Zhizheng Zhuo1, Liying Qu1, Peng Zhang2, Liwei Zhang3, Yaou Liu4, Yunyun Duan1, Dan Cheng1, Xiaolu Xu1, Ting Sun1, Jinli Ding1, Cong Xie1, Xing Liu5, Sven Haller6, Frederik Barkhof7,8. 1. Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China. 2. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, 10070, China. 3. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, 10070, China. zlwtt@aliyun.com. 4. Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100070, China. liuyaou@bjtth.org. 5. Department of Pathology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 10070, China. 6. Department of Imaging and Medical Informatics, University Hospitals of Geneva and Faculty of Medicine of the University of Geneva, Geneva, Switzerland. 7. UCL Institutes of Neurology and Healthcare Engineering, London, UK. 8. Department of Radiology & Nuclear Medicine, Amsterdam University Medical Centers, Amsterdam, The Netherlands.
Abstract
PURPOSE: H3K27M-mutant associated brainstem glioma (BSG) carries a very poor prognosis. We aimed to predict H3K27M mutation status by amide proton transfer-weighted (APTw) imaging and radiomic features. METHODS: Eighty-one BSG patients with APTw imaging at 3T MR and known H3K27M status were retrospectively studied. APTw values (mean, median, and max) and radiomic features within manually delineated 3D tumor masks were extracted. Comparison of APTw measures between H3K27M-mutant and wildtype groups was conducted by two-sample Student's T/Mann-Whitney U test and receiver operating characteristic curve (ROC) analysis. H3K27M-mutant prediction using APTw-derived radiomics was conducted using a machine learning algorithm (support vector machine) in randomly selected train (n = 64) and test (n = 17) sets. Sensitivity analysis with additional random splits of train and test sets, 2D tumor masks, and other classifiers were conducted. Finally, a prospective cohort including 29 BSG patients was acquired for validation of the radiomics algorithm. RESULTS: BSG patients with H3K27M-mutant were younger and had higher max APTw values than those with wildtype. APTw-derived radiomic measures reflecting tumor heterogeneity could predict H3K27M mutation status with an accuracy of 0.88, sensitivity of 0.92, and specificity of 0.80 in the test set. Sensitivity analysis confirmed the predictive ability (accuracy range: 0.71-0.94). In the independent prospective validation cohort, the algorithm reached an accuracy of 0.86, sensitivity of 0.88, and specificity of 0.85 for predicting H3K27M-mutation status. CONCLUSION: BSG patients with H3K27M-mutant had higher max APTw values than those with wildtype. APTw-derived radiomics could accurately predict a H3K27M-mutant status in BSG patients.
PURPOSE: H3K27M-mutant associated brainstem glioma (BSG) carries a very poor prognosis. We aimed to predict H3K27M mutation status by amide proton transfer-weighted (APTw) imaging and radiomic features. METHODS: Eighty-one BSG patients with APTw imaging at 3T MR and known H3K27M status were retrospectively studied. APTw values (mean, median, and max) and radiomic features within manually delineated 3D tumor masks were extracted. Comparison of APTw measures between H3K27M-mutant and wildtype groups was conducted by two-sample Student's T/Mann-Whitney U test and receiver operating characteristic curve (ROC) analysis. H3K27M-mutant prediction using APTw-derived radiomics was conducted using a machine learning algorithm (support vector machine) in randomly selected train (n = 64) and test (n = 17) sets. Sensitivity analysis with additional random splits of train and test sets, 2D tumor masks, and other classifiers were conducted. Finally, a prospective cohort including 29 BSG patients was acquired for validation of the radiomics algorithm. RESULTS: BSG patients with H3K27M-mutant were younger and had higher max APTw values than those with wildtype. APTw-derived radiomic measures reflecting tumor heterogeneity could predict H3K27M mutation status with an accuracy of 0.88, sensitivity of 0.92, and specificity of 0.80 in the test set. Sensitivity analysis confirmed the predictive ability (accuracy range: 0.71-0.94). In the independent prospective validation cohort, the algorithm reached an accuracy of 0.86, sensitivity of 0.88, and specificity of 0.85 for predicting H3K27M-mutation status. CONCLUSION: BSG patients with H3K27M-mutant had higher max APTw values than those with wildtype. APTw-derived radiomics could accurately predict a H3K27M-mutant status in BSG patients.
Authors: Jinyuan Zhou; He Zhu; Michael Lim; Lindsay Blair; Alfredo Quinones-Hinojosa; Steven A Messina; Charles G Eberhart; Martin G Pomper; John Laterra; Peter B Barker; Peter C M van Zijl; Jaishri O Blakeley Journal: J Magn Reson Imaging Date: 2013-02-25 Impact factor: 4.813
Authors: Jon D Larson; Lawryn H Kasper; Barbara S Paugh; Hongjian Jin; Gang Wu; Chang-Hyuk Kwon; Yiping Fan; Timothy I Shaw; André B Silveira; Chunxu Qu; Raymond Xu; Xiaoyan Zhu; Junyuan Zhang; Helen R Russell; Jennifer L Peters; David Finkelstein; Beisi Xu; Tong Lin; Christopher L Tinkle; Zoltan Patay; Arzu Onar-Thomas; Stanley B Pounds; Peter J McKinnon; David W Ellison; Jinghui Zhang; Suzanne J Baker Journal: Cancer Cell Date: 2018-12-27 Impact factor: 31.743
Authors: Hamid Nikbakht; Eshini Panditharatna; Leonie G Mikael; Rui Li; Tenzin Gayden; Matthew Osmond; Cheng-Ying Ho; Madhuri Kambhampati; Eugene I Hwang; Damien Faury; Alan Siu; Simon Papillon-Cavanagh; Denise Bechet; Keith L Ligon; Benjamin Ellezam; Wendy J Ingram; Caedyn Stinson; Andrew S Moore; Katherine E Warren; Jason Karamchandani; Roger J Packer; Nada Jabado; Jacek Majewski; Javad Nazarian Journal: Nat Commun Date: 2016-04-06 Impact factor: 14.919
Authors: Jinyuan Zhou; Moritz Zaiss; Linda Knutsson; Phillip Zhe Sun; Sung Soo Ahn; Silvio Aime; Peter Bachert; Jaishri O Blakeley; Kejia Cai; Michael A Chappell; Min Chen; Daniel F Gochberg; Steffen Goerke; Hye-Young Heo; Shanshan Jiang; Tao Jin; Seong-Gi Kim; John Laterra; Daniel Paech; Mark D Pagel; Ji Eun Park; Ravinder Reddy; Akihiko Sakata; Sabine Sartoretti-Schefer; A Dean Sherry; Seth A Smith; Greg J Stanisz; Pia C Sundgren; Osamu Togao; Moriel Vandsburger; Zhibo Wen; Yin Wu; Yi Zhang; Wenzhen Zhu; Zhongliang Zu; Peter C M van Zijl Journal: Magn Reson Med Date: 2022-04-22 Impact factor: 3.737
Authors: Ming Zhu; Sijia Li; Yu Kuang; Virginia B Hill; Amy B Heimberger; Lijie Zhai; Shengjie Zhai Journal: Front Oncol Date: 2022-08-02 Impact factor: 5.738