Volumetric Image Registration From Invariant Keypoints.
Volumetric Image Registration From Invariant Keypoints.
复制标题
DOI：
10.1109/tip.2017.2722689
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Rubin DL
中科院分区：
文献类型：
--
作者：
Rister B;Horowitz MA;Rubin DL
我们提出了一种基于 3D 尺度和旋转不变关键点的图像配准方法。该方法通过对方向分配和梯度直方图进行关键修改，将尺度不变特征变换 (SIFT) 扩展到任意维度。旋转不变性已通过数学证明。根据图像配准的需求，对极值检测和关键点匹配进行了额外的修改。我们的实验表明，离散极值检测中邻域的选择对图像配准精度有很大影响。在头部 MR 图像中，大脑被配准到平均 Dice 系数为 92% 的标记图谱，优于基于互信息的配准以及现有的 3D SIFT 实现。在腹部 CT 图像中，脊柱的平均误差为 4.82 毫米。此外，关键点与模拟头部 MR 图像中的高精度匹配，显示多发性硬化症病变。这些结果是仅使用仿射变换获得的，并且各种医学图像的参数没有变化。这项工作可以作为跨平台软件库免费提供。
We present a method for image registration based on 3D scale- and rotation-invariant keypoints. The method extends the Scale Invariant Feature Transform (SIFT) to arbitrary dimensions by making key modifications to orientation assignment and gradient histograms. Rotation invariance is proven mathematically. Additional modifications are made to extrema detection and keypoint matching based on the demands of image registration. Our experiments suggest that the choice of neighborhood in discrete extrema detection has a strong impact on image registration accuracy. In head MR images, the brain is registered to a labeled atlas with an average Dice coefficient of 92%, outperforming registration from mutual information as well as an existing 3D SIFT implementation. In abdominal CT images, the spine is registered with an average error of 4.82 mm. Furthermore, keypoints are matched with high precision in simulated head MR images exhibiting lesions from multiple sclerosis. These results were achieved using only affine transforms, and with no change in parameters across a wide variety of medical images. This work is freely available as a cross-platform software library.