skip to main content
research-article
Open Access

An Extensive Study on Cross-Dataset Bias and Evaluation Metrics Interpretation for Machine Learning Applied to Gastrointestinal Tract Abnormality Classification

Published:22 June 2020Publication History
Skip Abstract Section

Abstract

Precise and efficient automated identification of gastrointestinal (GI) tract diseases can help doctors treat more patients and improve the rate of disease detection and identification. Currently, automatic analysis of diseases in the GI tract is a hot topic in both computer science and medical-related journals. Nevertheless, the evaluation of such an automatic analysis is often incomplete or simply wrong. Algorithms are often only tested on small and biased datasets, and cross-dataset evaluations are rarely performed. A clear understanding of evaluation metrics and machine learning models with cross datasets is crucial to bring research in the field to a new quality level. Toward this goal, we present comprehensive evaluations of five distinct machine learning models using global features and deep neural networks that can classify 16 different key types of GI tract conditions, including pathological findings, anatomical landmarks, polyp removal conditions, and normal findings from images captured by common GI tract examination instruments. In our evaluation, we introduce performance hexagons using six performance metrics, such as recall, precision, specificity, accuracy, F1-score, and the Matthews correlation coefficient to demonstrate how to determine the real capabilities of models rather than evaluating them shallowly. Furthermore, we perform cross-dataset evaluations using different datasets for training and testing. With these cross-dataset evaluations, we demonstrate the challenge of actually building a generalizable model that could be used across different hospitals. Our experiments clearly show that more sophisticated performance metrics and evaluation methods need to be applied to get reliable models rather than depending on evaluations of the splits of the same dataset—that is, the performance metrics should always be interpreted together rather than relying on a single metric.

