Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Weakly supervised multilabel classification for semantic interpretation of endoscopy video frames

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Several studies have addressed the problem of abnormality detection in medical images using computer-based systems. The impact of such systems in clinical practice and in the society can be high, considering that they can contribute to the reduction of medical errors and the associated adverse events. Today, most of these systems are based on binary classification algorithms that are “strongly” supervised, in the sense that the abnormal training images need to be annotated in detail, i.e., with pixel-level annotations indicating the location of the abnormalities. However, this approach usually does not take into account the diversity of the image content, which may include a variety of structures and artifacts. In the context of gastrointestinal video-endoscopy, addressed in this study, the semantics of the normal contents of the endoscopic video frames include normal mucosal tissues, bubbles, debris and the hole of the lumen, whereas the abnormal video frames may include additional semantics corresponding to lesions or blood. This observation motivated us to investigate various multi-label classification methods, aiming to a richer semantic interpretation of the endoscopic images. Among them, an image-saliency enabled bag-of-words approach and a convolutional neural network architecture enabling multi-scale feature extraction (MM-CNN) are presented. Weakly-supervised learning is implemented using only semantic-level annotations, i.e., meaningful keywords, thus, avoiding the need for the resource demanding pixelwise annotation of the training images. Experiments were performed on a diverse set of wireless capsule endoscopy images. The results of the experiments validate that the weakly-supervised multi-label classification can provide enhanced discrimination of the gastrointestinal abnormalities, with MM-CNN method to provide the best performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. KID dataset: https://is-innovation.eu/kid/.

References

  • Abadi M, Agarwal et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint. arXiv:1603.04467

  • Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34:2274–2282. https://doi.org/10.1109/tpami.2012.120

    Article  Google Scholar 

  • Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Video Frame Underst 110:346–359. https://doi.org/10.1016/j.cviu.2007.09.014

    Article  Google Scholar 

  • Bernal J, Sánchez F, Fernández-Esparrach G, Gil D, Rodríguez C, Vilariño F (2015) WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput Med Imaging Graph 43:99–111

    Article  Google Scholar 

  • Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27

    Google Scholar 

  • Chen H, Wu X, Tao G, Peng Q (2017) Automatic content understanding with cascaded spatial–temporal deep framework for capsule endoscopy videos. Neurocomputing 229:77–87

    Article  Google Scholar 

  • Chollet F (2015) Keras. GitHub. https://github.com/fchollet/keras

  • Deng J, Dong W, Socher R et al (2009) Imagenet: a large-scale hierarchical image database. In: Computer vision and pattern recognition. CVPR. IEEE Conference, pp 248–255

  • Drake J, Hamerly G (2012) Accelerated k-means with adaptive distance bounds. In: 5th NIPS workshop on optimization for machine learning

  • Elisseeff A, Weston J (2001) A kernel method for multi-labeled classification. NIPS 681–687

  • Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27:861–874. https://doi.org/10.1016/j.patrec.2005.10.010

    Article  Google Scholar 

  • Fu Y, Zhang W, Mandal M, Meng M (2014) Computer-aided bleeding detection in WCE video. IEEE J Biomed Health Inform 18(2):636–642

    Article  Google Scholar 

  • Fürnkranz J, Hüllermeier E, Loza Mencía E, Brinker K (2008) Multilabel classification via calibrated label ranking. Mach Learn 73:133–153. https://doi.org/10.1007/s10994-008-5064-8

    Article  Google Scholar 

  • Georgakopoulos S, Iakovidis D, Vasilakakis M et al (2016) Weakly-supervised convolutional learning for detection of inflammatory gastrointestinal lesions. In: Imaging systems and techniques (IST), IEEE international conference. IEEE, pp 510–514

  • Gong Y, Jia Y, Leung T et al (2013) Deep convolutional ranking for multilabel image annotation. arXiv preprint. arXiv:1312.4894

  • Guillaumin M, Mensink T, Verbeek J, Schmid C (2009) Tagprop: discriminative metric learning in nearest neighbor models for image auto-annotation. In: Computer vision, 2009 IEEE 12th international conference, pp 309–316

