Yiming Li1, Dong Wei2, Xing Liu3, Xing Fan3, Kai Wang4, Shaowu Li3, Zhong Zhang1, Kai Ma2, Tianyi Qian5, Tao Jiang1,3,6,7,8, Yefeng Zheng9, Yinyan Wang10. 1. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 South Fourth Ring West Road, Beijing, 100070, China. 2. Tencent Jarvis Lab, No, 10000 Shennan Avenue, Shenzhen, 518057, China. 3. Beijing Neurosurgical Institute, Capital Medical University, Beijing, China. 4. Department of Nuclear Medicine, Beijing Tiantan Hospital, Capital Medical University, Beijing, China. 5. Tencent HealthCare Co. Ltd, Shenzhen, China. 6. Center of Brain Tumor, Beijing Institute for Brain Disorders, Beijing, China. 7. China National Clinical Research Center for Neurological Diseases, Beijing, China. 8. Chinese Glioma Genome Atlas Network (CGGA) and Asian Glioma Genome Atlas Network (AGGA), Beijing, China. 9. Tencent Jarvis Lab, No, 10000 Shennan Avenue, Shenzhen, 518057, China. yefengzheng@tencent.com. 10. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, No. 119 South Fourth Ring West Road, Beijing, 100070, China. wangyinyan@bjtth.org.
Abstract
OBJECTIVES: The molecular subtyping of diffuse gliomas is important. The aim of this study was to establish predictive models based on preoperative multiparametric MRI. METHODS: A total of 1016 diffuse glioma patients were retrospectively collected from Beijing Tiantan Hospital. Patients were randomly divided into the training (n = 780) and validation (n = 236) sets. According to the 2016 WHO classification, diffuse gliomas can be classified into four binary classification tasks (tasks I-IV). Predictive models based on radiomics and deep convolutional neural network (DCNN) were developed respectively, and their performances were compared with receiver operating characteristic (ROC) curves. Additionally, the radiomics and DCNN features were visualized and compared with the t-distributed stochastic neighbor embedding technique and Spearman's correlation test. RESULTS: In the training set, areas under the curves (AUCs) of the DCNN models (ranging from 0.99 to 1.00) outperformed the radiomics models in all tasks, and the accuracies of the DCNN models (ranging from 0.90 to 0.94) outperformed the radiomics models in tasks I, II, and III. In the independent validation set, the accuracies of the DCNN models outperformed the radiomics models in all tasks (0.74-0.83), and the AUCs of the DCNN models (0.85-0.89) outperformed the radiomics models in tasks I, II, and III. DCNN features demonstrated more superior discriminative capability than the radiomics features in feature visualization analysis, and their general correlations were weak. CONCLUSIONS: Both the radiomics and DCNN models could preoperatively predict the molecular subtypes of diffuse gliomas, and the latter performed better in most circumstances. KEY POINTS: • The molecular subtypes of diffuse gliomas could be predicted with MRI. • Deep learning features tend to outperform radiomics features in large cohorts. • The correlation between the radiomics features and DCNN features was low.
OBJECTIVES: The molecular subtyping of diffuse gliomas is important. The aim of this study was to establish predictive models based on preoperative multiparametric MRI. METHODS: A total of 1016 diffuse glioma patients were retrospectively collected from Beijing Tiantan Hospital. Patients were randomly divided into the training (n = 780) and validation (n = 236) sets. According to the 2016 WHO classification, diffuse gliomas can be classified into four binary classification tasks (tasks I-IV). Predictive models based on radiomics and deep convolutional neural network (DCNN) were developed respectively, and their performances were compared with receiver operating characteristic (ROC) curves. Additionally, the radiomics and DCNN features were visualized and compared with the t-distributed stochastic neighbor embedding technique and Spearman's correlation test. RESULTS: In the training set, areas under the curves (AUCs) of the DCNN models (ranging from 0.99 to 1.00) outperformed the radiomics models in all tasks, and the accuracies of the DCNN models (ranging from 0.90 to 0.94) outperformed the radiomics models in tasks I, II, and III. In the independent validation set, the accuracies of the DCNN models outperformed the radiomics models in all tasks (0.74-0.83), and the AUCs of the DCNN models (0.85-0.89) outperformed the radiomics models in tasks I, II, and III. DCNN features demonstrated more superior discriminative capability than the radiomics features in feature visualization analysis, and their general correlations were weak. CONCLUSIONS: Both the radiomics and DCNN models could preoperatively predict the molecular subtypes of diffuse gliomas, and the latter performed better in most circumstances. KEY POINTS: • The molecular subtypes of diffuse gliomas could be predicted with MRI. • Deep learning features tend to outperform radiomics features in large cohorts. • The correlation between the radiomics features and DCNN features was low.
Authors: Nicholas J Potter; Karl Mund; Jacqueline M Andreozzi; Jonathan G Li; Chihray Liu; Guanghua Yan Journal: Med Phys Date: 2020-08-13 Impact factor: 4.071
Authors: Kyaw L Aung; Sandra E Fischer; Robert E Denroche; Gun-Ho Jang; Anna Dodd; Sean Creighton; Bernadette Southwood; Sheng-Ben Liang; Dianne Chadwick; Amy Zhang; Grainne M O'Kane; Hamzeh Albaba; Shari Moura; Robert C Grant; Jessica K Miller; Faridah Mbabaali; Danielle Pasternack; Ilinca M Lungu; John M S Bartlett; Sangeet Ghai; Mathieu Lemire; Spring Holter; Ashton A Connor; Richard A Moffitt; Jen Jen Yeh; Lee Timms; Paul M Krzyzanowski; Neesha Dhani; David Hedley; Faiyaz Notta; Julie M Wilson; Malcolm J Moore; Steven Gallinger; Jennifer J Knox Journal: Clin Cancer Res Date: 2017-12-29 Impact factor: 12.531
Authors: Wenya Linda Bi; Ahmed Hosny; Matthew B Schabath; Maryellen L Giger; Nicolai J Birkbak; Alireza Mehrtash; Tavis Allison; Omar Arnaout; Christopher Abbosh; Ian F Dunn; Raymond H Mak; Rulla M Tamimi; Clare M Tempany; Charles Swanton; Udo Hoffmann; Lawrence H Schwartz; Robert J Gillies; Raymond Y Huang; Hugo J W L Aerts Journal: CA Cancer J Clin Date: 2019-02-05 Impact factor: 508.702