References

  1. Taruna Agrawal, Rahul Gupta, Saurabh Sahu, and Carol Y. Espy-Wilson. 2017. SCL-UMD at the Medico Task-MediaEval 2017: Transfer learning based classification of medical images. In Proceedings of MediaEval 2017.Google ScholarGoogle Scholar
  2. Luís A. Alexandre, Nuno Nobre, and João Casteleiro. 2008. Color and position versus texture features for endoscopic polyp detection. In Proceedings of IEEE BMEI2008, Vol. 2. 38--42.Google ScholarGoogle Scholar
  3. Stefan Ameling, Stephan Wirth, Dietrich Paulus, Gerard Lacey, and Fernando Vilarino. 2009. Texture-based polyp detection in colonoscopy. In Bildverarbeitung für die Medizin 2009. 346--350.Google ScholarGoogle Scholar
  4. Quentin Angermann, Jorge Bernal, Cristina Sánchez-Montes, Maroua Hammami, Gloria Fernández-Esparrach, Xavier Dray, Olivier Romain, F. Javier Sánchez, and Aymeric Histace. 2017. Towards real-time polyp detection in colonoscopy videos: Adapting still frame-based methodologies for video sequences analysis. In Proceedings of CARE and CLIP 2017. 29--41.Google ScholarGoogle Scholar
  5. Jorge Bernal, Aymeric Histace, Marc Masana, Quentin Angermann, Cristina Sánchez-Montes, Cristina Rodriguez, Maroua Hammami, et al. 2018. Polyp detection benchmark in colonoscopy videos using GTCreator: A novel fully configurable tool for easy and fast annotation of image databases. In Proceedings of CARS 2018.Google ScholarGoogle Scholar
  6. Jorge Bernal, F. Javier Sánchez, Gloria Fernández-Esparrach, Debora Gil, Cristina Rodríguez, and Fernando Vilariño. 2015. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized Medical Imaging and Graphics 43 (2015), 99--111.Google ScholarGoogle ScholarCross RefCross Ref
  7. Jorge Bernal, Javier Sánchez, and Fernando Vilarino. 2012. Towards automatic polyp detection with a polyp appearance model. Pattern Recognition 45, 9 (2012), 3166--3182.Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. Jorge Bernal, Javier Sánchez, and Fernando Vilarino. 2013. Impact of image preprocessing methods on polyp localization in colonoscopy frames. In Proceedings of IEEE EMBC 2013. 7350--7354.Google ScholarGoogle Scholar
  9. Jorge Bernal, Nima Tajkbaksh, Francisco Javier Sánchez, Bogdan J. Matuszewski, Hao Chen, Lequan Yu, Quentin Angermann, et al. 2017. Comparative validation of polyp detection methods in video colonoscopy: Results from the MICCAI 2015 Endoscopic Vision Challenge. IEEE Transactions on Medical Imaging 36, 6 (2017), 1231--1249.Google ScholarGoogle ScholarCross RefCross Ref
  10. Rune Johan Borgli, Pål Halvorsen, Michael Riegler, and Håkon Kvale Stensland. 2018. Automatic hyperparameter optimization in Keras for the MediaEval 2018 Medico Multimedia Task. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  11. Léon Bottou. 2010. Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT 2010. 177--186.Google ScholarGoogle ScholarCross RefCross Ref
  12. Freddie Bray, Jacques Ferlay, Isabelle Soerjomataram, Rebecca L. Siegel, Lindsey A. Torre, and Ahmedin Jemal. 2018. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians 68, 6 (2018), 394--424.Google ScholarGoogle ScholarCross RefCross Ref
  13. Da-Chuan Cheng, Wen-Chien Ting, Yung-Fu Chen, and Xiaoyi Jiang. 2011. Automatic detection of colorectal polyps in static images. Biomedical Engineering: Applications, Basis and Communications 23, 05 (2011), 357--367.Google ScholarGoogle Scholar
  14. Torch Contributors. 2018. Torchvision Models. Retrieved May 7, 2020 from https://pytorch.org/docs/stable/torchvision/models.html.Google ScholarGoogle Scholar
  15. Pieter-Tjerk de Boer, Dirk P. Kroese, Shie Mannor, and Reuven Y. Rubinstein. 2005. A tutorial on the cross-entropy method. Annals of Operations Research 134 (2005), 19--67.Google ScholarGoogle Scholar
  16. Thomas de Lange, Pål Halvorsen, and Michael Riegler. 2018. Methodology to develop machine learning algorithms to improve performance in gastrointestinal endoscopy. World Journal of Gastroenterology 24, 45 (2018), 5057.Google ScholarGoogle Scholar
  17. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of IEEE CVPR 2009. 248--255.Google ScholarGoogle ScholarCross RefCross Ref
  18. Danielle Dias and Ulisses Dias. 2018. Transfer learning with CNN architectures for classifying gastrointestinal diseases and anatomical landmarks. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  19. Patrick Doetsch, Christian Buck, Pavlo Golik, Niklas Hoppe, Michael Kramp, Johannes Laudenberg, Christian Oberdörfer, Pascal Steingrube, Jens Forster, and Arne Mauser. 2009. Logistic model trees with AUC split criterion for the KDD Cup 2009 Small Challenge. In Proceedings of KDD-Cup ’09. 77--88.Google ScholarGoogle Scholar
  20. Piotr Dollár, Christian Wojek, Bernt Schiele, and Pietro Perona. 2009. Pedestrian detection: A benchmark. In Proceedings of IEEE CVPR 2009.Google ScholarGoogle Scholar