  • He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034

  • Hinton GE, Srivastava N, Swersky K (2012) Lecture 6a—overview of mini-batch gradient descent. In: Neural networks for machine learning, pp 31

  • Hoai M, Torresani L, De la Torre F, Rother C (2014) Learning discriminative localization from weakly labeled data. Pattern Recogn 47:1523–1534. https://doi.org/10.1016/j.patcog.2013.09.028

    Article  MATH  Google Scholar 

  • Iakovidis D, Koulaouzidis A (2014) Automatic lesion detection in capsule endoscopy based on color saliency: closer to an essential adjunct for reviewing software. Gastrointest Endosc 80:877–883. https://doi.org/10.1016/j.gie.2014.06.026

    Article  Google Scholar 

  • Iakovidis D, Koulaouzidis A (2015) Software for enhanced video capsule endoscopy: challenges for essential progress. Nat Rev Gastroenterol Hepatol 12:172–186. https://doi.org/10.1038/nrgastro.2015.13

    Article  Google Scholar 

  • Iakovidis D, Goudas T, Smailis C, Maglogiannis I (2014a) Ratsnake: a versatile image video frame annotation tool with application to computer-aided diagnosis. Sci World J 2014:1–12. https://doi.org/10.1155/2014/286856

    Article  Google Scholar 

  • Iakovidis D, Sarmiento R, Silva J, Histace A, Romain O, Koulaouzidis A, Dehollain C, Pinna A, Granado B, Dray X (2014b) Towards intelligent capsules for robust wireless endoscopic imaging of the gut. In: Imaging systems and techniques, IEEE international conference. IEEE, pp 95–100

  • Iakovidis D, Chatzis D, Chrysanthopoulos P, Koulaouzidis A (2015) Blood detection in wireless capsule endoscope images based on salient superpixels. In: Annual international conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp 731–734

  • Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456

  • Jia X, Meng M (2018) A deep convolutional neural network for bleeding detection in wireless capsule endoscopy images. In: 38th annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp 639–642

  • Jia Y, Shelhamer E, Donahue J (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675–678

  • Koulaouzidis A, Rondonotti E, Karargyris A (2013) Small-bowel capsule endoscopy: a ten-point contemporary review. World J Gastroenterol 19(24):3726–3746. 6

    Article  Google Scholar 

  • Koulaouzidis A, Iakovidis DK, Karargyris A, Rondonotti E (2015) Wireless endoscopy in 2020: will it still be a capsule? World J Gastroenterol 21(17):5119–5130

    Article  Google Scholar 

  • Koulaouzidis A, Iakovidis DK, Yung DE, 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. Endosc Int Open 5(06):E477–E483

    Article  Google Scholar 

  • Krizhevsky A (2009) Learning multiple layers of features from tiny images. Technical Report, Computer Science Department, University of Toronto. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf

  • Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems (NIPS), Lake Tahoe, Nevada, vol 1, pp 1097–1105

  • Le Cun Y, Boser B, Denker J et al (1990) Handwritten digit recognition with a back-propagation network. In: Advances in neural information processing systems, pp 396–404

  • Li H, Liu L, Sun F et al (2016) Multi-level feature representations for video semantic concept detection. Neurocomputing 172:64–70. https://doi.org/10.1016/j.neucom.2014.09.096

    Article  Google Scholar 

  • Lowe D (2004) Distinctive image video frame features from scale-invariant keypoints. Int J Comput Vision 60:91–110. https://doi.org/10.1023/b:visi.0000029664.99615.94

    Article  Google Scholar 

  • Mencia E, Furnkranz J (2008) Pairwise learning of multilabel classifications with perceptrons. In: Neural networks, 2008. IJCNN 2008 (IEEE world congress on computational intelligence). IEEE international joint conference. IEEE, pp 2899–2906

  • Nickolls J, Buck I, Garland M, Skadron K (2008) Scalable parallel programming with CUDA. Queue 6:40. https://doi.org/10.1145/1365490.1365500

