A novel registration method for retinal images based on local features

Institute of Automation, Chinese Academy of Science, Beijing, China.
Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2008; 2008:2242-5. DOI: 10.1109/IEMBS.2008.4649642
Source: PubMed


Sometimes it is very hard to automatically detect the bifurcations of vascular network in retinal images so that the general feature based registration methods will fail to register two images. In order to solve this problem, we developed a novel local feature based retinal image registration method. We first detect the corner points instead of bifurcations since corner points are sufficient and uniformly distributed in the overlaps. Second, a novel highly distinctive local feature is extracted around each corner point. These local features are invariant to rotation and contrast, and partially invariant to scaling. Third, a bilateral matching technique is applied to identify the corresponding features between two images. Finally a second order polynomial transformation is used to register two images. Experimental results show that our method is very robust and compute efficient to register retinal images even of very low quality.

Download full-text


Available from: Roland Theodore Smith, Jul 10, 2015
  • Source
    • "Nonetheless, the main deficiency is its low distinctiveness due to the reduced dimension of SIFT. In order to achieve higher distinctiveness , the partial intensity invariant feature descriptor (PIIFD) [5] is introduced. Similar to SIFT constituting of a 128-dimensional vector and having some common characteristics [6], PIIFD combines constrained gradient orientations between 0 to í µí¼‹ linearly, and performs a rotation to address the multimodal problem of gradient orientations of corresponding points in opposite directions. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Existing feature descriptor-based methods on retinal image registration are mainly based on scale-invariant feature transform (SIFT) or partial intensity invariant feature descriptor (PIIFD). While these descriptors are often being exploited, they do not work very well upon unhealthy multimodal images with severe diseases. Additionally, the descriptors demand high dimensionality to adequately represent the features of interest. The higher the dimensional-ity, the greater the consumption of resources (e.g. memory space). To this end, this paper introduces a novel registration algorithm coined low-dimensional step pattern analysis (LoSPA), tailored to achieve low dimensionality while providing sufficient distinctiveness to effectively align unhealthy multimodal image pairs. The algorithm locates hypotheses of robust corner features based on connecting edges from the edge maps, mainly formed by vascular junctions. This method is insensitive to intensity changes, and produces uniformly distributed features and high repeata-bility across the image domain. The algorithm continues with describing the corner features in a rotation invariant manner using step patterns. These customized step patterns are robust to non-linear intensity changes, which are well-suited for multimodal retinal image registration. Apart from its low dimensionality, the LoSPA algorithm achieves about twofold higher success rate in multimodal registration on the dataset of severe retinal diseases when compared to the top score among state-of-the-art algorithms.
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 06/2015
  • Source
    • "Feature based techniques [18] [4] [10] involve the detection of landmark points in retinal vascular network and the extraction of features representing the landmark points, followed by the application of a match metric to identify the correspondences between two images. Most of the feature based methods use bifurcation points as landmarks since they are a remarkable indicator of vasculature, but some of them use also other control points such as Harris corners [5]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Accurate retinal image registration is essential to track the evolution of eye-related diseases. We propose a semiautomatic method based on features relying upon retinal graphs for temporal registration of retinal images. The features represent straight lines connecting vascular landmarks on the retina vascular tree: bifurcations, branchings, crossings, end points. In the built retinal graph, one straight line between two vascular landmarks indicates that they are connected by a vascular segment in the original retinal image. The locations of the landmarks are manually extracted to avoid the information loss due to errors in a retinal vessels segmentation algorithms. A straight line model is designed to compute a similarity measure to quantify the line matching between images. From the set of matching lines, corresponding points are extracted and a global transformation is computed. The performance of the registration method is evaluated in the absence of ground truth using the cumulative inverse consistency error (CICE).
    26th IEEE International Symposium on Computer-Based Medical Systems (CBMS 2013); 06/2013
  • Source
    • "Images were aligned with an automated image registration algorithm written in Matlab (version 7.7.0; The MathWorks, Natick, Massachusetts, USA) (Chen et al., 2008) for qualitative comparison of the visibility and localization of the tapetal reflex among different imaging modalities (Table 1). Spectralis SD-OCT 30 (9 mm) horizontal line scans centered at the fovea were captured in all eyes. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to investigate visualization of the tapetal-like reflex using current imaging modalities and evaluate SD-OCT changes in known carriers of X-linked retinitis pigmentosa (XLRP); the objective being the development of an optimal protocol for clinicians to identify carriers. Ten XLRP carriers (19 eyes) were examined using color fundus photography, 488 nm reflectance (488-R), near-infrared reflectance (NIR-R), autofluorescence (AF) and spectral-domain optical coherence tomography (SD-OCT) imaging (Spectralis SLO-OCT, Heidelberg). Horizontal line scans through the fovea were acquired in all subjects and in a group of 10 age-similar controls. Peripheral SD-OCT scans (extending to 27.5° eccentricity) were also acquired in both eyes of 7 carriers. MP-1 microperimetery (10-2 pattern; Nidek) was performed in one eye of each carrier. For the XLRP carriers, a tapetal reflex was observed with all imaging modalities in 8 of 19 eyes. It had the same retinal location on color fundus, 488-R and NIR-R imaging but a different location on AF. The tapetal reflex was most easily detected in 488-R images. The horizontal foveal SD-OCT scans were qualitatively normal, but measurements showed significant outer retinal layer thinning in all eyes. Additionally, the 14 eyes with peripheral SD-OCTs demonstrated patchy loss of the inner segment ellipsoid band. Microperimetry exhibited patchy visual sensitivity loss in 9 eyes. Full field ERGs were variable, ranging from normal to severely abnormal rod and cone responses. Our findings suggest that an optimal protocol for identifying carriers of XLRP should include 488-R imaging in a multimodal approach. Peripheral SD-OCT imaging and central retinal layer quantification revealed significant structural abnormalities.
    Experimental Eye Research 05/2013; 113. DOI:10.1016/j.exer.2013.05.003 · 2.71 Impact Factor
Show more