Featured Publications
Comparing 3D, 2.5D, and 2D Approaches to Brain Image Auto-Segmentation
Avesta A, Hossain S, Lin M, Aboian M, Krumholz H, Aneja S. Comparing 3D, 2.5D, and 2D Approaches to Brain Image Auto-Segmentation. Bioengineering 2023, 10: 181. PMID: 36829675, PMCID: PMC9952534, DOI: 10.3390/bioengineering10020181.Peer-Reviewed Original ResearchLimited training dataDice scoreComputational memoryTraining dataBrain imagesDeep-learning methodsHigher Dice scoresSegmentation accuracyAuto-segmentation modelComputational speedPerformance metricsOne-sliceAuto-SegmentationBetter performanceConsecutive slicesImagesDeploymentLowest Dice scoresMemoryPerformanceTrainingMetricsModelAccuracyDataArtificial Intelligence in Breast Cancer Screening
Potnis K, Ross J, Aneja S, Gross C, Richman I. Artificial Intelligence in Breast Cancer Screening. JAMA Internal Medicine 2022, 182: 1306-1312. PMID: 36342705, PMCID: PMC10623674, DOI: 10.1001/jamainternmed.2022.4969.Peer-Reviewed Original ResearchPerspectives of Patients About Artificial Intelligence in Health Care
Khullar D, Casalino LP, Qian Y, Lu Y, Krumholz HM, Aneja S. Perspectives of Patients About Artificial Intelligence in Health Care. JAMA Network Open 2022, 5: e2210309. PMID: 35507346, PMCID: PMC9069257, DOI: 10.1001/jamanetworkopen.2022.10309.Peer-Reviewed Original ResearchPrevalence of Missing Data in the National Cancer Database and Association With Overall Survival
Yang DX, Khera R, Miccio JA, Jairam V, Chang E, Yu JB, Park HS, Krumholz HM, Aneja S. Prevalence of Missing Data in the National Cancer Database and Association With Overall Survival. JAMA Network Open 2021, 4: e211793. PMID: 33755165, PMCID: PMC7988369, DOI: 10.1001/jamanetworkopen.2021.1793.Peer-Reviewed Original ResearchConceptsNational Cancer DatabaseNon-small cell lung cancerOverall survivalCell lung cancerCancer DatabaseMedical recordsLung cancerProstate cancerBreast cancerPatient recordsComplete dataRetrospective cohort studyCohort studyCancer RegistryCommon cancerVariables of interestHigh prevalenceMAIN OUTCOMEPatientsClinical advancementReal-world data sourcesCancerPrevalenceSurvivalHeterogeneous differencesPublic vs physician views of liability for artificial intelligence in health care
Khullar D, Casalino LP, Qian Y, Lu Y, Chang E, Aneja S. Public vs physician views of liability for artificial intelligence in health care. Journal Of The American Medical Informatics Association 2021, 28: 1574-1577. PMID: 33871009, PMCID: PMC8279784, DOI: 10.1093/jamia/ocab055.Peer-Reviewed Original ResearchComparison of radiomic feature aggregation methods for patients with multiple tumors
Chang E, Joel MZ, Chang HY, Du J, Khanna O, Omuro A, Chiang V, Aneja S. Comparison of radiomic feature aggregation methods for patients with multiple tumors. Scientific Reports 2021, 11: 9758. PMID: 33963236, PMCID: PMC8105371, DOI: 10.1038/s41598-021-89114-6.Peer-Reviewed Original ResearchConceptsCox proportional hazards modelCox proportional hazardsProportional hazards modelBrain metastasesRadiomic featuresHazards modelProportional hazardsStandard Cox proportional hazards modelMultifocal brain metastasesMultiple brain metastasesNumber of patientsPatient-level outcomesHigher concordance indexRadiomic feature analysisRandom survival forest modelSurvival modelsDifferent tumor volumesMultifocal tumorsCancer outcomesMultiple tumorsMetastatic cancerConcordance indexTumor volumePatientsTumor typesUsing Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology
Joel MZ, Umrao S, Chang E, Choi R, Yang DX, Duncan JS, Omuro A, Herbst R, Krumholz HM, Aneja S. Using Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology. JCO Clinical Cancer Informatics 2022, 6: e2100170. PMID: 35271304, PMCID: PMC8932490, DOI: 10.1200/cci.21.00170.Peer-Reviewed Original ResearchPremetastatic shifts of endogenous and exogenous mutational processes support consolidative therapy in EGFR-driven lung adenocarcinoma