    Article  Google Scholar 

  • Provost F, Fawcett T (1997) Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions. In: Proceedings of the third international conference on knowledge discovery and data mining (KDD'97), pp 43–48

  • Read J, Pfahringer B, Holmes G (2008) Multi-label classification using ensembles of pruned sets. Paper presented at the proceedings—IEEE international conference on data mining, ICDM, pp 995–1000

  • Read J, Reutemann P, Pfahringer B, Holmes G (2017) MEKA: a multi-label/multi-target extension to WEKA. J Mach Learn Res 17:1–5

    MathSciNet  MATH  Google Scholar 

  • Riphaus A, Richter S, Vonderach M, Wehrmann T (2009) Capsule endoscopy interpretation by an endoscopy nurse—a comparative trial. Zeitschrift für Gastroenterologie 47:273–276. https://doi.org/10.1055/s-2008-1027822

    Article  Google Scholar 

  • Seguí S, Drozdzal M, Pascual G, Radeva P, Malagelada C, Azpiroz F, Vitrià J (2016) Generic feature learning for wireless capsule endoscopy analysis. Comput Biol Med 79:163–172

    Article  Google Scholar 

  • Sekuboyina A, Devarakonda S, Seelamantula C (2017) A convolutional neural network approach for abnormality detection in wireless capsule endoscopy. In: Biomedical imaging (ISBI 2017). IEEE 14th international symposium, pp 1057–1060

  • Shi W, Chen J, Chen H, Peng Q, Gan T (2015) Bleeding fragment localization using time domain information for WCE videos. In: 2015 8th international conference on biomedical engineering and informatics, BMEI, pp 73–78

  • Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint. arXiv:1409.1556

  • Smeulders A, Worring M, Santini S et al (2000) Content-based imagevideo frame retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22:1349–1380. https://doi.org/10.1109/34.895972

    Article  Google Scholar 

  • Springenberg J, Dosovitskiy A, Brox T, Riedmiller M (2014) Striving for simplicity: the all convolutional net. arXiv preprint. arXiv:1412.6806

  • Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  • Theodoridis S, Koutroumbas K (2008) Pattern recognition. Elsevier/Academic Press, Amsterdam

    MATH  Google Scholar 

  • Tsoumakas G, Katakis I (2007) Multi-label classification. Int J Data Wareh Min 3:1–13. https://doi.org/10.4018/jdwm.2007070101

    Article  Google Scholar 

  • Tuytelaars T (2010) Dense interest points. In: Computer vision and pattern recognition (CVPR). IEEE conference, pp 2281–2288

  • Vasilakakis M, Iakovidis DK, Spyrou E, Koulaouzidis A (2016) Weakly-supervised lesion detection in video capsule endoscopy based on a bag-of-colour features model. In: International workshop on computer-assisted and robotic endoscopy, pp 96–103

  • Vasilakakis M, Iakovidis D, Spyrou E et al (2017) Beyond lesion detection: towards semantic interpretation of endoscopy videos. In: International conference on engineering applications of neural networks. Springer, Cham, pp 379–390

  • Wang S, Cong Y, Fan H, Yang Y, Tang Y, Zhao H (2015) Computer aided endoscope diagnosis via weakly labeled data mining. In: Image processing (ICIP). IEEE international conference, pp 3072–3076

  • Wang J, Yang Y, Mao J et al (2016a) Cnn-rnn: a unified framework for multi-label image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285–2294

  • Wang S, Cong Y, Fan H, Liu L, Li X, Yang Y, Tang Y, Zhao H, Yu H (2016b) Computer-aided endoscopic diagnosis without human-specific labeling. IEEE Trans Biomed Eng 63(11):2347–2358

    Article  Google Scholar 

  • Witten I, Frank E, Hall M, Pal C (2017) Data mining, 1st edn. Morgan Kaufmann, Amsterdam

