Abstract
Holistic medical multimedia systems covering end-to-end functionality from data collection to aided diagnosis are highly needed, but rare. In many hospitals, the potential value of multimedia data collected through routine examinations is not recognized. Moreover, the availability of the data is limited, as the health care personnel may not have direct access to stored data. However, medical specialists interact with multimedia content daily through their everyday work and have an increasing interest in finding ways to use it to facilitate their work processes. In this article, we present a novel, holistic multimedia system aiming to tackle automatic analysis of video from gastrointestinal (GI) endoscopy. The proposed system comprises the whole pipeline, including data collection, processing, analysis, and visualization. It combines filters using machine learning, image recognition, and extraction of global and local image features. The novelty is primarily in this holistic approach and its real-time performance, where we automate a complete algorithmic GI screening process. We built the system in a modular way to make it easily extendable to analyze various abnormalities, and we made it efficient in order to run in real time. The conducted experimental evaluation proves that the detection and localization accuracy are comparable or even better than existing systems, but it is by far leading in terms of real-time performance and efficient resource consumption.
- Martın Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. Proc. of USENIX OSDI. 265--283. Google ScholarDigital Library
- Zeno Albisser, Michael Riegler, Pål Halvorsen, Jiang Zhou, Carsten Griwodz, IIangko Balasingham, and Cathal Gurrin. 2015. Expert driven semi-supervised elucidation tool for medical endoscopic videos. In Proc. of ACM MMSys. 73--76. Google ScholarDigital Library
- Luís A. Alexandre, Joao Casteleiro, and Nuno Nobreinst. 2007. Polyp detection in endoscopic video using SVMs. In Proc. of PKDD. 358--365.Google ScholarCross Ref
- Stefan Ameling, Stephan Wirth, Dietrich Paulus, Gerard Lacey, and Fernando Vilarino. 2009. Texture-based polyp detection in colonoscopy. In Bildverarbeitung für die Medizin. Springer, 346--350.Google Scholar
- Hermann Brenner, Matthias Kloor, and Christian Peter Pox. 2016. Colorectal cancer. The Lancet (2016), 1490--1502.Google Scholar
- Antoni Buades, Bartomeu Coll, and Jean-Michel Morel. 2011. Non-local means denoising. IPOL 1 (2011), 208--212.Google ScholarCross Ref
- Da-Chuan Cheng, Wen-Chien Ting, Yung-Fu Chen, Qin Pu, and Xiaoyi Jiang. 2008. Colorectal polyps detection using texture features and support vector machine. In Advances in Mass Data Analysis of Images and Signals in Medicine, Biotechnology, Chemistry and Food Industry. Springer, 62--72. Google ScholarDigital Library
- Christine Chin and David E. Brown. 2000. Learning in science: A comparison of deep and surface approaches. Journal of Research in Science Teaching 37, 2 (2000), 109--138.Google ScholarCross Ref
- Francesco Ciompi, Kaman Chung, Sarah J. van Riel, Arnaud Arindra Adiyoso Setio, Paul K. Gerke, Colin Jacobs, Ernst Th. Scholten, Cornelia Schaefer-Prokop, Mathilde M. W. Wille, Alfonso Marchiano, and others. 2016. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. arXiv preprint arXiv:1610.09157 (2016).Google Scholar
- Yang Cong, Shuai Wang, Ji Liu, Jun Cao, Yunsheng Yang, and Jiebo Luo. 2015. Deep sparse feature selection for computer aided endoscopy diagnosis. Pattern Recognition 48, 3 (2015), 907--917. Google ScholarDigital Library
- Thomas de Lange, Stig Larsen, and Lars Aabakken. 2005. Image documentation of endoscopic findings in ulcerative colitis: Photographs or video clips? Gastrointestinal Endoscopy 61, 6 (2005), 715--720.Google ScholarCross Ref
- Ayso H. de Vries, Shandra Bipat, Evelien Dekker, Marjolein H. Liedenbaum, Jasper Florie, Paul Fockens, Roel van der Kraan, Elizabeth M. Mathus-Vliegen, Johannes B. Reitsma, Roel Truyen, and others. 2010. Polyp measurement based on CT colonography and colonoscopy: Variability and systematic differences. European Radiology 20, 6 (2010), 1404--1413.Google ScholarCross Ref
