Zhao W, Ginsberg M D, Smith D W
Department of Neurology, University of Miami School of Medicine, Florida 33101, USA.
J Cereb Blood Flow Metab. 1995 Jul;15(4):552-65. doi: 10.1038/jcbfm.1995.69.
Traditional autoradiographic image analysis has been restricted to the two-dimensional assessment of local cerebral glucose utilization (LCMRglc) or blood flow in individual brains. It is advantageous, however, to generate an entire three-dimensional (3D) data set and to develop the ability to map replicate images derived from multiple studies into the same 3D space, so as to generate average and standard deviation images for the entire series. We have developed a novel method, termed "disparity analysis," for the alignment and mapping of autoradiographic images. We present the theory of this method, which is based upon a linear affine model, to analyze point-to-point disparities in two images. The method is a direct one that estimates scaling, translation, and rotation parameters simultaneously. Disparity analysis is general and flexible and deals well with damaged or asymmetric sections. We applied this method to study LCMRglc in nine awake male Wistar rats by the [14C]2-deoxyglucose method. Brains were physically aligned in the anteroposterior axis and were sectioned subserially at 100-microns intervals. For each brain, coronal sections were aligned by disparity analysis. The nine brains were then registered in the z-axis with respect to a common coronal reference level (bregma + 0.7 mm). Eight of the nine brains were mapped into the remaining brain, which was designated the "template," and aggregate 3D data sets were generated of the mean and standard deviation for the entire series. The averaged images retained the major anatomic features apparent in individual brains but with some defocusing. Internal anatomic features of the averaged brain were smooth, continuous, and readily identifiable on sections through the 3D stack. The fidelity of the internal architecture of the averaged brain was compared with that of individual brains by analysis of line scans at four representative levels. Line scan comparisons between corresponding sections and their template showed a high degree of correlation, as did similar comparisons performed on entire sections. Fourier analysis of line scan data showed retention of low-frequency information with the expected attenuation of high-frequency components produced by averaging. Region-of-interest (ROI) analysis of the averaged brain yielded LCMRglc values virtually identical to those derived from measurements and subsequent averaging of data from individual brains.(ABSTRACT TRUNCATED AT 400 WORDS)
传统的放射自显影图像分析仅限于对单个大脑中局部脑葡萄糖利用（LCMRglc）或血流进行二维评估。然而，生成完整的三维（3D）数据集并开发将来自多项研究的重复图像映射到同一3D空间的能力是有优势的，以便为整个系列生成平均图像和标准差图像。我们已经开发了一种称为“视差分析”的新方法，用于放射自显影图像的对齐和映射。我们提出了基于线性仿射模型的该方法理论，以分析两幅图像中的点对点视差。该方法是一种直接方法，可同时估计缩放、平移和旋转参数。视差分析具有通用性和灵活性，并且能很好地处理受损或不对称的切片。我们应用此方法通过[14C]2-脱氧葡萄糖法研究了9只清醒雄性Wistar大鼠的LCMRglc。大脑在前后轴上进行物理对齐，并以100微米的间隔进行连续切片。对于每个大脑，冠状切片通过视差分析进行对齐。然后将这9个大脑相对于共同的冠状参考水平（前囟+0.7毫米）在z轴上进行配准。9个大脑中的8个被映射到剩余的大脑中，该大脑被指定为“模板”，并生成了整个系列的平均和标准差的聚合3D数据集。平均图像保留了各个大脑中明显的主要解剖特征，但有一些散焦。通过对四个代表性水平的线扫描分析，将平均大脑的内部解剖特征与各个大脑的内部解剖特征的保真度进行了比较。相应切片与其模板之间的线扫描比较显示出高度相关性，对整个切片进行的类似比较也是如此。线扫描数据的傅里叶分析表明，低频信息得以保留，同时由于平均产生的高频成分出现了预期的衰减。对平均大脑的感兴趣区域（ROI）分析得出的LCMRglc值与通过对各个大脑的数据进行测量并随后求平均得出的值几乎相同。（摘要截断于400字）