    Google Scholar 

  • Yu L, Yuen P, Lai J (2012) Ulcer detection in wireless capsule endoscopy images. In: 21st international conference on pattern recognition (ICPR). IEEE, pp 45–48

  • Yuan Y, Wang J, Li B, Meng M (2015) Saliency based ulcer detection for wireless capsule endoscopy diagnosis. IEEE Trans Med Imaging 34(10):2046–2057

    Article  Google Scholar 

  • Yuan Y, Li B, Meng M (2016a) Improved bag of feature for automatic polyp detection in wireless capsule endoscopy images video frames. IEEE Trans Autom Sci Eng 13:529–535. https://doi.org/10.1109/tase.2015.2395429

    Article  Google Scholar 

  • Yuan Y, Li B, Meng M (2016b) Bleeding frame and region detection in the wireless capsule endoscopy video. IEEE J Biomed Health Inform 20(2):624–630

    Article  Google Scholar 

  • Yuan Y, Li B, Meng M (2017a) WCE abnormality detection based on saliency and adaptive locality-constrained linear coding. IEEE Trans Autom Sci Eng 14(1):149–159

    Article  Google Scholar 

  • Yuan Y, Li D, Meng MQH (2017b) Automatic polyp detection via a novel unified bottom-up and top-down saliency approach. IEEE J Biomed Health Inform. https://doi.org/10.1109/JBHI.2017.2734329

    Article  Google Scholar 

  • Yung D, Fernandez-Urien I, Douglas S, Plevris J, Sidhu R, McAlindon M, Panter S, Koulaouzidis A (2017) Systematic review and meta-analysis of the performance of nurses in small bowel capsule endoscopy reading. United Eur Gastroenterol J. https://doi.org/10.1177/2050640616687232

    Article  Google Scholar 

  • Zhang M, Zhou Z (2006) Multilabel neural networks with applications to functional genomics and text categorization. IEEE Trans Knowl Data Eng 18:1338–1351. https://doi.org/10.1109/tkde.2006.162

    Article  Google Scholar 

  • Zhang M, Zhou Z (2007) ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn 40:2038–2048. https://doi.org/10.1016/j.patcog.2006.12.019

    Article  MATH  Google Scholar 

  • Zhang M, Zhou Z (2014) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26:1819–1837. https://doi.org/10.1109/tkde.2013.39

    Article  Google Scholar 

  • Zhang R, Zheng Y, Mak T, Yu R, Wong S, Lau J, Poon C (2017) Automatic detection and classification of colorectal polyps by transferring low-level CNN features from nonmedical domain. IEEE J Biomed Health Inform 21(1):41–47

    Article  Google Scholar 

  • Zheng Y, Hawkins L, Wolff J, Goloubeva O, Goldberg E (2012) Detection of lesions during capsule endoscopy: physician performance is disappointing. Am J Gastroenterol 107:554–560. https://doi.org/10.1038/ajg.2011.46

    Article  Google Scholar 

Download references

Acknowledgements

The research presented in this paper was financially supported by the project “Klearchos Koulaouzidis” Grant no. 5151 and the Special Account of Research Grants of the University of Thessaly, Greece.

Author information

Authors and Affiliations

  1. Department of Computer Science and Biomedical Informatics, University of Thessaly, Papasiopoulou 2-4, 35131, Lamia, Greece

    Michael D. Vasilakakis, Dimitris Diamantis, Evaggelos Spyrou & Dimtris K. Iakovidis

  2. Endoscopy Unit, The Royal Infirmary of Edinburgh, Edinburgh, UK

    Anastasios Koulaouzidis

Authors
  1. Michael D. Vasilakakis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dimitris Diamantis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Evaggelos Spyrou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anastasios Koulaouzidis
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dimtris K. Iakovidis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dimtris K. Iakovidis.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vasilakakis, M.D., Diamantis, D., Spyrou, E. et al. Weakly supervised multilabel classification for semantic interpretation of endoscopy video frames. Evolving Systems 11, 409–421 (2020). https://doi.org/10.1007/s12530-018-9236-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-018-9236-x

Keywords

Search

Navigation