%0 Generic
%T Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge
%A Spyridon Bakas
%A Mauricio Reyes
%A Andras Jakab
%A Stefan Bauer
%A Markus Rempfler
%A Alessandro Crimi
%A Russell Takeshi Shinohara
%A Christoph Berger
%A Sung Min Ha
%A Martin Rozycki
%A Marcel Prastawa
%A Esther Alberts
%A Jana Lipkova
%A John Freymann
%A Justin Kirby
%A Michel Bilello
%A Hassan Fathallah-Shaykh
%A Roland Wiest
%A Jan Kirschke
%A Benedikt Wiestler
%A Rivka Colen
%A Aikaterini Kotrotsou
%A Pamela Lamontagne
%A Daniel Marcus
%A Mikhail Milchenko
%A Arash Nazeri
%A Marc-Andre Weber
%A Abhishek Mahajan
%A Ujjwal Baid
%A Dongjin Kwon
%A Manu Agarwal
%A Mahbubul Alam
%A Alberto Albiol
%A Antonio Albiol
%A Varghese Alex
%A Tuan Anh Tran
%A Tal Arbel
%A Aaron Avery
%A Subhashis Banerjee
%A Thomas Batchelder
%A Kayhan Batmanghelich
%A Enzo Battistella
%A Martin Bendszus
%A Eze Benson
%A Jose Bernal
%A George Biros
%A Mariano Cabezas
%A Siddhartha Chandra
%A Yi-Ju Chang
%A Joseph Chazalon
%A Shengcong Chen
%A Wei Chen
%A Jefferson Chen
%A Kun Cheng
%A Meinel Christoph
%A Roger Chylla
%A Albert Clérigues
%A Anthony Costa
%A Xiaomeng Cui
%A Zhenzhen Dai
%A Lutao Dai
%A Eric Deutsch
%A Changxing Ding
%A Chao Dong
%A Wojciech Dudzik
%A Theo Estienne
%A Hyung Eun Shin
%A Richard Everson
%A Jonathan Fabrizio
%A Longwei Fang
%A Xue Feng
%A Lucas Fidon
%A Naomi Fridman
%A Huan Fu
%A David Fuentes
%A David G Gering
%A Yaozong Gao
%A Evan Gates
%A Amir Gholami
%A Mingming Gong
%A Sandra Gonzalez-Villa
%A J Gregory Pauloski
%A Yuanfang Guan
%A Sheng Guo
%A Sudeep Gupta
%A Meenakshi H Thakur
%A Klaus H Maier-Hein
%A Woo-Sup Han
%A Huiguang He
%A Aura Hernandez-Sabate
%A Evelyn Herrmann
%A Naveen Himthani
%A Winston Hsu
%A Cheyu Hsu
%A Xiaojun Hu
%A Xiaobin Hu
%A Yan Hu
%A Yifan Hu
%A Rui Hua
%D 2018
%F Spyridon Bakas2018
%O ADAS; 600.118
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3252), last updated on Thu, 28 Jan 2021 10:31:08 +0100
%X Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multiparametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e. 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in preoperative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that undergone gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.
%K BraTS
%K challenge
%K brain
%K tumor
%K segmentation
%K machine learning
%K glioma
%K glioblastoma
%K radiomics
%K survival
%K progression
%K RECIST
%9 miscellaneous