- Bradley Efron and Robert Tibshirani. 1997. Improvements on cross-validation: The .632+ bootstrap method. Journal of the American Statistical Association 92, 438 (1997), 548--560.Google Scholar
- Hugo Jair Escalante, Carlos A. Hérnadez, Luis Enrique Sucar, and Manuel Montes. 2008. Late fusion of heterogeneous methods for multimedia image retrieval. In Proc. of ICMR. 172--179. Google ScholarDigital Library
- J. Ferlay, E. Steliarova-Foucher, J. Lortet-Tieulent, S. Rosso, J. W. Coebergh, H. Comber, D. Forman, and F. Bray. 2013. Cancer incidence and mortality patterns in Europe: Estimates for 40 countries in 2012. European Journal of Cancer 49, 6 (2013), 1374--1403.Google ScholarCross Ref
- Andrew W. Fitzgibbon and Robert B. Fisher. 1995. A buyer’s guide to conic fitting. Proc. of (BMVC). 513--522. http://dl.acm.org/citation.cfm?id=243124.243148. Google ScholarDigital Library
- The Apache Software Foundation. 2013. Apache Lucene - Index File Formats. Retrieved from https://lucene.apache.org/.Google Scholar
- B. Giritharan, Xiaohui Yuan, Jianguo Liu, B. Buckles, JungHwan Oh, and Shou Jiang Tang. 2008. Bleeding detection from capsule endoscopy videos. In Proc. of EMBS.Google ScholarCross Ref
- O. Holme, M. Bretthauer, A. Fretheim, J. Odgaard-Jensen, and G. Hoff. 2013. Flexible sigmoidoscopy versus faecal occult blood testing for colorectal cancer screening in asymptomatic individuals. The Cochrane Library.Google Scholar
- Sae Hwang, JungHwan Oh, W. Tavanapong, J. Wong, and P. C. de Groen. 2007. Polyp detection in colonoscopy video using elliptical shape feature. In Proc. of ICIP. 465--468.Google ScholarCross Ref
- H. Inoue, H. Kashida, S. Kudo, M. Sasako, T. Shimoda, H. Watanabe, S. Yoshida, M. Guelrud, C. J. Lightdale, K. Wang, and others. 2003. The Paris endoscopic classification of superficial neoplastic lesions: Esophagus, stomach, and colon: November 30 to December 1, 2002. Gastrointest Endosc 58, 6 Suppl (2003), S3--43.Google Scholar
- Menglin Jiang, Shaoting Zhang, Hongsheng Li, and Dimitris N. Metaxas. 2015. Computer-aided diagnosis of mammographic masses using scalable image retrieval. IEEE Transactions on Biomedical Engineering 62, 2 (2015), 783--792.Google ScholarCross Ref
- M. F. Kaminski, J. Regula, E. Kraszewska, M. Polkowski, U. Wojciechowska, J. Didkowska, M. Zwierko, M. Rupinski, M. P. Nowacki, and E. Butruk. 2010. Quality indicators for colonoscopy and the risk of interval cancer. New England Journal of Medicine 362, 19 (2010), 1795--1803.Google ScholarCross Ref
- J. Kang and R. Doraiswami. 2003. Real-time image processing system for endoscopic applications. In Proc. of IEEE CCECE.Google Scholar
- A. Khaleghi and I. Balasingham. 2015. Wireless communication link for capsule endoscope at 600 MHz. In Proc. of IEEE EMBC. 4081--4084.Google Scholar
- Donald Ervin Knuth. 1998. The Art of Computer Programming: Sorting and Searching. Vol. 3. Pearson Education.Google Scholar
- S. Kudo, S. Hirota, T. Nakajima, S. Hosobe, H. Kusaka, T. Kobayashi, M. Himori, and A. Yagyuu. 1994. Colorectal tumours and pit pattern. Journal of Clinical Pathology 47, 10 (1994), 880--885.Google ScholarCross Ref
- Baopu Li and M. Q.-H. Meng. 2012. Tumor recognition in wireless capsule endoscopy images using textural features and SVM-based feature selection. IEEE Transactions on Information Technology in Biomedicine 16, 3 (2012), 323--329. Google ScholarDigital Library
- Baopu Li and Max Q. H. Meng. 2009. Computer-based detection of bleeding and ulcer in wireless capsule endoscopy images by chromaticity moments. CBM 39, 2 (2009), 141--147. Google ScholarDigital Library
- Xirong Li, Cees G. M. Snoek, and Marcel Worring. 2010. Unsupervised multi-feature tag relevance learning for social image retrieval. In Proc. of ACM ICMR. 10--17. Google ScholarDigital Library
- Danyu Liu, Yu Cao, Kihwan Kim, Sean Stanek, Bancha Doungratanaex-Chai, Kungen Lin, Wallapak Tavanapong, Johnny S. Wong, Jung-Hwan Oh, and Piet C. de Groen. 2007. Arthemis: Annotation software in an integrated capturing and analysis system for colonoscopy. Computer Methods and Programs in Biomedicine 88, 2 (2007), 152--163. Google ScholarDigital Library
- Mathias Lux. 2013. LIRE: Open source image retrieval in Java. In Proc. of the 21st ACM MM. ACM, 843--846. Google ScholarDigital Library
- Mathias Lux and Michael Riegler. 2013. Annotation of endoscopic videos on mobile devices: A bottom-up approach. In Proc. of ACM MMSys’13. ACM, 141--145. Google ScholarDigital Library
- Shawn Mallery and Jacques Van Dam. 2000. Advances in diagnostic and therapeutic endoscopy. Medical Clinics of North America 84, 5 (2000), 1059--1083.Google ScholarCross Ref
- A. V. Mamonov, I. N. Figueiredo, P. N. Figueiredo, and Y.-H. R. Tsai. 2014. Automated polyp detection in colon capsule endoscopy. IEEE Transactions on Medical Imaging 33, 7 (2014), 1488--1502.Google ScholarCross Ref
- Ruwan Nawarathna, JungHwan Oh, Jayantha Muthukudage, Wallapak Tavanapong, Johnny Wong, Piet C. De Groen, and Shou Jiang Tang. 2014. Abnormal image detection in endoscopy videos using a filter bank and local binary patterns. NC 144 (2014), 70--91. Google ScholarDigital Library
- Anh Nguyen, Jason Yosinski, and Jeff Clune. 2014. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. arXiv preprint arXiv:1412.1897 (2014).Google Scholar
- S. Oba, S. Tanaka, Y. Sano, S. Oka, and K. Chayama. 2011. Current status of narrow-band imaging magnifying colonoscopy for colorectal neoplasia in Japan. Digestion 83, 3 (2011), 167--172.Google ScholarCross Ref
- Sungheon Park, Myunggi Lee, and Nojun Kwak. 2015. Polyp detection in colonoscopy videos using deeply-learned hierarchical features. Proc. of (ISBI).Google Scholar
- Konstantin Pogorelov, Sigrun Losada, Carsten Griwodz, Thomas de Lange, Kristin Ranheim Randel, Duc Tien Dang Nguyen, Håkon Kvale Stensland, Francesco De Natale, Dag Johansen, Michael Riegler, and Pål Halvorsen. 2017. A holistic multimedia system for gastrointestinal tract disease detection. In Proc. of MMSys. Google ScholarDigital Library
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2015. You only look once: Unified, real-time object detection. arXiv preprint arXiv:1506.02640 (2015).Google Scholar
- Michael Riegler, Martha Larson, Mathias Lux, and Christoph Kofler. 2014. How ‘how’ reflects what’s what: Content-based exploitation of how users frame social images. In Proc. of ACM MM. 397--406. Google ScholarDigital Library
- Michael Riegler, Mathias Lux, Vincent Charvillat, Axel Carlier, Raynor Vliegendhart, and Martha Larson. 2014b. VideoJot: A multifunctional video annotation tool. In Proc. of ACM ICMR. 534--537. Google ScholarDigital Library
- Michael Riegler, Mathias Lux, Carsten Griwodz, Concetto Spampinato, Thomas de Lange, Sigrun L. Eskeland, Konstantin Pogorelov, Wallapak Tavanapong, Peter T. Schmidt, Cathal Gurrin, Dag Johansen, Håvard Johansen, and Pål Halvorsen. 2016. Multimedia and medicine: Teammates for better disease detection and survival. In Proc. of ACM MM. 968--977. Google ScholarDigital Library
- Michael Riegler, Konstantin Pogorelov, Pål Halvorsen, Thomas de Lange, Carsten Griwodz, Peter Thelin Schmidt, Sigrun Losada Eskeland, and Dag Johansen. 2016. EIR - efficient computer aided diagnosis framework for gastrointestinal endoscopies. In Proc. of CBMI.Google ScholarCross Ref
- Jürgen Schmidhuber. 2015. Deep learning in neural networks: An overview. Neural Networks 61 (2015), 85--117. Google ScholarDigital Library
- Joe V. Selby, Gary D. Friedman, Charles P. Quesenberry Jr, and Noel S. Weiss. 1992. A case--control study of screening sigmoidoscopy and mortality from colorectal cancer. New England Journal of Medicine 326, 10 (1992), 653--657.Google ScholarCross Ref
- Theodoros Semertzidis, Dimitrios Rafailidis, Eleftherios Tiakas, Michael G. Strintzis, and Petros Daras. 2013. Multimedia indexing, search, and retrieval in large databases of social networks. In Social Media Retrieval. Springer, 43--63.Google Scholar
- Cees G. M. Snoek, Marcel Worring, and Arnold W. M. Smeulders. 2005. Early versus late fusion in semantic video analysis. In Proc. of ACM MM. 399--402. Google ScholarDigital Library
- Jingkuan Song. 2013. Effective hashing for large-scale multimedia search. In Proc. of Sigmod/PODS PhD Symp. 55--60. Google ScholarDigital Library
- Donald F. Specht. 1990. Probabilistic neural networks. Neural Networks 3, 1 (1990), 109--118. Google ScholarDigital Library
