BACKGROUND: Lesion size in fluid attenuation inversion recovery (FLAIR) images is an important clinical parameter for patient assessment and follow-up. Although manual delineation of lesion areas considered as ground truth, it is time-consuming, highly user-dependent and difficult to perform in areas of indistinct borders. In this study, an automatic methodology for FLAIR lesion segmentation is proposed, and its application in patients with brain tumors undergoing therapy; and in patients following stroke is demonstrated. MATERIALS AND METHODS: FLAIR lesion segmentation was performed in 57 magnetic resonance imaging (MRI) data sets obtained from 44 patients: 28 patients with primary brain tumors; 5 patients with recurrent-progressive glioblastoma (rGB) who were scanned longitudinally during anti-angiogenic therapy (18 MRI scans); and 11 patients following ischemic stroke. RESULTS: FLAIR lesion segmentation was obtained in all patients. When compared to manual delineation, a high visual similarity was observed, with an absolute relative volume difference of 16.80% and 20.96% and a volumetric overlap error of 24.87% and 27.50% obtained for two raters: accepted values for automatic methods. Quantitative measurements of the segmented lesion volumes were in line with qualitative radiological assessment in four patients who received anti-anogiogenic drugs. In stroke patients the proposed methodology enabled identification of the ischemic lesion and differentiation from other FLAIR hyperintense areas, such as pre-existing disease. CONCLUSION: This study proposed a replicable methodology for FLAIR lesion detection and quantification and for discrimination between lesion of interest and pre-existing disease. Results from this study show the wide clinical applications of this methodology in research and clinical practice.
BACKGROUND: Lesion size in fluid attenuation inversion recovery (FLAIR) images is an important clinical parameter for patient assessment and follow-up. Although manual delineation of lesion areas considered as ground truth, it is time-consuming, highly user-dependent and difficult to perform in areas of indistinct borders. In this study, an automatic methodology for FLAIR lesion segmentation is proposed, and its application in patients with brain tumors undergoing therapy; and in patients following stroke is demonstrated. MATERIALS AND METHODS: FLAIR lesion segmentation was performed in 57 magnetic resonance imaging (MRI) data sets obtained from 44 patients: 28 patients with primary brain tumors; 5 patients with recurrent-progressive glioblastoma (rGB) who were scanned longitudinally during anti-angiogenic therapy (18 MRI scans); and 11 patients following ischemic stroke. RESULTS: FLAIR lesion segmentation was obtained in all patients. When compared to manual delineation, a high visual similarity was observed, with an absolute relative volume difference of 16.80% and 20.96% and a volumetric overlap error of 24.87% and 27.50% obtained for two raters: accepted values for automatic methods. Quantitative measurements of the segmented lesion volumes were in line with qualitative radiological assessment in four patients who received anti-anogiogenic drugs. In strokepatients the proposed methodology enabled identification of the ischemic lesion and differentiation from other FLAIR hyperintense areas, such as pre-existing disease. CONCLUSION: This study proposed a replicable methodology for FLAIR lesion detection and quantification and for discrimination between lesion of interest and pre-existing disease. Results from this study show the wide clinical applications of this methodology in research and clinical practice.
Authors: Bjoern H Menze; Heinz Handels; Mauricio Reyes; Oskar Maier; Janina von der Gablentz; Levin Ḧani; Mattias P Heinrich; Matthias Liebrand; Stefan Winzeck; Abdul Basit; Paul Bentley; Liang Chen; Daan Christiaens; Francis Dutil; Karl Egger; Chaolu Feng; Ben Glocker; Michael Götz; Tom Haeck; Hanna-Leena Halme; Mohammad Havaei; Khan M Iftekharuddin; Pierre-Marc Jodoin; Konstantinos Kamnitsas; Elias Kellner; Antti Korvenoja; Hugo Larochelle; Christian Ledig; Jia-Hong Lee; Frederik Maes; Qaiser Mahmood; Klaus H Maier-Hein; Richard McKinley; John Muschelli; Chris Pal; Linmin Pei; Janaki Raman Rangarajan; Syed M S Reza; David Robben; Daniel Rueckert; Eero Salli; Paul Suetens; Ching-Wei Wang; Matthias Wilms; Jan S Kirschke; Ulrike M Kr Amer; Thomas F Münte; Peter Schramm; Roland Wiest Journal: Med Image Anal Date: 2016-07-21 Impact factor: 8.545
Authors: Mary T Joy; Einor Ben Assayag; Dalia Shabashov-Stone; Sigal Liraz-Zaltsman; Jose Mazzitelli; Marcela Arenas; Nora Abduljawad; Efrat Kliper; Amos D Korczyn; Nikita S Thareja; Efrat L Kesner; Miou Zhou; Shan Huang; Tawnie K Silva; Noomi Katz; Natan M Bornstein; Alcino J Silva; Esther Shohami; S Thomas Carmichael Journal: Cell Date: 2019-02-21 Impact factor: 66.850
Authors: Dazhou Guo; Julius Fridriksson; Paul Fillmore; Christopher Rorden; Hongkai Yu; Kang Zheng; Song Wang Journal: BMC Med Imaging Date: 2015-10-30 Impact factor: 1.930