Format

Send to

Choose Destination
Clin Cancer Res. 2018 Mar 1;24(5):1073-1081. doi: 10.1158/1078-0432.CCR-17-2236. Epub 2017 Nov 22.

Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging.

Author information

1
Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts.
2
Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania.
3
Department of Neurology, Xiangya Hospital, Central South University, Changsha, Hunan, China.
4
Department of Therapeutic Radiology, Yale School of Medicine, New Haven, Connecticut.
5
Department of Neurosurgery, Brigham and Women's Hospital, Boston, Massachusetts.
6
Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Boston, Massachusetts.
7
Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts.
8
Department of Radiology, Xiangya Hospital, Central South University, Changsha, Hunan, China.
9
Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha, Hunan, China.
10
Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, Hunan China.
11
Department of Pathology, Brigham and Women's Hospital, Boston, Massachusetts.
12
Department of Medical Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts.
13
Department of Neurology, Massachusetts General Hospital, Boston, Massachusetts.
14
Department of Pathology and Laboratory Medicine, Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania.
15
Department of Neurology, The Second Xiangya Hospital, Central South University, Changsha, Hunan, China. kalpathy@nmr.mgh.harvard.edu yangli762@gmail.com ryhuang@partners.org.
16
Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts. kalpathy@nmr.mgh.harvard.edu yangli762@gmail.com ryhuang@partners.org.
17
Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts. kalpathy@nmr.mgh.harvard.edu yangli762@gmail.com ryhuang@partners.org.

Abstract

Purpose: Isocitrate dehydrogenase (IDH) mutations in glioma patients confer longer survival and may guide treatment decision making. We aimed to predict the IDH status of gliomas from MR imaging by applying a residual convolutional neural network to preoperative radiographic data.Experimental Design: Preoperative imaging was acquired for 201 patients from the Hospital of University of Pennsylvania (HUP), 157 patients from Brigham and Women's Hospital (BWH), and 138 patients from The Cancer Imaging Archive (TCIA) and divided into training, validation, and testing sets. We trained a residual convolutional neural network for each MR sequence (FLAIR, T2, T1 precontrast, and T1 postcontrast) and built a predictive model from the outputs. To increase the size of the training set and prevent overfitting, we augmented the training set images by introducing random rotations, translations, flips, shearing, and zooming.Results: With our neural network model, we achieved IDH prediction accuracies of 82.8% (AUC = 0.90), 83.0% (AUC = 0.93), and 85.7% (AUC = 0.94) within training, validation, and testing sets, respectively. When age at diagnosis was incorporated into the model, the training, validation, and testing accuracies increased to 87.3% (AUC = 0.93), 87.6% (AUC = 0.95), and 89.1% (AUC = 0.95), respectively.Conclusions: We developed a deep learning technique to noninvasively predict IDH genotype in grade II-IV glioma using conventional MR imaging using a multi-institutional data set. Clin Cancer Res; 24(5); 1073-81. ©2017 AACR.

PMID:
29167275
PMCID:
PMC6051535
DOI:
10.1158/1078-0432.CCR-17-2236
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for HighWire Icon for PubMed Central
Loading ...
Support Center