TY  - STD
AU  - Spyridon Bakas
AU  - Mauricio Reyes
AU  - Andras Jakab
AU  - Stefan Bauer
AU  - Markus Rempfler
AU  - Alessandro Crimi
AU  - Russell Takeshi Shinohara
AU  - Christoph Berger
AU  - Sung Min Ha
AU  - Martin Rozycki
AU  - Marcel Prastawa
AU  - Esther Alberts
AU  - Jana Lipkova
AU  - John Freymann
AU  - Justin Kirby
AU  - Michel Bilello
AU  - Hassan Fathallah-Shaykh
AU  - Roland Wiest
AU  - Jan Kirschke
AU  - Benedikt Wiestler
AU  - Rivka Colen
AU  - Aikaterini Kotrotsou
AU  - Pamela Lamontagne
AU  - Daniel Marcus
AU  - Mikhail Milchenko
AU  - Arash Nazeri
AU  - Marc-Andre Weber
AU  - Abhishek Mahajan
AU  - Ujjwal Baid
AU  - Dongjin Kwon
AU  - Manu Agarwal
AU  - Mahbubul Alam
AU  - Alberto Albiol
AU  - Antonio Albiol
AU  - Varghese Alex
AU  - Tuan Anh Tran
AU  - Tal Arbel
AU  - Aaron Avery
AU  - Subhashis Banerjee
AU  - Thomas Batchelder
AU  - Kayhan Batmanghelich
AU  - Enzo Battistella
AU  - Martin Bendszus
AU  - Eze Benson
AU  - Jose Bernal
AU  - George Biros
AU  - Mariano Cabezas
AU  - Siddhartha Chandra
AU  - Yi-Ju Chang
AU  - Joseph Chazalon
AU  - Shengcong Chen
AU  - Wei Chen
AU  - Jefferson Chen
AU  - Kun Cheng
AU  - Meinel Christoph
AU  - Roger Chylla
AU  - Albert Clérigues
AU  - Anthony Costa
AU  - Xiaomeng Cui
AU  - Zhenzhen Dai
AU  - Lutao Dai
AU  - Eric Deutsch
AU  - Changxing Ding
AU  - Chao Dong
AU  - Wojciech Dudzik
AU  - Theo Estienne
AU  - Hyung Eun Shin
AU  - Richard Everson
AU  - Jonathan Fabrizio
AU  - Longwei Fang
AU  - Xue Feng
AU  - Lucas Fidon
AU  - Naomi Fridman
AU  - Huan Fu
AU  - David Fuentes
AU  - David G Gering
AU  - Yaozong Gao
AU  - Evan Gates
AU  - Amir Gholami
AU  - Mingming Gong
AU  - Sandra Gonzalez-Villa
AU  - J Gregory Pauloski
AU  - Yuanfang Guan
AU  - Sheng Guo
AU  - Sudeep Gupta
AU  - Meenakshi H Thakur
AU  - Klaus H Maier-Hein
AU  - Woo-Sup Han
AU  - Huiguang He
AU  - Aura Hernandez-Sabate
AU  - Evelyn Herrmann
AU  - Naveen Himthani
AU  - Winston Hsu
AU  - Cheyu Hsu
AU  - Xiaojun Hu
AU  - Xiaobin Hu
AU  - Yan Hu
AU  - Yifan Hu
AU  - Rui Hua
PY  - 2018//
TI  - Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge
KW  - BraTS
KW  - challenge
KW  - brain
KW  - tumor
KW  - segmentation
KW  - machine learning
KW  - glioma
KW  - glioblastoma
KW  - radiomics
KW  - survival
KW  - progression
KW  - RECIST
N2  - 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.
N1  - ADAS; 600.118
ID  - Spyridon Bakas2018
ER  -