Cabezas M, Corral J F, Oliver A, Díez Y, Tintoré M, Auger C, Montalban X, Lladó X, Pareto D, Rovira À
From the Section of Neuroradiology, Department of Radiology (M.C., J.F.C., C.A., D.P., À.R.)
Visió per Computador i Robòtica group (M.C., A.O., Y.D., X.L.), University of Girona, Girona, Spain.
AJNR Am J Neuroradiol. 2016 Oct;37(10):1816-1823. doi: 10.3174/ajnr.A4829. Epub 2016 Jun 9.
Detection of disease activity, defined as new/enlarging T2 lesions on brain MR imaging, has been proposed as a biomarker in MS. However, detection of new/enlarging T2 lesions can be hindered by several factors that can be overcome with image subtraction. The purpose of this study was to improve automated detection of new T2 lesions and reduce user interaction to eliminate inter- and intraobserver variability.
Multiparametric brain MR imaging was performed at 2 time points in 36 patients with new T2 lesions. Images were registered by using an affine transformation and the Demons algorithm to obtain a deformation field. After affine registration, images were subtracted and a threshold was applied to obtain a lesion mask, which was then refined by using the deformation field, intensity, and local information. This pipeline was compared with only applying a threshold, and with a state-of-the-art approach relying only on image intensities. To assess improvements, we compared the results of the different pipelines with the expert visual detection.
The multichannel pipeline based on the deformation field obtained a detection Dice similarity coefficient close to 0.70, with a false-positive detection of 17.8% and a true-positive detection of 70.9%. A statistically significant correlation ( = 0.81, value = 2.2688e-09) was found between visual detection and automated detection by using our approach.
The deformation field-based approach proposed in this study for detecting new/enlarging T2 lesions resulted in significantly fewer false-positives while maintaining most true-positives and showed a good correlation with visual detection annotations. This approach could reduce user interaction and inter- and intraobserver variability.
疾病活动的检测，定义为脑磁共振成像上新发/增大的T2病变，已被提议作为多发性硬化症的一种生物标志物。然而，新发/增大的T2病变的检测可能会受到多种因素的阻碍，而图像相减可以克服这些因素。本研究的目的是改进新发T2病变的自动检测，并减少用户交互以消除观察者间和观察者内的变异性。
对36例有新发T2病变的患者在两个时间点进行多参数脑磁共振成像。使用仿射变换和魔鬼算法对图像进行配准以获得变形场。仿射配准后，对图像进行相减并应用阈值以获得病变掩码，然后使用变形场、强度和局部信息对其进行细化。将此流程与仅应用阈值以及仅依赖图像强度的最新方法进行比较。为了评估改进情况，我们将不同流程的结果与专家视觉检测结果进行了比较。
基于变形场的多通道流程获得的检测骰子相似系数接近0.70，假阳性检测率为17.8%，真阳性检测率为70.9%。通过我们的方法进行的视觉检测与自动检测之间发现了具有统计学意义的相关性（=0.81，p值=2.2688e-09）。
本研究中提出的基于变形场的方法用于检测新发/增大的T2病变，在保持大多数真阳性的同时显著减少了假阳性，并且与视觉检测标注显示出良好的相关性。这种方法可以减少用户交互以及观察者间和观察者内的变异性。
