Trends in Development of Novel Machine Learning Methods for the Identification of Gliomas in Datasets That Include Non-Glioma Images: A Systematic Review
Subramanian H, Dey R, Brim WR, Tillmanns N, Petersen G, Brackett A, Mahajan A, Johnson M, Malhotra A, Aboian M. Trends in Development of Novel Machine Learning Methods for the Identification of Gliomas in Datasets That Include Non-Glioma Images: A Systematic Review. Frontiers In Oncology 2021, 11: 788819. PMID: 35004312, PMCID: PMC8733688, DOI: 10.3389/fonc.2021.788819.Peer-Reviewed Original ResearchMachine learningIdentification of gliomasNovel machine learning methodMachine learning methodsAccuracy of algorithmsFive-fold cross validationDeep learningArtificial intelligenceGlioma imagesAlgorithm trainingNeural networkHeterogeneous datasetsLearning methodsAlgorithm testingTRIPOD criteriaNormal imagesAlgorithm developmentSame datasetAbnormal imagesDatasetLimited datasetAlgorithmSingle-institution datasetCross validationLearningNIMG-71. IDENTIFYING CLINICALLY APPLICABLE MACHINE LEARNING ALGORITHMS FOR GLIOMA SEGMENTATION USING A SYSTEMATIC LITERATURE REVIEW
Tillmanns N, Lum A, Brim W, Subramanian H, Lin M, Bousabarah K, Malhotra A, cui J, Brackett A, Payabvash S, Ikuta I, Johnson M, Turowski B, Aboian M. NIMG-71. IDENTIFYING CLINICALLY APPLICABLE MACHINE LEARNING ALGORITHMS FOR GLIOMA SEGMENTATION USING A SYSTEMATIC LITERATURE REVIEW. Neuro-Oncology 2021, 23: vi145-vi145. PMCID: PMC8598815, DOI: 10.1093/neuonc/noab196.568.Peer-Reviewed Original ResearchConvolutional neural networkSegmentation of gliomasSupport vector machineGlioma segmentationDeep learningMachine learningLikelihood of overfittingMachine Learning AlgorithmsArtificial intelligenceLearning algorithmDice scoreML algorithmsTumor segmentationNeural networkVector machineCommon algorithmsSegmentationSame datasetML methodsTCIA datasetAlgorithmData acquisitionAccuracy reportingHigh accuracyLearning