Fisk JN, Mahal AR, Dornburg A, Gaffney SG, Aneja S, Contessa JN, Rimm D, Yu JB, Townsend JP. Premetastatic shifts of endogenous and exogenous mutational processes support consolidative therapy in EGFR-driven lung adenocarcinoma. Cancer Letters 2021, 526: 346-351. PMID: 34780851, PMCID: PMC8702484, DOI: 10.1016/j.canlet.2021.11.011.Peer-Reviewed Original ResearchConceptsMutational processesSingle ancestral lineageAncestral lineageProgression of cancerMetastatic lineagesPhylogenetic analysisGenetic resistanceEvolutionary processesExogenous mutational processesCancer evolutionConsolidative therapyMutational signature analysisEGFR-positive non-small cell lung cancerNon-small cell lung cancerKey eventsLineagesCell populationsTherapeutic resistanceLocal consolidative therapyClinical time courseCell lung cancerDisease etiologyTherapeutic decision makingCisplatin therapyLung cancerComparing Detection Schemes for Adversarial Images against Deep Learning Models for Cancer Imaging
Joel M, Avesta A, Yang D, Zhou J, Omuro A, Herbst R, Krumholz H, Aneja S. Comparing Detection Schemes for Adversarial Images against Deep Learning Models for Cancer Imaging. Cancers 2023, 15: 1548. PMID: 36900339, PMCID: PMC10000732, DOI: 10.3390/cancers15051548.Peer-Reviewed Original ResearchAdversarial imagesDeep learning modelsDL modelsDetection modelLearning modelConvolutional neural networkDetection schemeAdversarial detectionDefense techniquesMachine learningMedical imagesAdversarial perturbationsInput imageAdversarial trainingNeural networkArt performanceMagnetic resonance imagingGradient descentPixel valuesHigh accuracyImagesBrain magnetic resonance imagingAbsence of malignancyClassificationScheme3D Capsule Networks for Brain Image Segmentation
Avesta A, Hui Y, Aboian M, Duncan J, Krumholz H, Aneja S. 3D Capsule Networks for Brain Image Segmentation. American Journal Of Neuroradiology 2023, 44: 562-568. PMID: 37080721, PMCID: PMC10171390, DOI: 10.3174/ajnr.a7845.Peer-Reviewed Original Research
2024
Validating International Classification of Diseases Code (ICD) 10th Revision Algorithms for Accurate Identification of Pulmonary Embolism
Bikdeli B, Khairani C, Bejjani A, Lo Y, Mahajan S, Caraballo C, Jimenez J, Krishnathasan D, Zarghami M, Rashedi S, Jimenez D, Barco S, Secemsky E, Klok F, Hunsaker A, Aghayev A, Muriel A, Hussain M, Appah-Sampong A, Lu Y, Lin Z, Mojibian H, Aneja S, Khera R, Konstantinides S, Goldhaber S, Wang L, Zhou L, Monreal M, Piazza G, Krumholz H, Investigators P. Validating International Classification of Diseases Code (ICD) 10th Revision Algorithms for Accurate Identification of Pulmonary Embolism. Journal Of Thrombosis And Haemostasis 2024 PMID: 39505153, DOI: 10.1016/j.jtha.2024.10.013.Peer-Reviewed Original ResearchDischarge codesInternational ClassificationICD-10Yale New Haven Health SystemPositive predictive valueMass General Brigham hospitalsAccuracy of ICD-10ICD-10 codesPulmonary embolismHealth systemImage codingElectronic databasesF1 scorePre-specified protocolExcellent positive predictive valueIndependent physiciansHighest F1 scoreIdentification of pulmonary embolismAcute pulmonary embolismSecondary codePE codesScoresIdentified PERevised algorithmCUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation
Liu C, Amodio M, Shen L, Gao F, Avesta A, Aneja S, Wang J, Del Priore L, Krishnaswamy S. CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation. Lecture Notes In Computer Science 2024, 15008: 155-165. DOI: 10.1007/978-3-031-72111-3_15.Peer-Reviewed Original ResearchMedical image segmentationImage segmentationLack of labeled dataUnsupervised deep learning frameworkSegmenting medical imagesDeep learning frameworkBrain MRI imagesRetinal fundus imagesContrastive learningLearning frameworkUnsupervised methodDeep learningExpert annotationsData topologyMedical imagesGranularity levelsEmbedding mapHausdorff distanceFundus imagesDice coefficientImage dataEmbeddingAnnotationLearningMRI imagesEnhancing Clinical Decision-Making: An Externally Validated Machine Learning Model for Predicting IDH Mutation in Gliomas using Radiomics from Pre-Surgical MRI
