2025
AI in Action: A Roadmap from the Radiology AI Council for Effective Model Evaluation and Deployment
Trivedi H, Khosravi B, Gichoya J, Benson L, Dyckman D, Galt J, Howard B, Kikano E, Kunjummen J, Lall N, Li X, Patel S, Safdar N, Salastekar N, Segovis C, van Assen M, Harri P. AI in Action: A Roadmap from the Radiology AI Council for Effective Model Evaluation and Deployment. Journal Of The American College Of Radiology 2025 PMID: 40414408, DOI: 10.1016/j.jacr.2025.05.016.Peer-Reviewed Original ResearchAI modelsArtificial intelligenceIntegration of artificial intelligenceWorkflow implementationRadiology workflowPerformance metricsModel evaluationDevelopment of frameworksResource allocationDeploymentClinical workflowWorkflowStandard processModel performanceReturn on investmentPerformanceIntelligenceEvaluationMetricsComprehensive rubricAllocationModelCross-Institutional Evaluation of Large Language Models for Radiology Diagnosis Extraction: A Prompt-Engineering Perspective
Moassefi M, Houshmand S, Faghani S, Chang P, Sun S, Khosravi B, Triphati A, Rasool G, Bhatia N, Folio L, Andriole K, Gichoya J, Erickson B. Cross-Institutional Evaluation of Large Language Models for Radiology Diagnosis Extraction: A Prompt-Engineering Perspective. Journal Of Imaging Informatics In Medicine 2025, 1-6. PMID: 40341981, DOI: 10.1007/s10278-025-01523-5.Peer-Reviewed Original ResearchArtificial Intelligence in the Management of Heart Failure
Cheema B, Hourmozdi J, Kline A, Ahmad F, Khera R. Artificial Intelligence in the Management of Heart Failure. Journal Of Cardiac Failure 2025 PMID: 40345521, DOI: 10.1016/j.cardfail.2025.02.020.Peer-Reviewed Original ResearchArtificial intelligenceState-of-the-art algorithmsData privacy concernsState-of-the-artManagement of heart failureAI-based toolsElectronic health recordsAI solutionsMultimodal dataHeart failureHealth recordsIntegration challengesHeart failure syndromeStructural heart diseaseHeart failure treatmentIntelligenceImplementation challengesModel performanceModel governanceAdvanced diseaseFailure syndromeCardiomyopathy diagnosisFailure treatmentRisk factorsHeart diseaseUltrasound Image Synthesis Using Generative AI for Lung Consolidation Detection
Chou Y, Li G, Chen L, Zahiri M, Balaraju N, Patil S, Hicks B, Schnittke N, Parker M, Kessler D, Shupp J, Baloescu C, Moore C, Gregory C, Gregory K, Raju B, Kruecker J, Chen A. Ultrasound Image Synthesis Using Generative AI for Lung Consolidation Detection. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10980728.Peer-Reviewed Original ResearchSRE-CONV: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification
Du Y, Zhang J, Zeevi T, Dvornek N, Onofrey J. SRE-CONV: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10981270.Peer-Reviewed Original ResearchConvolutional neural networkConvolutional neural network backboneComputer vision tasksBiomedical image classificationRotation-invariant featuresReduced memory footprintVision tasksEquivariant convolutionImage classificationIncreased training costsMemory footprintRotation-equivariantData augmentationNeural networkModel sizeTraining costsTest datasetInfor-mationPerformance accuracyParam-etersBiomedical imagingDatasetIncor-poratedEquivarianceModel performanceA foundation model for generalizable cancer diagnosis and survival prediction from histopathological images
Yang Z, Wei T, Liang Y, Yuan X, Gao R, Xia Y, Zhou J, Zhang Y, Yu Z. A foundation model for generalizable cancer diagnosis and survival prediction from histopathological images. Nature Communications 2025, 16: 2366. PMID: 40064883, PMCID: PMC11894166, DOI: 10.1038/s41467-025-57587-y.Peer-Reviewed Original ResearchConceptsWhole slide imagesLeveraging self-supervised learningScarcity of annotated dataHistopathological imagesSelf-supervised learningPre-training approachSelf-supervised modelPre-trained modelsApplication of artificial intelligenceSmall-scale dataIntelligent healthcareEnhance model performanceExpert annotationsPre-trainingArtificial intelligenceComputational pathologyImaging modelEfficient solutionSlide imagesCancer classificationModel performanceRepresentationImagesCancer diagnosisIntelligenceImproving topic modeling performance on social media through semantic relationships within biomedical terminology
