Functional Brain Center, The Wohl Institute for Advanced Imaging, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel.
Eur J Radiol. 2013 Feb;82(2):e87-94. doi: 10.1016/j.ejrad.2012.09.001. Epub 2012 Sep 25.
Current methods for evaluation of treatment response in glioblastoma are inaccurate, limited and time-consuming. This study aimed to develop a multi-modal MRI automatic classification method to improve accuracy and efficiency of treatment response assessment in patients with recurrent glioblastoma (GB).
A modification of the k-Nearest-Neighbors (kNN) classification method was developed and applied to 59 longitudinal MR data sets of 13 patients with recurrent GB undergoing bevacizumab (anti-angiogenic) therapy. Changes in the enhancing tumor volume were assessed using the proposed method and compared with Macdonald's criteria and with manual volumetric measurements. The edema-like area was further subclassified into peri- and non-peri-tumoral edema, using both the kNN method and an unsupervised method, to monitor longitudinal changes.
Automatic classification using the modified kNN method was applicable in all scans, even when the tumors were infiltrative with unclear borders. The enhancing tumor volume obtained using the automatic method was highly correlated with manual measurements (N=33, r=0.96, p<0.0001), while standard radiographic assessment based on Macdonald's criteria matched manual delineation and automatic results in only 68% of cases. A graded pattern of tumor infiltration within the edema-like area was revealed by both automatic methods, showing high agreement. All classification results were confirmed by a senior neuro-radiologist and validated using MR spectroscopy.
This study emphasizes the important role of automatic tools based on a multi-modal view of the tissue in monitoring therapy response in patients with high grade gliomas specifically under anti-angiogenic therapy.
目前评估胶质母细胞瘤治疗反应的方法存在不准确性、局限性和耗时等问题。本研究旨在开发一种多模态 MRI 自动分类方法，以提高复发性胶质母细胞瘤（GB）患者治疗反应评估的准确性和效率。
对 13 例接受贝伐单抗（抗血管生成）治疗的复发性 GB 患者的 59 个纵向磁共振数据集进行了研究，对 k 最近邻（kNN）分类方法进行了改进，并将其应用于该研究。采用提出的方法评估增强肿瘤体积的变化，并与 Macdonald 标准和手动体积测量进行比较。进一步使用 kNN 方法和无监督方法将类水肿区域细分为瘤周和非瘤周水肿，以监测纵向变化。
使用改进的 kNN 方法的自动分类在所有扫描中均适用，即使肿瘤浸润边界不清晰。自动方法获得的增强肿瘤体积与手动测量高度相关（N=33，r=0.96，p<0.0001），而基于 Macdonald 标准的标准放射学评估仅在 68%的情况下与手动勾画和自动结果相匹配。两种自动方法均显示出肿瘤在类水肿区域内浸润的分级模式，具有高度一致性。所有分类结果均由一名资深神经放射科医生确认，并通过磁共振波谱进行验证。
本研究强调了基于组织多模态视图的自动工具在监测高级别胶质瘤患者，特别是接受抗血管生成治疗的患者的治疗反应方面的重要作用。
