Abstract
Wireless capsule endoscopy (WCE) is a noninvasive procedure to examine gastrointestinal tract. The main challenge in this medical procedure is the time required to examine the recorded video by the medical expert. The computer aided diagnosis of gastrointestinal disorders can prove great help in WCE examination procedure. In this paper a WCE video summarization technique is proposed which makes use of transfer learning. In the methodology, Inception V3, a version of standard convolution neural network (CNN) architecture is used for transfer learning along with K-means clustering. The experimental results are evaluated by using F-measure and compression ratio. The results depicts that the Transfer Learning based Video Summarization (TLVS) method performs well in eliminating redundant frames and thus ultimately reduces the time of diagnosis in WCE video inspection.
Similar content being viewed by others
Data availability
KID datasets.
Code availability
Software application.
References
Schoofs GEN, Devière J, Van Gossum A (2006) PillCam colon capsule endoscopy compared with colonoscopy for colorectal tumor diagnosis: a prospective pilot study. Endoscopy 38(10):971–977
Vrushali R, Reena G (2020) Video summarization approaches in wireless capsule endoscopy: a review.In: 6th International Conference on Energy and City of the Future (EVF-2019), vol. 170, Dec 2020
Kanaan M, Farhadi H (2017) Advances in wireless video capsule endoscopy. Int J Wireless Inf Netw 24:166–167
Biniaz A, Zoroofi RA, Sohrabi MR (2020) Automatic reduction of wireless capsule endoscopy reviewing time based on factorization analysis. Biomed Signal Process Control 59:10187
Mehmood I, Sajjad M, Baik SW (2014) Video summarization based tele-endoscopy: a service to efficiently manage visual data generated during wireless capsule endoscopy procedure. J Med Syst. https://doi.org/10.1007/s10916-014-0109-y
Oette M, Stelzer A, Göbels K, Wettstein M, Sagir A, Feldt T, Häussinger D (2009) Wireless capsule endoscopy for the detection of small bowel diseases in HIV-1-infected patients. Eur J Med Res. https://doi.org/10.1186/2047-783X-14-5-191
Bashar MK, Kitasaka T, Suenaga Y, Mekada Y, Mori K (2010) Automatic detection of informative frames from wireless capsule endoscopy images. Med Image Anal 14(3):449–470
Junzhou C et al (2011) Contourlet based feature extraction and classification for Wireless Capsule Endoscopic images. In: Biomedical Engineering and Informatics (BMEI), 2011 4th International Conference on. 2011. IEEE
Vladimir, Shvets A (2018) TernausNet: U-net with VGG11 encoder pre-trained on imagenet for image segmentation. arXiv preprint arXiv:1801.05746
Iakovidis DK, Georgakopoulos SV, Vasilakakis M, Koulaouzidis A, Plagianakos V (2018) Detecting and locating gastrointestinal anomalies using deep learning and iterative cluster unification. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2018.2837002
Schwartz GD, Barkin JS (2007) Small-bowel tumors detected by wireless capsule endoscopy. Dig Dis Sci 52:1026–1030
Emam AZ, Ali YA, Ben Ismail MM (2015) Adaptive features extraction for Capsule Endoscopy (CE) video summarization. In: International Conference on Computer Vision and Image Analysis Applications, Sousse, pp 1–5, https://doi.org/10.1109/ICCVIA.2015.7351879
Rani S, Kumar M (2019) Key frame extraction techniques: a survey (October 2, 2019). In: Proceedings of International Conference on Advancements in Computing & Management (ICACM)
Chen J, Wang Y, Zou YX (2015) An adaptive redundant image elimination for Wireless Capsule Endoscopy review based on temporal correlation and color-texture feature similarity. In: 2015 IEEE International Conference on Digital Signal Processing (DSP), Singapore, pp 735–739, https://doi.org/10.1109/ICDSP.2015.7251973
Zhan C, Cai Y, Sheng N, Qiu C, Cui Y, Gao X (2016) Saliency based wireless capsule endoscopy video abstract. In: 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Datong, pp 1423–1428, https://doi.org/10.1109/CISP-BMEI.2016.7852940
Chen J, Zou Y, Wang Y (2016) Wireless capsule endoscopy video summarization: a learning approach based on Siamese neural network and support vector machine. In: 23rd International Conference on Pattern Recognition (ICPR), Cancun, 2016, pp. 1303–1308. https://doi.org/10.1109/ICPR.2016.7899817
Mohammed A, Yildirim S, Pedersen M, Hovde Ø, Cheikh F (2017) Sparse coded handcrafted and deep features for colon capsule video summarization. In: 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), Thessaloniki, pp 728–733, https://doi.org/10.1109/CBMS
Rafik H, Khan M, Zhihan Lv, Faiza T (2017) Secure video summarization framework for personalized wireless capsule endoscopy. Pervasive Mobile Comput. https://doi.org/10.1016/j.pmcj.2017.03.011
Biniaz A, Zoroofi RA, Sohrabi MR (2020) Automatic reduction of wireless capsule endoscopy reviewing time based on factorization analysis. Biomed Signal Process Control 59:101897
Sushma B, Aparna P (2020) Summarization of wireless capsule endoscopy video using deep feature matching and motion analysis. In: IEEE Access, pp 1–1. https://doi.org/10.1109/ACCESS.2020.3044759
Zhao Q, Meng MQ-H, (2011) Wce video abstracting based on novel color and texture features. In: 2011 IEEE International Conference on Robotics and Biomimetics. IEEE, pp 455–459
Li B, Meng MQ-H, Zhao Q (2010) Wireless capsule endoscopy videosummary. In: 2010 IEEE International Conference on Robotics andBiomimetics. IEEE, pp 454–459
Yuan Y, Meng MQ-H (2013) Hierarchical key frames extraction forWCE video. In: 2013 IEEE International Conference on Mechatronics and Automation. IEEE, pp 225–229
Huo JS, Zou YX, Li L (2012) An advanced WCE video summary usingrelation matrix rank. In: Proceedings of IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE, pp 675–678
Berrimi M, Moussaoui A (2020) Deep learning for identifying and classifying retinal diseases. In: 2nd International Conference on Computer and Information Sciences (ICCIS), Sakaka, Saudi Arabia, pp 1–6, https://doi.org/10.1109/ICCIS49240.2020.9257674
Koulaouzidis A, Iakovidis DK, Yung D, Rondonotti E, Kopylov U, Plevris JN, Toth E, Eliakim A, Johansson GW, Marlicz W et al (2017) KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes”. Endoscopy Int Open 5(06):E477–E483
Huo JS, Zou YX, Li L (2012) An advanced WCE video summary using relation matrix rank. In: Biomedical and Health Informatics (BHI), In: 2012 IEEE-EMBS International Conference on, pp 675–678
Acknowledgements
We thank Dr. Dimitris Iakovidis, University of Thessaly, Greece for permitting access to the requested KID datasets.
Funding
There is no funding sources.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declares that they have no conflict of interest.
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Ok.
Rights and permissions
About this article
Cite this article
Raut, V., Gunjan, R. Transfer learning based video summarization in wireless capsule endoscopy. Int. j. inf. tecnol. 14, 2183–2190 (2022). https://doi.org/10.1007/s41870-022-00894-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-022-00894-0