Xin Y, Grabowska M, Gangireddy S, Krantz M, Kerchberger V, Dickson A, Feng Q, Yin Z, Wei W. Improving topic modeling performance on social media through semantic relationships within biomedical terminology. PLOS ONE 2025, 20: e0318702. PMID: 39982945, PMCID: PMC11845042, DOI: 10.1371/journal.pone.0318702.Peer-Reviewed Original ResearchConceptsSocial media textsTopic modelsSocial mediaHealth-related topicsAnalyze social mediaSemantic relationshipsBiomedical terminologiesMedical conceptsSemantic typesRecord validationModeling pipelineMedia textsUnsupervised machineExpert evaluationHealthcare ResearchModel performanceOnline discussionsTextTopicsPipelineUsersMachineModeling approachModelTechnique's potentialDICOM LUT is a Key Step in Medical Image Preprocessing Towards AI Generalizability
Dapamede T, Li F, Khosravi B, Purkayastha S, Trivedi H, Gichoya J. DICOM LUT is a Key Step in Medical Image Preprocessing Towards AI Generalizability. Journal Of Imaging Informatics In Medicine 2025, 1-9. PMID: 39890738, DOI: 10.1007/s10278-025-01418-5.Peer-Reviewed Original ResearchDeep learning modelsHistogram equalizationInformation lossPreprocessing techniquesPre-processingLearning modelsPerformance of deep learning modelsMachine learning practitionersRisk of information lossDeep learning classifierImage preprocessing techniquesImprove model robustnessImage pre-processingTraining dataCXR datasetPreprocessed informationLearning classifiersDataset curationLearning practitionersModel performancePotential overfittingDatasetModel robustnessPreprocessingSharing datasetTotal Knee Arthroplasty Automated Implant Detector: An Uncertainty-Aware Deep Learning Classifier to Identify Total Knee Arthroplasty Implants
Mulford K, Saniei S, Kaji E, Grove A, Girod-Hoffman M, Rouzrokh P, Abdel M, Taunton M, Wyles C. Total Knee Arthroplasty Automated Implant Detector: An Uncertainty-Aware Deep Learning Classifier to Identify Total Knee Arthroplasty Implants. The Journal Of Arthroplasty 2025 PMID: 39832639, DOI: 10.1016/j.arth.2025.01.019.Peer-Reviewed Original ResearchHeld-out test setTest setDetection systemDeep learning classifierDeep learning algorithmsDeep learning modelsExternal test setUncertainty-awareEfficientNet architectureLearning algorithmsLearning classifiersConformal predictionLearning modelsExternal testPrimary knee implantsModel accuracyTime-consumingUncertainty quantificationSafety mechanismsAverage model accuracyModel performanceUncertainty estimationImagesEfficientNetClassifier
2024
Integrative factor-adjusted sparse generalized linear models
Xu F, Ma S, Zhang Q. Integrative factor-adjusted sparse generalized linear models. Journal Of Statistical Computation And Simulation 2024, 95: 764-780. DOI: 10.1080/00949655.2024.2439450.Peer-Reviewed Original ResearchVariable selection consistencyHigh-dimensional dataIncreased accessibility of dataSelection consistencyConsistency propertiesCorrelated covariatesGeneralized linear modelVariable selectionAnalysis of genetic dataAccessibility of dataIdiosyncratic componentsCompetitive performanceCovariatesGenetic dataLinear modelSample sizeImprove model performanceEstimationIntegrated analysisModel estimatesLatent factorsModel performancePractical useConsistencySelf-supervised Pre-training Tasks for an fMRI Time-Series Transformer in Autism Detection
