An Iterative Method for Gastroscopic Image Registration

Image registration is an essential technology for image guided diagnosis. However, in gastroscopic environment, it is still a challenging work due to the ambiguous and noisy endoscopic images. In this paper, we propose an iterative image registration method, homographic triangle and epipolar constraint registration, based on the homographic hypothesis. The method starts with establishing initial matching point pairs between gastroscopic image sequences and clustering them by Delaunay triangulation; normalized cross correlation is then introduced to validate the homographic assumptions of the matching triangles; after that, the inscribed circle’s center point of an unmatched triangle is registered by the epipolar constraint; finally, each unmatched triangles is divided into three sub-triangles according to its vertexes and inscribed circle center point for next HTECR iteration. Clinical data experimental results show a promising performance with this method.

[1]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[2]  Tomás Pajdla,et al.  The geometric error for homographies , 2003, Comput. Vis. Image Underst..

[3]  Roy Soetikno,et al.  Endoscopic mucosal resection for early cancers of the upper gastrointestinal tract. , 2005, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[4]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Huilong Duan,et al.  Dynamic 3D Reconstruction of Gastric Internal Surface Under Gastroscopy , 2014 .

[6]  Dinggang Shen,et al.  A General Fast Registration Framework by Learning Deformation–Appearance Correlation , 2012, IEEE Transactions on Image Processing.

[7]  Kurt Konolige,et al.  CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching , 2008, ECCV.

[8]  Luc Soler,et al.  Evaluation of Endoscopic Image Enhancement for Feature Tracking: A New Validation Framework , 2013, AE-CAI.

[9]  I. Ķikuste,et al.  Advanced endoscopic imaging for gastric cancer assessment: new insights with new optics? , 2014, Best practice & research. Clinical gastroenterology.

[10]  Huilong Duan,et al.  A non-invasive navigation system for retargeting gastroscopic lesions. , 2014, Bio-medical materials and engineering.

[11]  Olivier D. Faugeras,et al.  The fundamental matrix: Theory, algorithms, and stability analysis , 2004, International Journal of Computer Vision.

[12]  Michael Brady,et al.  Motion Correction and Attenuation Correction for Respiratory Gated PET Images , 2011, IEEE Transactions on Medical Imaging.

[13]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[14]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[15]  João Manuel R S Tavares,et al.  Medical image registration: a review , 2014, Computer methods in biomechanics and biomedical engineering.

[16]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[17]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Dinggang Shen,et al.  Improved image registration by sparse patch-based deformation estimation , 2015, NeuroImage.

[19]  Martin De Biasio,et al.  High-sensitivity hyper-spectral video endoscopy system for intra-surgical tissue classification , 2010, 2010 IEEE Sensors.

[20]  Keiichiro Kume,et al.  Endoscopic therapy for early gastric cancer: standard techniques and recent advances in ESD. , 2014, World journal of gastroenterology.

[21]  Frank M. Candocia.  Simultaneous homographic and comparametric alignment of multiple exposure-adjusted pictures of the same scene , 2003, IEEE Trans. Image Process..

[22]  Huilong Duan,et al.  Gastroscopic Image Graph: Application to Noninvasive Multitarget Tracking under Gastroscopy , 2014, Comput. Math. Methods Medicine.