Lost J, Ashraf N, Jekel L, von Reppert M, Tillmanns N, Willms K, Merkaj S, Petersen G, Avesta A, Ramakrishnan D, Omuro A, Nabavizadeh A, Bakas S, Bousabarah K, De Lin M, Aneja S, Sabel M, Aboian M. Enhancing Clinical Decision-Making: An Externally Validated Machine Learning Model for Predicting IDH Mutation in Gliomas using Radiomics from Pre-Surgical MRI. Neuro-Oncology Advances 2024, vdae157. DOI: 10.1093/noajnl/vdae157.Peer-Reviewed Original ResearchIsocitrate dehydrogenase mutation statusArea under the curveMagnetic resonance imagingMutation statusML modelsMachine learningSemi-automated tumour segmentationsPre-surgical magnetic resonance imagingCare of glioma patientsMachine learning modelsClinical care of glioma patientsIsocitrate dehydrogenase statusAnnotated datasetsFeature extractionPrediction taskMulti-institutional dataModel trainingIDH mutationsPredicting IDH mutationLearning modelsRetrospective studyHeterogeneous datasetsTumor segmentationGlioma patientsBrain tumorsA Comparison of Machine Learning Models to Predict Lymph Node Metastasis with Primary Tumor Transcriptome in Non-Small Cell Lung Cancer
Lee V, Park H, Aneja S, Patel A. A Comparison of Machine Learning Models to Predict Lymph Node Metastasis with Primary Tumor Transcriptome in Non-Small Cell Lung Cancer. International Journal Of Radiation Oncology • Biology • Physics 2024, 120: e638. DOI: 10.1016/j.ijrobp.2024.07.1402.Peer-Reviewed Original ResearchNon-small cell lung cancerLymph nodal metastasisCell lung cancerMedian AUCNodal metastasisPrimary tumorEndobronchial ultrasoundNon-small cell lung cancer stagingLung cancerDiagnostic uncertaintyPrediction of nodal metastasisPET-avid lesionsTreatment strategy formulationPrimary lung adenocarcinomaEBUS-guided biopsiesLymph node metastasisPrimary tumor tissuesReceiver operating characteristic curveTumor transcriptomic dataPET-CTNode metastasisNeedle aspirationCT scanNon-smallClinical decision-makingApplying Language Models to Radiology Text for Identifying Oligometastatic Non-Small Cell Lung Cancer
Moore N, Laird J, Verma N, Hager T, Sritharan D, Lee V, Maresca R, Chadha S, Park H, Aneja S. Applying Language Models to Radiology Text for Identifying Oligometastatic Non-Small Cell Lung Cancer. International Journal Of Radiation Oncology • Biology • Physics 2024, 120: e644. DOI: 10.1016/j.ijrobp.2024.07.1417.Peer-Reviewed Original ResearchNon-small cell lung cancerOligometastatic diseaseCell lung cancerRadiologic impressionTumor RegistryTest cohortOligometastatic non-small cell lung cancerIV non-small cell lung cancerStage IV non-small cell lung cancerLung cancerConvolutional neural networkMetastasis-directed therapyOligometastatic NSCLC patientsMonths of diagnosisLanguage modelClinician reviewNSCLC patientsPatient cohortClinical dataScreening patientsSubgroup analysisBrain MRIClinical textBurden of diseaseClinical relevanceAcceleration of Volumetric Abdominal Aortic Aneurysm Measurements by Leveraging Artificial Intelligence
Weiss D, Hager T, Aboian M, Lin M, Bousabarah K, Renninghoff D, Holler W, Simmons K, Loh S, Fischer U, Deuschl C, Aneja S, Aboian E. Acceleration of Volumetric Abdominal Aortic Aneurysm Measurements by Leveraging Artificial Intelligence. Journal Of Vascular Surgery 2024, 80: e37-e38. DOI: 10.1016/j.jvs.2024.06.066.Peer-Reviewed Original ResearchArtificial Intelligence-based Morpho-volumetric Analysis of Pre- and Post-EVAR Infrarenal Abdominal Aortic Aneurysms Characterized on Computed Tomography Angiography
Weiss D, Hager T, Aboian M, Lin M, Renninghoff D, Holler W, Fischer U, Deuschl C, Aneja S, Aboian E. Artificial Intelligence-based Morpho-volumetric Analysis of Pre- and Post-EVAR Infrarenal Abdominal Aortic Aneurysms Characterized on Computed Tomography Angiography. Journal Of Vascular Surgery 2024, 79: e133-e134. DOI: 10.1016/j.jvs.2024.03.165.Peer-Reviewed Original ResearchLymph node metastasis prediction with non-small cell lung cancer histopathology imaging.
