Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

Abstract

Deep learning approaches such as convolutional neural nets have consistently outperformed previous methods on challenging tasks such as dense, semantic segmentation. However, the various proposed networks perform differently, with behaviour largely influenced by architectural choices and training settings. This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods. The approach reduces the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database. EMMA can be seen as an unbiased, generic deep learning model which is shown to yield excellent performance, winning the first position in the BRATS 2017 competition among 50+ participating teams.

The method won the 1st-place in the Brain Tumour Segmentation (BRATS) 2017 competition (segmentation task)

References in corpus (2)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks

Cited by in corpus (17)

• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• A review: Deep learning for medical image segmentation using multi-modality fusion
• Cross-Modality Deep Feature Learning for Brain Tumor Segmentation
• Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images
• Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
• Automated Olfactory Bulb Segmentation on High Resolutional T2-Weighted MRI
• Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data
• Survival prediction using ensemble tumor segmentation and transfer learning
• Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions
• ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
• Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
• A Volumetric Convolutional Neural Network for Brain Tumor Segmentation
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• Deep Learning Based Segmentation of Various Brain Lesions for Radiosurgery
• Artificial Intelligence in Tumor Subregion Analysis Based on Medical Imaging: A Review
• EchoFusion: Tracking and Reconstruction of Objects in 4D Freehand Ultrasound Imaging without External Trackers
• BEDS: Bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation