Department of Neurosurgery, Tufts Medical Center, Boston, Massachusetts, USA.
Department of Neurosurgery, Tufts Medical Center, Boston, Massachusetts, USA
J Neurointerv Surg. 2021 Aug;13(8):755-761. doi: 10.1136/neurintsurg-2020-016808. Epub 2020 Nov 6.
Morphological differences between ruptured and unruptured cerebral aneurysms represent a focus of neuroimaging researchfor understanding the mechanisms of aneurysmal rupture. We evaluated the performance of Radiomics derived morphological features, recently proposed for rupture status classification, against automatically measured shape and size features previously established in the literature.
353 aneurysms (123 ruptured) from three-dimensional rotational catheter angiography (3DRA) datasets were analyzed. Based on a literature review, 13 Radiomics and 13 established morphological descriptors were automatically extracted per aneurysm, and evaluated for rupture status prediction using univariate and multivariate statistical analysis, yielding an area under the curve (AUC) metric of the receiver operating characteristic.
Validation of overlapping descriptors for size/volume using both methods were highly correlated (p<0.0001, =0.99). Univariate analysis selected AspectRatio (p<0.0001, AUC=0.75), Non-sphericity Index (p<0.0001, AUC=0.75), Height/Width (p<0.0001, AUC=0.73), and SizeRatio (p<0.0001, AUC=0.73) as best among established descriptors, and Elongation (p<0.0001, AUC=0.71) and Flatness (p<0.0001, AUC=0.72) among Radiomics features. Radiomics Elongation correlated best with established Height/Width ( =0.52), whereas Radiomics Flatness correlated best with Ellipticity Index ( =0.54). Radiomics Sphericity correlated best with Undulation Index ( =0.65). Best Radiomics performers, Elongation and Flatness, were highly correlated descriptors (p<0.0001, =0.75). In multivariate analysis, established descriptors (Height/Width, SizeRatio, Ellipticity Index; AUC=0.79) outperformed Radiomics features (Elongation, Maximum3Ddiameter; AUC=0.75).
Although recently introduced Radiomics analysis for aneurysm shape and size evaluation has the advantage of being an efficient operator independent methodology, it currently offers inferior rupture status discriminant performance compared with established descriptors. Future research is needed to extend the current Radiomics feature set to better capture aneurysm shape information.
破裂和未破裂脑动脉瘤之间的形态学差异是神经影像学研究的一个重点，旨在了解动脉瘤破裂的机制。我们评估了最近提出的用于破裂状态分类的放射组学形态特征的性能，以对抗以前在文献中建立的自动测量的形状和大小特征。
对来自三维旋转导管血管造影（3DRA）数据集的 353 个动脉瘤（123 个破裂）进行了分析。根据文献综述，每个动脉瘤自动提取 13 个放射组学和 13 个已建立的形态描述符，并使用单变量和多变量统计分析进行破裂状态预测，得出受试者工作特征的曲线下面积（AUC）度量。
使用两种方法验证重叠描述符的大小/体积，相关性很高（p<0.0001， =0.99）。单变量分析选择了纵横比（p<0.0001，AUC=0.75）、非球形指数（p<0.0001，AUC=0.75）、高度/宽度（p<0.0001，AUC=0.73）和大小比（p<0.0001，AUC=0.73）作为最佳的已建立描述符，以及伸长率（p<0.0001，AUC=0.71）和扁平度（p<0.0001，AUC=0.72）作为放射组学特征。放射组学伸长率与已建立的高度/宽度相关性最好（ =0.52），而放射组学扁平度与椭圆度指数相关性最好（ =0.54）。放射组学球形度与波动指数相关性最好（ =0.65）。最佳放射组学表现者，伸长率和平坦度，是高度相关的描述符（p<0.0001， =0.75）。在多变量分析中，已建立的描述符（高度/宽度、大小比、椭圆度指数；AUC=0.79）优于放射组学特征（伸长率、最大 3D 直径；AUC=0.75）。
尽管最近引入的用于评估动脉瘤形状和大小的放射组学分析具有高效、操作员独立的方法的优势，但与已建立的描述符相比，它目前提供的破裂状态判别性能较差。需要进一步研究以扩展当前的放射组学特征集，以更好地捕捉动脉瘤的形状信息。
