Yaou Liu1,2,3,4, Di Dong5,6, Liwen Zhang5,6, Yali Zang5,6, Yunyun Duan7,8, Xiaolu Qiu9, Jing Huang9, Huiqing Dong10, Frederik Barkhof11,12, Chaoen Hu5,6, Mengjie Fang5,6, Jie Tian13,14, Kuncheng Li7,9. 1. Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100050, People's Republic of China. asiaeurope80@gmail.com. 2. Tiantan Image Research Center, China National Clinical Research Center for Neurological Diseases, Beijing, 100050, People's Republic of China. asiaeurope80@gmail.com. 3. Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, 1007 MB, Amsterdam, The Netherlands. asiaeurope80@gmail.com. 4. Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, People's Republic of China. asiaeurope80@gmail.com. 5. CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China. 6. University of Chinese Academy of Sciences, Beijing, China. 7. Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100050, People's Republic of China. 8. Tiantan Image Research Center, China National Clinical Research Center for Neurological Diseases, Beijing, 100050, People's Republic of China. 9. Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, People's Republic of China. 10. Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, People's Republic of China. 11. Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, 1007 MB, Amsterdam, The Netherlands. 12. Institutes of Neurology and Healthcare Engineering, UCL, London, UK. 13. CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China. tian@ieee.org. 14. University of Chinese Academy of Sciences, Beijing, China. tian@ieee.org.
Abstract
OBJECTIVE: To develop and validate an individual radiomics nomogram for differential diagnosis between multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD). METHODS: We retrospectively collected 67 MS and 68 NMOSD with spinal cord lesions as a primary cohort and prospectively recruited 28 MS and 26 NMOSD patients as a validation cohort. Radiomic features were extracted from the spinal cord lesions. A prediction model for differentiating MS and NMOSD was built by combining the radiomic features with several clinical and routine MRI measurements. The performance of the model was assessed with respect to its calibration plot and clinical discrimination in the primary and validation cohorts. RESULTS: Nine radiomics features extracted from an initial set of 485, predominantly reflecting lesion heterogeneity, combined with lesion length, patient sex, and EDSS, were selected to build the model for differentiating MS and NMOSD. The areas under the ROC curves (AUC) for differentiating the two diseases were 0.8808 and 0.7115, for the primary and validation cohort, respectively. This model demonstrated good calibration (C-index was 0.906 and 0.802 in primary and validation cohort). CONCLUSIONS: A validated nomogram that incorporates the radiomic signature of spinal cord lesions, as well as cord lesion length, sex, and EDSS score, can usefully differentiate MS and NMOSD. KEY POINTS: • Radiomic features of spinal cord lesions in MS and NMOSD were different. • Radiomic signatures can capture pathological alterations and help differentiate MS and NMOSD.
OBJECTIVE: To develop and validate an individual radiomics nomogram for differential diagnosis between multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD). METHODS: We retrospectively collected 67 MS and 68 NMOSD with spinal cord lesions as a primary cohort and prospectively recruited 28 MS and 26 NMOSD patients as a validation cohort. Radiomic features were extracted from the spinal cord lesions. A prediction model for differentiating MS and NMOSD was built by combining the radiomic features with several clinical and routine MRI measurements. The performance of the model was assessed with respect to its calibration plot and clinical discrimination in the primary and validation cohorts. RESULTS: Nine radiomics features extracted from an initial set of 485, predominantly reflecting lesion heterogeneity, combined with lesion length, patient sex, and EDSS, were selected to build the model for differentiating MS and NMOSD. The areas under the ROC curves (AUC) for differentiating the two diseases were 0.8808 and 0.7115, for the primary and validation cohort, respectively. This model demonstrated good calibration (C-index was 0.906 and 0.802 in primary and validation cohort). CONCLUSIONS: A validated nomogram that incorporates the radiomic signature of spinal cord lesions, as well as cord lesion length, sex, and EDSS score, can usefully differentiate MS and NMOSD. KEY POINTS: • Radiomic features of spinal cord lesions in MS and NMOSD were different. • Radiomic signatures can capture pathological alterations and help differentiate MS and NMOSD.
Authors: Massimo Filippi; Maria A Rocca; Frederik Barkhof; Wolfgang Brück; Jacqueline T Chen; Giancarlo Comi; Gabriele DeLuca; Nicola De Stefano; Bradley J Erickson; Nikos Evangelou; Franz Fazekas; Jeroen J G Geurts; Claudia Lucchinetti; David H Miller; Daniel Pelletier; Bogdan F Gh Popescu; Hans Lassmann Journal: Lancet Neurol Date: 2012-03-19 Impact factor: 44.182
Authors: J Shimizu; Y Hatanaka; M Hasegawa; A Iwata; I Sugimoto; H Date; J Goto; T Shimizu; M Takatsu; Y Sakurai; H Nakase; Y Uesaka; H Hashida; K Hashimoto; T Komiya; S Tsuji Journal: Neurology Date: 2010-09-08 Impact factor: 9.910
Authors: Philippe Lambin; Emmanuel Rios-Velazquez; Ralph Leijenaar; Sara Carvalho; Ruud G P M van Stiphout; Patrick Granton; Catharina M L Zegers; Robert Gillies; Ronald Boellard; André Dekker; Hugo J W L Aerts Journal: Eur J Cancer Date: 2012-01-16 Impact factor: 9.162
Authors: Dean M Wingerchuk; Vanda A Lennon; Claudia F Lucchinetti; Sean J Pittock; Brian G Weinshenker Journal: Lancet Neurol Date: 2007-09 Impact factor: 44.182
Authors: Chris H Polman; Stephen C Reingold; Brenda Banwell; Michel Clanet; Jeffrey A Cohen; Massimo Filippi; Kazuo Fujihara; Eva Havrdova; Michael Hutchinson; Ludwig Kappos; Fred D Lublin; Xavier Montalban; Paul O'Connor; Magnhild Sandberg-Wollheim; Alan J Thompson; Emmanuelle Waubant; Brian Weinshenker; Jerry S Wolinsky Journal: Ann Neurol Date: 2011-02 Impact factor: 10.422
Authors: Sven Jarius; Klemens Ruprecht; Brigitte Wildemann; Tania Kuempfel; Marius Ringelstein; Christian Geis; Ingo Kleiter; Christoph Kleinschnitz; Achim Berthele; Johannes Brettschneider; Kerstin Hellwig; Bernhard Hemmer; Ralf A Linker; Florian Lauda; Christoph A Mayer; Hayrettin Tumani; Arthur Melms; Corinna Trebst; Martin Stangel; Martin Marziniak; Frank Hoffmann; Sven Schippling; Jürgen H Faiss; Oliver Neuhaus; Barbara Ettrich; Christian Zentner; Kersten Guthke; Ulrich Hofstadt-van Oy; Reinhard Reuss; Hannah Pellkofer; Ulf Ziemann; Peter Kern; Klaus P Wandinger; Florian Then Bergh; Tobias Boettcher; Stefan Langel; Martin Liebetrau; Paulus S Rommer; Sabine Niehaus; Christoph Münch; Alexander Winkelmann; Uwe K Zettl U; Imke Metz; Christian Veauthier; Jörn P Sieb; Christian Wilke; Hans P Hartung; Orhan Aktas; Friedemann Paul Journal: J Neuroinflammation Date: 2012-01-19 Impact factor: 8.322