Image Mosaic Method of Capsule Endoscopy Intestinal Wall Based on Improved Weighted Fusion

doi:10.1007/s12204-023-2637-4

Abstract

Abstract: There is still a dearth of systematic study on picture stitching techniques for the natural tubular structures of intestines, and traditional stitching techniques have a poor application to endoscopic images with deep scenes. In order to recreate the intestinal wall in two dimensions, a method is developed. The normalized Laplacian algorithm is used to enhance the image and transform it into polar coordinates according to the characteristics that intestinal images are not obvious and usually arranged in a circle, in order to extract the new image segments of the current image relative to the previous image. The improved weighted fusion algorithm is then used to sequentially splice the segment images. The experimental results demonstrate that the suggested approach can improve image clarity and minimize noise while maintaining the information content of intestinal images. In addition, the method’s seamless transition between the final portions of a panoramic image also demonstrates that the stitching trace has been removed.

Key words: capsule endoscopy, image stitching, intestinal wall, image enhancement, improved weighted fusion

摘要： 目前针对肠道天然管状结构的图像拼接方法仍缺乏系统的研究，且传统拼接方法对带有深景区域的内镜图像存在适用性差的问题。为了在二维空间中重塑肠道内壁，我们开发了一种方法，该方法根据肠道图像特征不明显且通常呈圆环状排列的特点，采用基于归一化的拉普拉斯算法增强图像并将其进行极坐标展开变换，进而提取出当前图像相对于前张图像的新增图像片段，并利用改进的加权融合算法顺序拼接片段图像。实验结果表明，所提方法可以提高图像的清晰度，并在确保肠道图像信息含量的同时将噪声降到最低，同时最终呈现的全景图像片段之间过渡平缓，拼接痕迹明显消失。

关键词: 胶囊内镜，图像拼接，肠道内壁，图像增强，改进加权融合

CLC Number:

TP391.7
R319

Ma Ting, Wu Jianfang, Hu Feng, Nie Wei, Liu Youxin. Image Mosaic Method of Capsule Endoscopy Intestinal Wall Based on Improved Weighted Fusion[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 535-544.

References

[1] VAN DE BRUAENE C. Small bowel capsule endoscopy: Where are we after almost 15 years of use? [J]. World Journal of Gastrointestinal Endoscopy, 2015, 7(1): 13.
[2] MELTZER A C, BASHIR S. Promise and potential of video capsule endoscopy in the emergency department [J]. Techniques in Gastrointestinal Endoscopy, 2015, 17(1): 2-4.
[3] WEIBEL T, DAUL C, WOLF D, et al. Endoscopic bladder image registration using sparse graph cuts [C]//2010 IEEE International Conference on Image Processing. Hong Kong: IEEE, 2010: 157-160.
[4] CHEN C I, SARGENT D, WANG Y F. Modeling tumor/polyp/lesion structure in 3D for computer-aided diagnosis in colonoscopy [J]. Proceedings of SPIE, 2010, 7625: 76252F.
[5] HU R R. Research on endoscopic image mosaic technology for minimally invasive surgery [D]. Sichuan: University of Electronic Science and Technology, 2018 (in Chinese).
[6] LIU Y, TIAN J W, HU R R, et al. Improved feature point pair purification algorithm based on SIFT during endoscope image stitching [J]. Frontiers in Neurorobotics, 2022, 16: 840594.
[7] ROUSSO B, PELEG S, FINCI I, et al. Universal mosaicing using pipe projection [C]//Sixth International Conference on Computer Vision. Bombay: IEEE, 1998: 945-950.
[8] SEIBEL E J, CARROLL R E, DOMINITZ J A, et al. Tethered capsule endoscopy, A low-cost and high-performance alternative technology for the screening of esophageal cancer and Barrett’s esophagus [J]. IEEE Transactions on Biomedical Engineering, 2008, 55(3): 1032-1042.
[9] ISHII T, ZENBUTSU S, NAKAGUCHI T, et al. Novel points of view for endoscopy: Panoramized intraluminal opened image and 3D shape reconstruction [J]. Journal of Medical Imaging and Health Informatics, 2011, 1(1): 13-20.
[10] ATTAR R, XIE X, WANG Z H, et al. 2D reconstruction of small intestine’s interior wall [J]. Computers in Biology and Medicine, 2019, 105: 54-63.
[11] ZHANG H N. Research on 3D endoscope point cloud stitching algorithm based on binocular camera [D]. Hangzhou: Zhejiang University, 2021 (in Chinese).
[12] WEI Y. Research on depixelation and image mosaicking algorithm of medical confocal endoscopy[D]. Wuhan: Huazhong University of Science and Technology, 2017 (in Chinese).
[13] BERGEN T, WITTENBERG T. Stitching and surface reconstruction from endoscopic image sequences: A review of applications and methods [J]. IEEE Journal of Biomedical and Health Informatics, 2016, 20(1): 304-321.
[14] BARKIN J A, BARKIN J S. Video capsule endoscopy [J]. Gastrointestinal Endoscopy Clinics of North America, 2017, 27(1): 15-27.
[15] QIAN K. Analysis of related factors to small bowel capsule endoscopy gastric-duodenal reciprocation [D]. Guangzhou: Southern Medical University, 2019 (in Chinese).
[16] CHYE E U, SHEIN A B, ZMEU K V. Implementation peculiarities of transition processes analysis algorithms in dynamic systems by Laplace transform [C]//2019 International Multi-Conference on Industrial Engineering and Modern Technologies. Vladivostok: IEEE, 2019: 1-4.
[17] VENKATANATH N, PRANEETH D, BH M C, et al. Blind image quality evaluation using perception based features [C]//2015 Twenty First National Conference on Communications. Mumbai: IEEE, 2015: 1-6.
[18] HUANG L D, ZHAO W, WANG J, et al. Combination of contrast limited adaptive histogram equalisation and discrete wavelet transform for image enhancement [J]. IET Image Processing, 2015, 9(10): 908-915.
[19] CHEN B Y. Local linear enhancement of luminance histogram of color remote sensing image [J]. Optics and Precision Engineering, 2017, 25(2): 502-508 (in Chinese).
[20] SUN Q J, JIANG H Y, YI D H. A study of pathological image detail enhancement method based on improved single scale retinex [J]. Journal of Medical Imaging and Health Informatics, 2018, 8(5): 1051-1056.
[21] LEI F, ZHU L, WANG X L. Improved multi scale Retinex enhancement technology on color underwater image[J]. Journal of Chinese Computer Systems, 2018, 39(1): 185-188 (in Chinese).
[22] WANG W J, WEI C, YANG W H, et al. GLADNet: low-light enhancement network with global awareness [C]//2018 13th IEEE International Conference on Automatic Face & Gesture Recognition. Xi'an: IEEE, 2018: 751-755.
[23] WANG S, LI J Y, XIAO Y Y, et al. Analysis of scene profile image mosaic technology based on surf algorithm [J]. Electronic Technology, 2022, 51(5): 36-37 (in Chinese).
[24] HUANG Z Q, MU Z, CEN C, et al. 360-degree real-time stitching technology for multi-channel video [J]. Journal of Xidian University, 2020, 47(2): 1-8 (in Chinese).
[25] REN Z, TANG Y, XIE Y B, et al. Panoramic image Mosaic technology based on multi-band fusion[J]. Science and Technology Innovation and Application, 2021(1): 55-61 (in Chinese).
[26] LIN C C, PANKANTI S U, RAMAMURTHY K N, et al. Adaptive as-natural-as-possible image stitching [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1155-1163.
[27] ZARAGOZA J, CHIN T J, TRAN Q H, et al. As-projective-As-possible image stitching with moving DLT [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1285-1298.
[28] ZHANG F, LIU F. Parallax-tolerant image stitching [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 3262-3269.