Yiming Li1, Yuchao Liang2, Zhiyan Sun1, Kaibin Xu3, Xing Fan1, Shaowu Li4, Zhong Zhang2, Tao Jiang5,6, Xing Liu1, Yinyan Wang7. 1. Beijing Neurosurgical Institute, Capital Medical University, Beijing, China. 2. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, 6 Tiantanxili, Beijing, 100050, China. 3. Institute of Automation, Chinese Academy of Sciences, Beijing, China. 4. Neurological Imaging Center, Beijing Neurosurgical Institute, Capital Medical University, Beijing, China. 5. Chinese Glioma Genome Atlas Network (CGGA) and Asian Glioma Genome Atlas Network (AGGA), Beijing, China. 6. China National Clinical Research Center for Neurological Diseases, Beijing, China. 7. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, 6 Tiantanxili, Beijing, 100050, China. tiantanyinyan@126.com.
Abstract
PURPOSE: PTEN mutation status is a pivotal biomarker for glioblastoma. This study aimed to establish a radiomic signature to predict PTEN mutation status in patients with glioblastoma, and to investigate the genetic background behind this radiomic signature. METHODS: In this study, a total of 862 radiomic features were extracted from each patient. The training (n = 69) and validation (n = 40) sets were retrospectively collected from the Cancer Genome Atlas and the Chinese Glioma Genome Atlas, respectively. The minimum redundancy maximum relevance (mRMR) algorithm was used to select the best predictive features of PTEN status. A machine learning model was then built with the selected features using a support vector machine classifier. The predictive performance of each selected feature and the complete model were evaluated via the area under the curve from receiver operating characteristic analysis in both the training and validation sets. The genetic background underlying the radiomic signature was determined using radiogenomic analysis. RESULTS: Six features were selected using the mRMR algorithm, including two features derived from contrast-enhanced images and four features derived from T2-weighted images. The predictive performance of the machine learning model for the training and validation sets were 0.925 and 0.787, respectively, which were better than the individual features. Radiogenomics analysis revealed that the PTEN-associated biological processes could be described using the radiomic signature. CONCLUSION: These results show that radiomic features derived from preoperative MRI can predict PTEN mutation status in glioblastoma patients, thus providing a novel noninvasive imaging biomarker.
PURPOSE:PTEN mutation status is a pivotal biomarker for glioblastoma. This study aimed to establish a radiomic signature to predict PTEN mutation status in patients with glioblastoma, and to investigate the genetic background behind this radiomic signature. METHODS: In this study, a total of 862 radiomic features were extracted from each patient. The training (n = 69) and validation (n = 40) sets were retrospectively collected from the Cancer Genome Atlas and the Chinese Glioma Genome Atlas, respectively. The minimum redundancy maximum relevance (mRMR) algorithm was used to select the best predictive features of PTEN status. A machine learning model was then built with the selected features using a support vector machine classifier. The predictive performance of each selected feature and the complete model were evaluated via the area under the curve from receiver operating characteristic analysis in both the training and validation sets. The genetic background underlying the radiomic signature was determined using radiogenomic analysis. RESULTS: Six features were selected using the mRMR algorithm, including two features derived from contrast-enhanced images and four features derived from T2-weighted images. The predictive performance of the machine learning model for the training and validation sets were 0.925 and 0.787, respectively, which were better than the individual features. Radiogenomics analysis revealed that the PTEN-associated biological processes could be described using the radiomic signature. CONCLUSION: These results show that radiomic features derived from preoperative MRI can predict PTEN mutation status in glioblastomapatients, thus providing a novel noninvasive imaging biomarker.
Entities:
Keywords:
Glioblastoma; Machine learning; Phosphatase and tensin homolog (PTEN); Radiogenomics
Authors: Graziella Orrù; William Pettersson-Yeo; Andre F Marquand; Giuseppe Sartori; Andrea Mechelli Journal: Neurosci Biobehav Rev Date: 2012-01-28 Impact factor: 8.989
Authors: Michael Karsy; Jayson A Neil; Jian Guan; Mark A Mahan; Mahan A Mark; Howard Colman; Randy L Jensen Journal: Neurosurg Focus Date: 2015-03 Impact factor: 4.047
Authors: Yiling Yang; Naiyuan Shao; Guanghua Luo; Lu Li; Lu Zheng; Peter Nilsson-Ehle; Ning Xu Journal: Anticancer Res Date: 2010-03 Impact factor: 2.480
Authors: Michael Lehrer; Anindya Bhadra; Visweswaran Ravikumar; James Y Chen; Max Wintermark; Scott N Hwang; Chad A Holder; Erich P Huang; Brenda Fevrier-Sullivan; John B Freymann; Arvind Rao Journal: Oncoscience Date: 2017-06-23
Authors: Jorge A Benitez; Jianhui Ma; Matteo D'Antonio; Antonia Boyer; Maria Fernanda Camargo; Ciro Zanca; Stephen Kelly; Alireza Khodadadi-Jamayran; Nathan M Jameson; Michael Andersen; Hrvoje Miletic; Shahram Saberi; Kelly A Frazer; Webster K Cavenee; Frank B Furnari Journal: Nat Commun Date: 2017-05-12 Impact factor: 14.919
Authors: Alexander G Yearley; Julian Bryan Iorgulescu; Ennio Antonio Chiocca; Pier Paolo Peruzzi; Timothy R Smith; David A Reardon; Michael A Mooney Journal: Neurooncol Adv Date: 2022-06-24
Authors: Evi J van Kempen; Max Post; Manoj Mannil; Benno Kusters; Mark Ter Laan; Frederick J A Meijer; Dylan J H A Henssen Journal: Cancers (Basel) Date: 2021-05-26 Impact factor: 6.639
Authors: Felix Corr; Dustin Grimm; Benjamin Saß; Mirza Pojskić; Jörg W Bartsch; Barbara Carl; Christopher Nimsky; Miriam H A Bopp Journal: J Pers Med Date: 2022-03-04