Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

File Description SizeFormat 
1711.01468v1.pdfAccepted version3.17 MBAdobe PDFView/Open
Title: Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation
Authors: Kamnitsas, K
Bai, W
Ferrante, E
McDonagh, S
Sinclair, M
Pawlowski, N
Rajchl, M
Lee, M
Kainz, B
Rueckert, D
Glocker, B
Item Type: Working Paper
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.
URI: http://hdl.handle.net/10044/1/54498
Copyright Statement: © The Authors
Sponsor/Funder: Commission of the European Communities
NVIDIA Corporation
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: HEALTH-F2-2013-602150
EP/N023668/1
Keywords: cs.CV
cs.AI
cs.LG
Notes: The method won the 1st-place in the Brain Tumour Segmentation (BRATS) 2017 competition (segmentation task)
Appears in Collections:Faculty of Engineering
Computing
Department of Medicine
Faculty of Medicine



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons