Saliency based Wireless Capsule Endoscopy video abstract

Wireless Capsule Endoscopy (WCE) is a novel revolutionary medical technology obtaining visual information of the entire gastrointestinal, especially the small intestine. However, reviewing a WCE video is a highly time-consuming assignment for the doctors. Focused on the salient region of the WCE images, this paper has proposed a new method to obtain the video abstract. The most representative frames are detected combined mutational and gradient detection. The experiments were performed on 8 video clips and the results demonstrated a promising performance of the proposed method. The average sensitivity, specificity, accuracy and compression are as high as 98%, 84%, 87% and 72%.

[1]  Giovanni Gallo,et al.  Information Theory Based WCE Video Summarization , 2010, 2010 20th International Conference on Pattern Recognition.

[2]  Giovanni Gallo,et al.  Sudden Changes Detection in WCE Video , 2009, ICIAP.

[3]  Max Q.-H. Meng,et al.  Novel detection strategy for abnormalities in WCE video clips , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[4]  Max Q.-H. Meng,et al.  Saliency Based Ulcer Detection for Wireless Capsule Endoscopy Diagnosis , 2015, IEEE Transactions on Medical Imaging.

[5]  Atreyi Kankanhalli,et al.  Automatic partitioning of full-motion video , 1993, Multimedia Systems.

[6]  Michal Mackiewicz,et al.  Wireless Capsule Endoscopy Color Video Segmentation , 2008, IEEE Transactions on Medical Imaging.

[7]  Laurent Itti,et al.  Automatic foveation for video compression using a neurobiological model of visual attention , 2004, IEEE Transactions on Image Processing.

[8]  De Xu,et al.  Illumination-independent descriptors using color moment invariants , 2009 .

[9]  Yoshito Mekada,et al.  Automatic detection of informative frames from wireless capsule endoscopy images , 2010, Medical Image Anal..

[10]  Giovanni Gallo,et al.  Wireless Capsule Endoscopy video segmentation , 2009, 2009 IEEE International Workshop on Medical Measurements and Applications.

[11]  Max Q.-H. Meng,et al.  WCE video abstracting based on novel color and texture features , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[12]  Max Q.-H. Meng,et al.  WCE video clips segmentation based on abnormality , 2010, 2010 IEEE International Conference on Robotics and Biomimetics.

[14]  Max Q.-H. Meng,et al.  An abnormality based WCE video segmentation strategy , 2010, 2010 IEEE International Conference on Automation and Logistics.

[15]  P. Swain,et al.  Wireless capsule endoscopy. , 2002, The Israel Medical Association journal : IMAJ.