Zhou Y, Duan P, Du Y, Dvornek N. Self-supervised Pre-training Tasks for an fMRI Time-Series Transformer in Autism Detection. Lecture Notes In Computer Science 2024, 15266: 145-154. PMID: 40160559, PMCID: PMC11951341, DOI: 10.1007/978-3-031-78761-4_14.Peer-Reviewed Original ResearchSelf-supervised pre-training tasksPre-training tasksFunctional magnetic resonance imagingPre-training stepTransformer-based modelsTime-series fMRI dataTraining data availabilityAutism spectrum disorderTime series transformationsTransformation modelMachine learning methodsFunctional magnetic resonance imaging time-series dataClassification taskPublic datasetsTraining dataOver-fittingComputed functional connectivityLearning methodsModel performanceMasking strategyAutism detectionCross-validationTaskDatasetAverage improvementUncertainty-Aware Deep Learning Characterization of Knee Radiographs for Large-Scale Registry Creation
Mulford K, Grove A, Kaji E, Rouzrokh P, Roman R, Kremers M, Maradit Kremers H, Taunton M, Wyles C. Uncertainty-Aware Deep Learning Characterization of Knee Radiographs for Large-Scale Registry Creation. The Journal Of Arthroplasty 2024, 40: 1232-1238. PMID: 39477040, PMCID: PMC11985313, DOI: 10.1016/j.arth.2024.10.103.Peer-Reviewed Original ResearchConceptsObject detection modelDetection modelF1 scoreConformal predictionAverage precisionOut-of-domain imagesOut-of-domainPer-class F1-scoresUncertainty-awareMultilabel classifierEfficientNet modelIngestion pipelineLabel outputsClassification modelClassifierDomain detectionHeld-outMultilabelUncertainty quantificationModel performanceKnee imagesEfficientNetLarge-scaleHardwarePrecisionSubject-aware PET Denoising with Contrastive Adversarial Domain Generalization
Liu X, Marin T, Eslahi S, Tiss A, Chemli Y, Johson K, Fakhri G, Ouyang J. Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization. 2011 IEEE Nuclear Science Symposium Conference Record 2024, 00: 1-1. PMID: 39445307, PMCID: PMC11497478, DOI: 10.1109/nss/mic/rtsd57108.2024.10656150.Peer-Reviewed Original ResearchDomain generalizationDenoising performanceDenoising moduleDeep learningSubject-independent mannerSubject-invariant featuresSuperior denoising performanceAdversarial learning frameworkSubject-related informationConventional UNetBottleneck featuresTrustworthy systemsLearning frameworkDL modelsDL model performanceDenoisingNoise realizationsNegative samplesList-mode dataImage volumesModel performancePerformancePerformance of positron emission tomographyUNetFraction of eventsAdding the third dimension: 3D convolutional neural network diagnosis of temporal lobe epilepsy
Kaestner E, Hassanzadeh R, Gleichgerrcht E, Hasenstab K, Roth R, Chang A, Rüber T, Davis K, Dugan P, Kuzniecky R, Fridriksson J, Parashos A, Bagić A, Drane D, Keller S, Calhoun V, Abrol A, Bonilha L, McDonald C. Adding the third dimension: 3D convolutional neural network diagnosis of temporal lobe epilepsy. Brain Communications 2024, 6: fcae346. PMID: 39474046, PMCID: PMC11520928, DOI: 10.1093/braincomms/fcae346.Peer-Reviewed Original ResearchConvolutional neural networkTwo-dimension convolutional neural networkThree-dimension convolutional neural networksNeural network diagnosisSaliency mapNetwork diagnosisImage harmonizationTraining 3DNeural networkModel trainingMedical imagesTemporal lobe epilepsyModel performanceSubcortical regionsMedian accuracySignificant outperformanceLobe epilepsyStructural abnormalitiesAccuracyClassificationDatapointsEpilepsy lesionsCNN diagnosisPerformanceEvaluating 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 setDeepChannelPrediction Consistency Regularization for Learning with Noise Labels Based on Contrastive Clustering
Sun X, Zhang S, Ma S. Prediction Consistency Regularization for Learning with Noise Labels Based on Contrastive Clustering. Entropy 2024, 26: 308. PMID: 38667864, PMCID: PMC11049179, DOI: 10.3390/e26040308.Peer-Reviewed Original ResearchLabel noiseContrastive clusteringConsistency regularizationRegularization termPrediction consistencyClassification accuracyImpact of label noiseEffects of label noiseClassification taskClustering problemComprehensive experimentsNoise labelsLabel informationNeural networkClustering resultsSample recognitionNoise rateMitigate noiseNoiseClassificationModel performanceRegularizationPrototypeAccuracyLabelingImproving Age Prediction: Utilizing LSTM-Based Dynamic Forecasting For Data Augmentation in Multivariate Time Series Analysis
Gao Y, Ellis C, Calhoun V, Miller R. Improving Age Prediction: Utilizing LSTM-Based Dynamic Forecasting For Data Augmentation in Multivariate Time Series Analysis. 2024, 00: 125-128. DOI: 10.1109/ssiai59505.2024.10508611.Peer-Reviewed Original ResearchLong short-term memoryDeep learning modelsData augmentationPerformance deep learning modelsLearning modelsMultivariate time series dataAge prediction taskShort-term memoryPrediction taskAugmented datasetDynamical forecastsComponent networksMultivariate time series analysisDatasetNeuroimaging datasetsRobust solutionTime series dataOriginal dataValidation frameworkTime series analysisSeries dataNetworkNeuroimaging fieldDataModel performancePrompt Tuning in Biomedical Relation Extraction
He J, Li F, Li J, Hu X, Nian Y, Xiang Y, Wang J, Wei Q, Li Y, Xu H, Tao C. Prompt Tuning in Biomedical Relation Extraction. Journal Of Healthcare Informatics Research 2024, 8: 206-224. PMID: 38681754, PMCID: PMC11052745, DOI: 10.1007/s41666-024-00162-9.Peer-Reviewed Original ResearchFew-shot scenariosBiomedical relation extractionNatural language processingBiomedical RERelation extractionPrompt tuningState-of-the-art performanceText mining applicationsTuning modelBioCreative VISemEval-2013Knowledge graphLanguage modelMining applicationsBiomedical textOriginal inputComputational resourcesLanguage processingExternal knowledgeSpecific textsSuperior performanceDatasetEfficient approachTaskModel performanceImproving large language models for clinical named entity recognition via prompt engineering
Hu Y, Chen Q, Du J, Peng X, Keloth V, Zuo X, Zhou Y, Li Z, Jiang X, Lu Z, Roberts K, Xu H. Improving large language models for clinical named entity recognition via prompt engineering. Journal Of The American Medical Informatics Association 2024, 31: 1812-1820. PMID: 38281112, PMCID: PMC11339492, DOI: 10.1093/jamia/ocad259.Peer-Reviewed Original ResearchClinical NER tasksNER taskTask-specific promptsEntity recognitionLanguage modelTraining samplesState-of-the-art modelsFew-shot learningState-of-the-artMinimal training dataTask-specific knowledgeF1-socreAnnotated samplesConcept extractionModel performanceAnnotated datasetsTraining dataF1 scoreTask descriptionFormat specificationsComplex clinical dataOptimal performanceTaskEvaluation schemaGPT modelLearn from orientation prior for radiograph super-resolution: Orientation operator transformer
Huang Y, Miyazaki T, Liu X, Jiang K, Tang Z, Omachi S. Learn from orientation prior for radiograph super-resolution: Orientation operator transformer. Computer Methods And Programs In Biomedicine 2024, 245: 108000. PMID: 38237449, DOI: 10.1016/j.cmpb.2023.108000.Peer-Reviewed Original ResearchConceptsSingle-image super-resolutionSuper-ResolutionFusion strategyMulti-scale feature fusion strategyImage super-resolution taskEffective latent representationsSuper-resolution taskFeature fusion strategyOperational transformationImage enhancement fieldSecond-best performanceLatent representationDenoised mapsUpsampling factorsOrientation operatorObjective metricsColor spaceImaging pipelineHigh-resolution radiographic imagesReceptive fieldsImage qualityExperimental resultsImaging fieldModel performanceImages
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply