Publication | Open Access
Brain tumour segmentation using U-Net based fully convolutional networks and extremely randomized trees
20
Citations
0
References
2018
Year
Convolutional Neural NetworkEngineeringMachine LearningDigital PathologyPathologyNeuro-oncologyImage AnalysisData SciencePattern RecognitionBrain Tumour SegmentationConvolutional NetworksTissue SegmentationRadiologyMachine VisionMedical ImagingNeuroimagingMedical Image ComputingDeep LearningComputer VisionRadiomicsBrain TumourBiomedical ImagingComputer-aided DiagnosisRandomized TreesNeuroscienceMedicineMedical Image AnalysisImage SegmentationTumour Core
In this paper, we present a model-based learning for brain tumour segmentation from multimodal MRI protocols. The model uses U-Net-based fully convolutional networks to extract features from a multimodal MRI training dataset and then applies them to Extremely randomized trees (ExtraTrees) classifier for segmenting the abnormal tissues associated with brain tumour. The morphological filters are then utilized to remove the misclassified labels. Our method was evaluated on the Brain Tumour Segmentation Challenge 2013 (BRATS 2013) dataset, achieving the Dice metric of 0.85, 0.81 and 0.72 for whole tumour, tumour core and enhancing tumour core, respectively. The segmentation results obtained have been compared to the most recent methods, providing a competitive performance.