FLAIR lesion segmentation: Application in patients with brain tumors and acute ischemic stroke
FLAIR lesion segmentation: Application in patients with brain tumors and acute ischemic stroke
复制标题
DOI：
10.1016/j.ejrad.2013.05.029
复制
发表时间：
2013-09-01
影响因子：
3.3
通讯作者：
Ben Bashat, Dafna
中科院分区：
文献类型：
--
作者：
Artzi, Moran;Aizenstein, Orna;Ben Bashat, Dafna
背景资料：液体衰减反转恢复（FLAIR）图像中的病变大小是患者评估和随访的重要临床参数。尽管病变区域的手动描绘被认为是基础事实，但它耗时，高度依赖于用户，并且难以在边界模糊的区域中执行。在这项研究中，提出了一种自动的方法FLAIR病变分割，并在脑肿瘤患者接受治疗的应用，并在患者中风后demonstrated.Materials和方法：FLAIR病变分割进行了57磁共振成像（MRI）数据集从44例患者：28例原发性脑肿瘤; 5例复发-进展性胶质母细胞瘤（rGB）患者在抗血管生成治疗期间进行纵向扫描（18次MRI扫描）; 11例缺血性卒中患者。与手动描绘相比，观察到高度的视觉相似性，绝对相对体积差异为16.80%和20.96%，两名评分员获得的体积重叠误差为24.87%和27.50%：自动方法的可接受值。在接受抗血管生成药物的4例患者中，分段病变体积的定量测量与定性放射学评估一致。在中风患者中，所提出的方法使识别缺血性病变和分化从其他FLAIR高信号区，如预先存在的diseases.Conclusion：本研究提出了一种可复制的方法，FLAIR病变检测和量化和病变之间的利益和预先存在的疾病的歧视。本研究的结果表明，该方法在研究和临床实践中具有广泛的临床应用。(C)由Elsevier爱尔兰有限公司出版。
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. (C) 2013 Published by Elsevier Ireland Ltd.