage informationPrior shapeShape informationTarget objectBayesian formulationShape modelStatistical variationSmoothness constraintShape parametersNatural approachPosterior probabilityGeneric informationInformationObjectsAdditional flexibilitySetKey componentImagesSimilar shape
2001
Use of General-purpose Negation Detection to Augment Concept Indexing of Medical Documents
Mutalik P, Deshpande A, Nadkarni P. Use of General-purpose Negation Detection to Augment Concept Indexing of Medical Documents. Journal Of The American Medical Informatics Association 2001, 8: 598-609. PMID: 11687566, PMCID: PMC130070, DOI: 10.1136/jamia.2001.0080598.Peer-Reviewed Original ResearchConceptsNegation detectionMedical documentsUMLS conceptsProgramming language compilersFinite state machinesLanguage compilerConcept indexingMedical narrativesContext-free grammarsConcept matchingLexical scannerAbsence of negationDifferent test setsFormal languageState machinesRegular expressionsReliability of detectionDiverse training setConcept IDsTraining setParserHuman observationTest setLarge setHuman observers
1998
Improving machine learning performance by removing redundant cases in medical data sets.
Ohno-Machado L, Fraser H, Ohrn A. Improving machine learning performance by removing redundant cases in medical data sets. AMIA Annual Symposium Proceedings 1998, 523-7. PMID: 9929274, PMCID: PMC2232167.Peer-Reviewed Original Research
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply