2023
Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning
Kucukkaya A, Zeevi T, Chai N, Raju R, Haider S, Elbanan M, Petukhova-Greenstein A, Lin M, Onofrey J, Nowak M, Cooper K, Thomas E, Santana J, Gebauer B, Mulligan D, Staib L, Batra R, Chapiro J. Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning. Scientific Reports 2023, 13: 7579. PMID: 37165035, PMCID: PMC10172370, DOI: 10.1038/s41598-023-34439-7.Peer-Reviewed Original ResearchMeSH KeywordsCarcinoma, HepatocellularHumansLiver NeoplasmsMachine LearningMagnetic Resonance ImagingNeoplasm Recurrence, LocalRetrospective Studies
2022
Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study.
Iseke S, Zeevi T, Kucukkaya AS, Raju R, Gross M, Haider SP, Petukhova-Greenstein A, Kuhn TN, Lin M, Nowak M, Cooper K, Thomas E, Weber MA, Madoff DC, Staib L, Batra R, Chapiro J. Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study. American Journal Of Roentgenology 2022, 220: 245-255. PMID: 35975886, PMCID: PMC10015590, DOI: 10.2214/ajr.22.28077.Peer-Reviewed Original ResearchMeSH KeywordsCarcinoma, HepatocellularFemaleHumansLiver NeoplasmsMagnetic Resonance ImagingMaleMiddle AgedNeoplasm Recurrence, LocalRetrospective StudiesRisk FactorsConceptsEarly-stage hepatocellular carcinomaLiver transplantHepatocellular carcinomaImaging featuresPosttreatment recurrenceOrgan allocationMean AUCLiver transplant eligibilityPretreatment clinical characteristicsPretreatment MRI examinationsKaplan-Meier analysisKaplan-Meier curvesClinical characteristicsImaging surveillanceTherapy allocationTransplant eligibilityUnderwent treatmentClinical parametersRetrospective studyUnpredictable complicationMRI dataConcept studyPoor survivalClinical impactPretreatment MRIMR Imaging Biomarkers for the Prediction of Outcome after Radiofrequency Ablation of Hepatocellular Carcinoma: Qualitative and Quantitative Assessments of the Liver Imaging Reporting and Data System and Radiomic Features
Petukhova-Greenstein A, Zeevi T, Yang J, Chai N, DiDomenico P, Deng Y, Ciarleglio M, Haider SP, Onyiuke I, Malpani R, Lin M, Kucukkaya AS, Gottwald LA, Gebauer B, Revzin M, Onofrey J, Staib L, Gunabushanam G, Taddei T, Chapiro J. MR Imaging Biomarkers for the Prediction of Outcome after Radiofrequency Ablation of Hepatocellular Carcinoma: Qualitative and Quantitative Assessments of the Liver Imaging Reporting and Data System and Radiomic Features. Journal Of Vascular And Interventional Radiology 2022, 33: 814-824.e3. PMID: 35460887, PMCID: PMC9335926, DOI: 10.1016/j.jvir.2022.04.006.Peer-Reviewed Original ResearchMeSH KeywordsBiomarkersCarcinoma, HepatocellularCatheter AblationContrast MediaHumansLiver NeoplasmsMagnetic Resonance ImagingRetrospective StudiesConceptsProgression-free survivalPoor progression-free survivalLiver Imaging ReportingHepatocellular carcinomaMR imaging biomarkersRadiomics signatureRadiofrequency ablationRadiomic featuresImaging biomarkersImaging ReportingFirst follow-up imagingMedian progression-free survivalRF ablationEarly-stage hepatocellular carcinomaPretreatment magnetic resonanceFirst-line treatmentMultifocal hepatocellular carcinomaSelection operator Cox regression modelTherapy-naïve patientsEarly-stage diseaseKaplan-Meier analysisCox regression modelLog-rank testFollow-up imagingPrediction of outcome
2020
Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning
Bousabarah K, Letzen B, Tefera J, Savic L, Schobert I, Schlachter T, Staib LH, Kocher M, Chapiro J, Lin M. Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning. Abdominal Radiology 2020, 46: 216-225. PMID: 32500237, PMCID: PMC7714704, DOI: 10.1007/s00261-020-02604-5.Peer-Reviewed Original ResearchMeSH KeywordsCarcinoma, HepatocellularDeep LearningHumansLiver NeoplasmsMagnetic Resonance ImagingRetrospective StudiesConceptsDeep convolutional neural networkAverage false positive rateDice similarity coefficientU-NetDeep learning algorithmsConvolutional neural networkTest setMean Dice similarity coefficientRandom forest classifierDCNN methodDCNN approachDeep learningNet architectureLearning algorithmNeural networkLiver segmentationManual 3D segmentationForest classifierGround truthManual segmentationFalse positive rateCorresponding segmentationSegmentationMultiphasic contrast-enhanced MRIThresholding
2016
Is there an added value of a hepatobiliary phase with gadoxetate disodium following conventional MRI with an extracellular gadolinium agent in a single imaging session for detection of primary hepatic malignancies?
Pahade JK, Juice D, Staib L, Israel G, Cornfeld D, Mitchell K, Weinreb J. Is there an added value of a hepatobiliary phase with gadoxetate disodium following conventional MRI with an extracellular gadolinium agent in a single imaging session for detection of primary hepatic malignancies? Abdominal Radiology 2016, 41: 1270-1284. PMID: 26800701, DOI: 10.1007/s00261-016-0635-9.Peer-Reviewed Original Research