Prediction of 1p/19q Codeletion in Diffuse Glioma Patients Using Pre-operative Multiparametric Magnetic Resonance Imaging

被引:24
作者
Kim, Donnie [1 ]
Wang, Nicholas [2 ]
Ravikumar, Viswesh [1 ]
Raghuram, D. R. [1 ]
Li, Jinju [2 ]
Patel, Ankit [1 ]
Wendt, Richard E., III [1 ]
Rao, Ganesh [1 ]
Rao, Arvind [2 ]
机构
[1] Univ Texas MD Anderson Canc Ctr, Dept Bioinformat & Computat Biol, Houston, TX 77030 USA
[2] Univ Michigan, Dept Computat Med & Bioinformat, Ann Arbor, MI 48109 USA
关键词
multiparametric MRI; image perturbation; radiomic features; glioma; persistent homology; 1p/19q codeletion; GRADE GLIOMAS; MUTATIONS; STABILITY; DELETION; IMAGES; SYSTEM; IDH;
D O I
10.3389/fncom.2019.00052
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
This study compared the predictive power and robustness of texture, topological, and convolutional neural network (CNN) based image features for measuring tumors in MRI. These features were used to predict 1p/19q codeletion in the MICCAI BRATS 2017 challenge dataset. Topological data analysis (TDA) based on persistent homology had predictive performance as good as or better than texture-based features and was also less susceptible to image-based perturbations. Features from a pre-trained convolutional neural network had similar predictive performances and robustness as TDA, but also performed better using an alternative classification algorithm, k-top scoring pairs. Feature robustness can be used as a filtering technique without greatly impacting model performance and can also be used to evaluate model stability.
引用
收藏
页数:10
相关论文
共 28 条
[1]   Classification of hepatic lesions using the matching metric [J].
Adcock, Aaron ;
Rubin, Daniel ;
Carlsson, Gunnar .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2014, 121 :36-42
[2]  
Adcock Aaron, 2013, ARXIV13040530
[3]   switchBox: an R package for k-Top Scoring Pairs classifier development [J].
Afsari, Bahman ;
Fertig, Elana J. ;
Geman, Donald ;
Marchionni, Luigi .
BIOINFORMATICS, 2015, 31 (02) :273-274
[4]   Predicting Deletion of Chromosomal Arms 1p/19q in Low-Grade Gliomas from MR Images Using Machine Intelligence [J].
Akkus, Zeynettin ;
Ali, Issa ;
Sedlar, Jiri ;
Agrawal, Jay P. ;
Parney, Ian F. ;
Giannini, Caterina ;
Erickson, Bradley J. .
JOURNAL OF DIGITAL IMAGING, 2017, 30 (04) :469-476
[5]  
[Anonymous], 2017, SEGMENTATION LABELS
[6]  
Bakas S., 2018, ARXIV181102629
[7]   Data Descriptor: Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features [J].
Bakas, Spyridon ;
Akbari, Hamed ;
Sotiras, Aristeidis ;
Bilello, Michel ;
Rozycki, Martin ;
Kirby, Justin S. ;
Freymann, John B. ;
Farahani, Keyvan ;
Davatzikos, Christos .
SCIENTIFIC DATA, 2017, 4
[8]  
Bauer S., 2012, Insight Journal
[9]   Stability of radiomic features in CT perfusion maps [J].
Bogowicz, M. ;
Riesterer, O. ;
Bundschuh, R. A. ;
Veit-Haibach, P. ;
Huellner, M. ;
Studer, G. ;
Stieb, S. ;
Glatz, S. ;
Pruschy, M. ;
Guckenberger, M. ;
Tanadini-Lang, S. .
PHYSICS IN MEDICINE AND BIOLOGY, 2016, 61 (24) :8736-8749
[10]   Significance of complete 1p/19q co-deletion, IDH1 mutation and MGMT promoter methylation in gliomas: use with caution [J].
Boots-Sprenger, Sandra H. E. ;
Sijben, Angelique ;
Rijntjes, Jos ;
Tops, Bastiaan B. J. ;
Idema, Albert J. ;
Rivera, Andreana L. ;
Bleeker, Fonnet E. ;
Gijtenbeek, Anja M. ;
Diefes, Kristin ;
Heathcock, Lindsey ;
Aldape, Kenneth D. ;
Jeuken, Judith W. M. ;
Wesseling, Pieter .
MODERN PATHOLOGY, 2013, 26 (07) :922-929