Using Anatomic Magnetic Resonance Image Information to Enhance Visualization and Interpretation of Functional Images: A Comparison of Methods Applied to Clinical Arterial Spin Labeling Images.
Using Anatomic Magnetic Resonance Image Information to Enhance Visualization and Interpretation of Functional Images: A Comparison of Methods Applied to Clinical Arterial Spin Labeling Images.
复制标题
DOI：
10.1109/tmi.2016.2615567
复制
发表时间：
2017-02
影响因子：
10.6
通讯作者：
Alsop DC
中科院分区：
文献类型：
--
作者：
Zhao L;Dai W;Soman S;Hackney DB;Wong ET;Robson PM;Alsop DC
功能成像提供血流动力学和代谢信息，并越来越多地被纳入临床诊断和研究。通常，与作为常规临床方案的一部分获得的其他非功能性横截面图像相比，功能性图像具有降低的信噪比和空间分辨率。我们假设，通过解剖信息增强功能图像的可视化和解释可以提供更好的质量和上级诊断价值。在这项工作中，我们实现了五种方法（频率相加，频率相乘，小波变换，非下采样轮廓波变换和强度-色调-饱和度）和一个新提出的ShArpening局部相似性与解剖图像（SALSA）的方法，以增强功能图像的可视化，同时保留原始的功能对比度和定量信号强度特性在更大的空间尺度。动脉自旋标记脑血流磁共振图像使用解剖图像与多种对比剂进行可视化增强。该算法进行了验证的数字体模和他们的表现对脑肿瘤患者的图像进行了评估的定量指标和神经放射科医生的主观评级。在较大的空间尺度上，倍频方法在保持原始功能图像对比度方面具有最低的残余误差（模拟数据为其他方法的55%-98%，实验数据为64%-86%）。放射科医生对肿瘤的分级也明显更高（肿瘤周围清晰的脑解剖结构p<0.005）。与其他方法相比，SALSA在模拟中提供了11%-133%的与地面真实图像的相似性，并且显示出略低的神经放射科医生分级评分。这些单色方法中的大多数不需要关于功能和解剖图像特征的任何先验知识，除了所获取的分辨率。因此，在临床图像上的自动实现应该是容易可行的。
Functional imaging provides hemodynamic and metabolic information and is increasingly being incorporated into clinical diagnostic and research studies. Typically functional images have reduced signal-to-noise ratio and spatial resolution compared to other non-functional cross sectional images obtained as part of a routine clinical protocol. We hypothesized that enhancing visualization and interpretation of functional images with anatomic information could provide preferable quality and superior diagnostic value. In this work, we implemented five methods (frequency addition, frequency multiplication, wavelet transform, non-subsampled contourlet transform and intensity-hue-saturation) and a newly proposed ShArpening by Local Similarity with Anatomic images (SALSA) method to enhance the visualization of functional images, while preserving the original functional contrast and quantitative signal intensity characteristics over larger spatial scales. Arterial spin labeling blood flow MR images of the brain were visualization enhanced using anatomic images with multiple contrasts. The algorithms were validated on a numerical phantom and their performance on images of brain tumor patients were assessed by quantitative metrics and neuroradiologist subjective ratings. The frequency multiplication method had the lowest residual error for preserving the original functional image contrast at larger spatial scales (55%–98% of the other methods with simulated data and 64%–86% with experimental data). It was also significantly more highly graded by the radiologists (p<0.005 for clear brain anatomy around the tumor). Compared to other methods, the SALSA provided 11%–133% higher similarity with ground truth images in the simulation and showed just slightly lower neuroradiologist grading score. Most of these monochrome methods do not require any prior knowledge about the functional and anatomic image characteristics, except the acquired resolution. Hence, automatic implementation on clinical images should be readily feasible.