Jingtao Wang1,2, Xuejun Zheng3, Jinling Zhang4, Hao Xue5, Lijie Wang1,2, Rui Jing6, Shuo Chen7, Fengyuan Che8, Xueyuan Heng8, Gang Li9, Fuzhong Xue10,11. 1. Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, 44 Wenhuaxi Road, Jinan, 250012, Shandong, China. 2. Institute for Medical Dataology, Shandong University, 12550 Erhuandong Road, Jinan, 250002, Shandong, China. 3. Department of Radiology, The Linyi People's Hospital, Shandong University, 27 Jiefang Road, Linyi, 276000, Shandong, China. 4. Cancer Center & The Research Center Of Function Image on Brain Tumor, The Linyi People's Hospital, Shandong University, 27 Jiefang Road, Linyi, 276000, Shandong, China. 5. Department of Neurosurgery, Qilu Hospital of Shandong University, 107 Wenhuaxi Road, Jinan, 250012, Shandong, China. 6. Department of Radiology, Second Hospital of Shandong University, 247 Beiyuan Road, Jinan, 250000, Shandong, China. 7. Division of Biostatistics and Bioinformatics, Maryland Psychiatric Research Center, Department of Psychiatry, University of Maryland School of Medicine, 55 Wade Avenue, Baltimore, MD, 20742, USA. 8. Neurology Department & The Research Center of Function Image on Brain Tumor, The Linyi People's Hospital, Shandong University, 27 Jiefang Road, Linyi, 276000, Shandong, China. 9. Department of Neurosurgery, Qilu Hospital of Shandong University, 107 Wenhuaxi Road, Jinan, 250012, Shandong, China. ligangqiluhospital@163.com. 10. Department of Biostatistics, School of Public Health, Cheeloo College of Medicine, Shandong University, 44 Wenhuaxi Road, Jinan, 250012, Shandong, China. xuefzh@sdu.edu.cn. 11. Institute for Medical Dataology, Shandong University, 12550 Erhuandong Road, Jinan, 250002, Shandong, China. xuefzh@sdu.edu.cn.
Abstract
OBJECTIVES: The aim of this study was to develop and validate a radiomics signature for predicting survival and chemotherapeutic benefits of patients with lower-grade gliomas (LGG). METHODS: Radiomics features were extracted from precontrast axial fluid-attenuated inversion recovery (FLAIR) and contrast-enhanced axial T-1 weighted (CE-T1-w) sequence. Lasso Cox regression model was used for feature selection and radiomics signature building. The radiomics signature was developed in a primary cohort that consisted of 149 LGG patients and was then validated on an entirely new validation cohort that contained 66 LGG patients. A radiomics nomogram for the prediction of OS was established by adding the radiomics to clinicopathologic nomogram which developed with clinical data. RESULTS: A radiomics signature derived from joint CE-T1-w and FLAIR images showed better prognostic performance (C-index, 0.798) than signatures derived from CE-T1-w (C-index, 0.744) or FLAIR (C-index, 0.736) sequences alone. Multivariable Cox regression revealed that the radiomics signature was an independent prognostic factor. One radiomics nomogram integrated the radiomics signature from joint CE-T1-w and FLAIR sequences with the clinicopathologic nomogram outperformed the clinicopathologic nomogram based on clinicopathologic data alone in predicting OS of LGG (C-index, 0.821 vs. 0.692; p < 0.001). Further analysis revealed that patients with higher radiomics signature were prone to benefit from chemotherapy. CONCLUSIONS: The radiomics signature was independent with clinicopathologic data and was a noninvasive pretreatment predictor for LGG patients' survival. Moreover, it could predict which patients with LGG benefit from chemotherapy. KEY POINTS: • A radiomics signature derived from joint CE-T1-w and FLAIR sequences showed better prognostic performance than signatures derived from either single imaging modality. • The radiomics signature is an independent prognostic factor and outperformed clinicopathologic features in predicting overall survival of LGG patients. • The radiomics signature could help preoperatively identify LGG patients who may benefit from chemotherapy.
