Non-local Shape Descriptor: A New Similarity Metric for Deformable Multi-modal Registration

Abstract

Abstract. Deformable registration of images obtained from different modalities remains a challenging task in medical image analysis. This paper addresses this problem and proposes a new similarity metric for multi-modal registration, the non-local shape descriptor. It aims to extract the shape of anatomical features in a non-local region. By utilizing the dense evaluation of shape descriptors, this new measure bridges the gap between intensity-based and geometric feature-based similarity criteria. Our new metric allows for accurate and reliable registration of clinical multi-modal datasets and is robust against the most considerable differences between modalities, such as non-functional intensity relations, different amounts of noise and non-uniform bias fields. The measure has been implemented in a non-rigid diffusion-regularized registration framework. It has been applied to synthetic test images and challenging clinical MRI and CT chest scans. Experimental results demonstrate its advantages over the most commonly used similarity metric -mutual information, and show improved alignment of anatomical landmarks.

MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration

“…This article extends our earlier work (Heinrich et al, 2011) by using a more principled derivation of this image descriptor, thus making it more robust to changes in local noise and contrast and therefore allowing for the use of the L2 norm to compare descriptors across modalities. We also present a more thorough evaluation including quantitative comparisons to more recent multi-modal similarity metrics.…”

Non-local Means Resolution Enhancement of Lung 4D-CT Data

“…In a recent work, Buades et al [5] shows that non-local means filtering gives state-of-the-art performance in structurepreserving image denoising. The strategy has also been applied to brain image labeling [6], image registration [8], and MR image super-resolution [9]. We employ nonlocal averaging for combining all matching patches that have been determined based on the distance measure as described in Section 2.2.…”

Self-similarity weighted mutual information: A new nonrigid image registration metric

“…Self-similarity estimates the similarity of a point in one of the images to other points in the same image, and depends on local structures which are ignored by MI. Self-similarity was first proposed for object detection and image retrieval [8], and has since been used in image denoising [9] and registration [10].…”