- Nima Tajbakhsh, Suryakanth Gurudu, and Jianming Liang. 2016. Automated polyp detection in colonoscopy videos using shape and context information. IEEE Transactions on Medical Imaging 35, 2 (Feb. 2016), 630--644.Google ScholarCross Ref
- Nima Tajbakhsh, Suryakanth R. Gurudu, and Jianming Liang. 2015. Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In Proc. of IEEE ISBI.Google ScholarCross Ref
- Kyosuke Tanaka, Carlos A. Rubio, Aldona Dlugosz, Kotryna Truskaite, Ragnar Befrits, Greger Lindberg, and Peter T. Schmidt. 2013. Narrow-band imaging magnifying endoscopy in adult patients with eosinophilic esophagitis/esophageal eosinophilia and lymphocytic esophagitis. Gastrointestinal Endoscopy 78, 4 (2013), 659--664.Google ScholarCross Ref
- The New York Times. 2013. The $2.7 Trillion Medical Bill. Retrieved from http://goo.gl/CuFyFJ.Google Scholar
- L. von Karsa, J. Patnick, and N. Segnan. 2012. European guidelines for quality assurance in colorectal cancer screening and diagnosis. First edition--executive summary. Endoscopy 44 Suppl 3 (2012), SE1--8.Google Scholar
- Dayong Wang, Aditya Khosla, Rishab Gargeya, Humayun Irshad, and Andrew H. Beck. 2016b. Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718 (2016).Google Scholar
- Shuai Wang, Yang Cong, Huijie Fan, Lianqing Liu, Xiaoqiu Li, Yunsheng Yang, Yandong Tang, Huaici Zhao, and Haibin Yu. 2016. Computer-aided endoscopic diagnosis without human-specific labeling. Transactions on BME 63, 11 (2016).Google Scholar
- Yi Wang, Wallapak Tavanapong, Johnny Wong, JungHwan Oh, and Piet C. de Groen. 2011. Computer-aided detection of retroflexion in colonoscopy. In Proc. of IEEE CBMS. 1--6. Google ScholarDigital Library
- Yi Wang, Wallapak Tavanapong, Johnny Wong, JungHwan Oh, and Piet C. de Groen. 2013. Near real-time retroflexion detection in colonoscopy. IEEE Journal of Biomedical and Health Informatics 17, 1 (2013), 143--152.Google ScholarCross Ref
- Yi Wang, Wallapak Tavanapong, Johnson Wong, JungHwan Oh, and Piet C. de Groen. 2014. Part-based multiderivative edge cross-sectional profiles for polyp detection in colonoscopy. Journal of BMHI 18, 4 (2014), 1379--1389.Google Scholar
- Yi Wang, Wallapak Tavanapong, Johnny Wong, Jung Hwan Oh, and Piet C. de Groen. 2015. Polyp-alert: Near real-time feedback during colonoscopy. Computer Methods and Programs in Biomedicine 120, 3 (2015), 164--179. Google ScholarDigital Library
- Yi Wang, Wallapak Tavanapong, Johnny S. Wong, JungHwan Oh, and Piet C. de Groen. 2010. Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection. IEEE Transactions on Biomedical Engineering 57, 3 (2010), 685--695.Google ScholarCross Ref
- World Health Organization - International Agency for Research on Cancer. 2012. Estimated Cancer Incidence, Mortality and Prevalence Worldwide in 2012. Retrieved from http://globocan.iarc.fr/Pages/fact_sheets_popula tion.aspx.Google Scholar
- Mingda Zhou, Guanqun Bao, Yishuang Geng, B. Alkandari, and Xiaoxi Li. 2014. Polyp detection and radius measurement in small intestine using video capsule endoscopy. In Proc. of BMEI. 237--241.Google ScholarCross Ref
Index Terms
- From Annotation to Computer-Aided Diagnosis: Detailed Evaluation of a Medical Multimedia System
Recommendations
A Holistic Multimedia System for Gastrointestinal Tract Disease Detection
MMSys'17: Proceedings of the 8th ACM on Multimedia Systems ConferenceAnalysis of medical videos for detection of abnormalities and diseases requires both high precision and recall, but also real-time processing for live feedback and scalability for massive screening of entire populations. Existing work on this field does ...
Computer-aided diagnosis system for colon abnormalities detection in wireless capsule endoscopy images
Wireless capsule endoscopy (WCE) is a novel imaging technique that can travel through human body and image the small bowel entirely. Therefore, it has been gradually adopted compared with traditional endoscopies for gastrointestinal diseases. However, ...
Computer-aided diagnosis: The emerging of three CAD systems induced by Japanese health care needs
The aim of this paper is to describe three emerging computer-aided diagnosis (CAD) systems induced by Japanese health care needs. CAD has been developing fast in the last two decades. The idea of using a computer to help in medical image diagnosis is ...
Comments