OBJECTIVES: The aim of this study was to develop and validate a radiomics signature for predicting survival and chemotherapeutic benefits of patients with lower-grade gliomas (LGG). METHODS: Radiomics features were extracted from precontrast axial fluid-attenuated inversion recovery (FLAIR) and contrast-enhanced axial T-1 weighted (CE-T1-w) sequence. Lasso Cox regression model was used for feature selection and radiomics signature building. The radiomics signature was developed in a primary cohort that consisted of 149 LGG patients and was then validated on an entirely new validation cohort that contained 66 LGG patients. A radiomics nomogram for the prediction of OS was established by adding the radiomics to clinicopathologic nomogram which developed with clinical data. RESULTS: A radiomics signature derived from joint CE-T1-w and FLAIR images showed better prognostic performance (C-index, 0.798) than signatures derived from CE-T1-w (C-index, 0.744) or FLAIR (C-index, 0.736) sequences alone. Multivariable Cox regression revealed that the radiomics signature was an independent prognostic factor. One radiomics nomogram integrated the radiomics signature from joint CE-T1-w and FLAIR sequences with the clinicopathologic nomogram outperformed the clinicopathologic nomogram based on clinicopathologic data alone in predicting OS of LGG (C-index, 0.821 vs. 0.692; p < 0.001). Further analysis revealed that patients with higher radiomics signature were prone to benefit from chemotherapy. CONCLUSIONS: The radiomics signature was independent with clinicopathologic data and was a noninvasive pretreatment predictor for LGG patients' survival. Moreover, it could predict which patients with LGG benefit from chemotherapy. KEY POINTS: • A radiomics signature derived from joint CE-T1-w and FLAIR sequences showed better prognostic performance than signatures derived from either single imaging modality. • The radiomics signature is an independent prognostic factor and outperformed clinicopathologic features in predicting overall survival of LGG patients. • The radiomics signature could help preoperatively identify LGG patients who may benefit from chemotherapy.
Entities:
Keywords:
Glioma; Magnetic resonance imaging; Nomograms; Prognosis; Radiomics
Authors: Michael Weller; Martin van den Bent; Jörg C Tonn; Roger Stupp; Matthias Preusser; Elizabeth Cohen-Jonathan-Moyal; Roger Henriksson; Emilie Le Rhun; Carmen Balana; Olivier Chinot; Martin Bendszus; Jaap C Reijneveld; Frederick Dhermain; Pim French; Christine Marosi; Colin Watts; Ingela Oberg; Geoffrey Pilkington; Brigitta G Baumert; Martin J B Taphoorn; Monika Hegi; Manfred Westphal; Guido Reifenberger; Riccardo Soffietti; Wolfgang Wick Journal: Lancet Oncol Date: 2017-05-05 Impact factor: 41.316
Authors: M J van den Bent; J S Wefel; D Schiff; M J B Taphoorn; K Jaeckle; L Junck; T Armstrong; A Choucair; A D Waldman; T Gorlia; M Chamberlain; B G Baumert; M A Vogelbaum; D R Macdonald; D A Reardon; P Y Wen; S M Chang; A H Jacobs Journal: Lancet Oncol Date: 2011-04-05 Impact factor: 41.316
Authors: André N Abrunhosa-Branquinho; Raquel Bar-Deroma; Sandra Collette; Enrico Clementel; Yan Liu; Coen W Hurkmans; Loïc Feuvret; Karen Van Beek; Martin van den Bent; Brigitta G Baumert; Damien C Weber Journal: Radiother Oncol Date: 2018-03-29 Impact factor: 6.280
Authors: C Houillier; X Wang; G Kaloshi; K Mokhtari; R Guillevin; J Laffaire; S Paris; B Boisselier; A Idbaih; F Laigle-Donadey; K Hoang-Xuan; M Sanson; J-Y Delattre Journal: Neurology Date: 2010-10-26 Impact factor: 11.800
Authors: Brigitta G Baumert; Monika E Hegi; Martin J van den Bent; Andreas von Deimling; Thierry Gorlia; Khê Hoang-Xuan; Alba A Brandes; Guy Kantor; Martin J B Taphoorn; Mohamed Ben Hassel; Christian Hartmann; Gail Ryan; David Capper; Johan M Kros; Sebastian Kurscheid; Wolfgang Wick; Roelien Enting; Michele Reni; Brian Thiessen; Frederic Dhermain; Jacoline E Bromberg; Loic Feuvret; Jaap C Reijneveld; Olivier Chinot; Johanna M M Gijtenbeek; John P Rossiter; Nicolas Dif; Carmen Balana; Jose Bravo-Marques; Paul M Clement; Christine Marosi; Tzahala Tzuk-Shina; Robert A Nordal; Jeremy Rees; Denis Lacombe; Warren P Mason; Roger Stupp Journal: Lancet Oncol Date: 2016-09-27 Impact factor: 54.433