Lee V, King A, Sritharan D, Moore N, Chadha S, Maresca R, Hager T, Aneja S. Lymph node metastasis prediction with non-small cell lung cancer histopathology imaging. Journal Of Clinical Oncology 2024, 42: 8063-8063. DOI: 10.1200/jco.2024.42.16_suppl.8063.Peer-Reviewed Original ResearchNon-small cell lung cancerLymph nodal metastasisNational Lung Screening TrialLymph node metastasisNodal metastasisNode metastasisEndobronchial ultrasound-guided transbronchial needle aspirationUltrasound-guided transbronchial needle aspirationTreatment strategy formulationTransbronchial needle aspirationCell lung cancerDistant metastasis statusLymph node metastasis predictionPrimary tumor dataHematoxylin and eosin (H&EInvasive diagnostic techniquesInfluence clinical decisionsN0 diseaseN3 diseaseEosin (H&EPrimary resectionDistant metastasisPET-CTNeedle aspirationCT scanOPTIMIZING PHENOTYPING ALGORITHMS FOR IDENTIFYING PULMONARY EMBOLISM IN ELECTRONIC DATABASES: THE MULTICENTER PE-EHR+ STUDY
Bikdeli B, Bejjani A, Lo Y, Khairani C, Mahajan S, Secemsky E, Jimenez J, Aghayev A, Hunsaker A, Wang L, Hussain M, Appah-Sampong A, Mojibian H, Lin Z, Aneja S, Barco S, Klok F, Konstantinides S, Zhou L, Monreal M, Jimenez D, Piazza G, Krumholz H. OPTIMIZING PHENOTYPING ALGORITHMS FOR IDENTIFYING PULMONARY EMBOLISM IN ELECTRONIC DATABASES: THE MULTICENTER PE-EHR+ STUDY. Journal Of The American College Of Cardiology 2024, 83: 2108. DOI: 10.1016/s0735-1097(24)04098-1.Peer-Reviewed Original ResearchComparison of Volumetric and 2D Measurements and Longitudinal Trajectories in the Response Assessment of BRAF V600E-Mutant Pediatric Gliomas in the Pacific Pediatric Neuro-Oncology Consortium Clinical Trial
Ramakrishnan D, Brüningk S, von Reppert M, Memon F, Maleki N, Aneja S, Kazerooni A, Nabavizadeh A, Lin M, Bousabarah K, Molinaro A, Nicolaides T, Prados M, Mueller S, Aboian M. Comparison of Volumetric and 2D Measurements and Longitudinal Trajectories in the Response Assessment of BRAF V600E-Mutant Pediatric Gliomas in the Pacific Pediatric Neuro-Oncology Consortium Clinical Trial. American Journal Of Neuroradiology 2024, 45: 475-482. PMID: 38453411, PMCID: PMC11288571, DOI: 10.3174/ajnr.a8189.Peer-Reviewed Original ResearchArea under the curvePediatric gliomasBT-RADSResponse assessmentPartial responseClinical trialsVolumetric analysisReceiver operating characteristic analysisBrain Tumor ReportingReceiver operating characteristic curveModel estimation timeOperating characteristic analysisEvaluate treatment efficacyStable diseasePartial respondersManual volumetric segmentationNo significant differenceSolid tumorsProspective studyTumor ReportingClinical decision-makingTreatment efficacyGliomaSignificant differenceCharacteristic curve