  21. Jerome Friedman, Trevor Hastie, and Robert Tibshirani. 2000. Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors). Annals of Statistics 28, 2 (2000), 337--407.Google ScholarGoogle ScholarCross RefCross Ref
  22. Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten. 2009. The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter 11, 1 (2009), 10--18.Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of IEEE CVPR 2016. 770--778.Google ScholarGoogle ScholarCross RefCross Ref
  24. Steven A. Hicks, Pia H. Smedsrud, Pål Halvorsen, and Michael Riegler. 2018. Deep learning based disease detection using domain specific transfer learning. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  25. Trung-Hieu Hoang, Hai-Dang Nguyen, and Thanh-An Nguyen. 2018. An application of residual network and faster - RCNN for Medico: Multimedia Task at MediaEval 2018. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  26. Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. 2017. Densely connected convolutional networks. In Proceedings of IEEE CVPR 2017. 2261--2269.Google ScholarGoogle Scholar
  27. Sae Hwang, JungHwan Oh, Wallapak Tavanapong, Johnny Wong, and Piet C. De Groen. 2007. Polyp detection in colonoscopy video using elliptical shape feature. In Proceedings of IEEE ICIP 2007, Vol. 2. 465--468.Google ScholarGoogle Scholar
  28. Dimitrios K. Iakovidis, Dimitrios E. Maroulis, Stavros A. Karkanis, and A. Brokos. 2005. A comparative study of texture features for the discrimination of gastric polyps in endoscopic video. In Proceedings of IEEE CBMS 2005. 575--580.Google ScholarGoogle Scholar
  29. Yuji Iwahori, Takayuki Shinohara, Akira Hattori, Robert J. Woodham, Shinji Fukui, Manas Kamal Bhuyan, and Kunio Kasugai. 2013. Automatic polyp detection in endoscope images using a Hessian filter. In Proceedings of MVA 2013, Vol. 13. 21--24.Google ScholarGoogle Scholar
  30. Debesh Jha, Pia Smedsrud, Michael Riegler, Pål Halvorsen, Thomas de Lange, Dag Johansen, and Håvard Johansen. 2020. Kvasir-SEG: A segmented polyp dataset. In Proceedings of MMM 2020. 1--12.Google ScholarGoogle Scholar
  31. Xiao Jia and Max Q.-H. Meng. 2017. Gastrointestinal bleeding detection in wireless capsule endoscopy images using handcrafted and CNN features. In Proceedings of IEEE EMBC 2017. 3154--3157.Google ScholarGoogle Scholar
  32. Stavros A. Karkanis, Dimitrios K. Iakovidis, Dimitrios E. Maroulis, Dimitris A. Karras, and M. Tzivras. 2003. Computer-aided tumor detection in endoscopic video using color wavelet features. IEEE Transactions on Information Technology in Biomedicine 7, 3 (2003), 141--152.Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. Zeshan Khan and Muhammad Atif Tahir. 2018. Majority voting of heterogeneous classifiers for finding abnormalities in the gastro-intestinal tract. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  34. Aditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei Efros, and Antonio Torralba. 2012. Undoing the damage of dataset bias. In Proceedings of ECCV 2012.Google ScholarGoogle Scholar
  35. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980.Google ScholarGoogle Scholar
  36. Mathias Kirkerød, Vajira Thambawita, Michael Riegler, and Pål Halvorsen. 2018. Using preprocessing as a tool in medical image detection. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  37. Tobey H. Ko, Zhonglei Gu, and Yang Liu. 2018. Weighted discriminant embedding: Discriminant subspace learning for imbalanced medical data classification. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  38. Niels Landwehr, Mark Hall, and Eibe Frank. 2005. Logistic model trees. Machine Learning 59, 1--2 (2005), 161--205.Google ScholarGoogle ScholarDigital LibraryDigital Library
  39. A. M. Leufkens, M. G. H. van Oijen, F. P. Vleggaar, and P. D. Siersema. 2012. Factors influencing the miss rate of polyps in a back-to-back colonoscopy study. Endoscopy 44, 05 (2012), 470--475.Google ScholarGoogle Scholar
  40. Baopu Li and Max 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 ScholarGoogle ScholarDigital LibraryDigital Library
  41. David Lieberman. 2005. Quality and colonoscopy: A new imperative. Gastrointestinal Endoscopy 61, 3 (2005), 392--394.Google ScholarGoogle ScholarCross RefCross Ref
  42. Mathias Lux, Michael Riegler, Pål Halvorsen, Konstantin Pogorelov, and Nektarios Anagnostopoulos. 2016. LIRE: Open source visual information retrieval. In Proceedings of ACM MMSys 2016. 30.Google ScholarGoogle Scholar
  43. Alexander V. Mamonov, Isabel N. Figueiredo, Pedro N. Figueiredo, and Yen-Hsi Richard Tsai. 2014. Automated polyp detection in colon capsule endoscopy. IEEE Transactions on Medical Imaging 33, 7 (2014), 1488--1502.Google ScholarGoogle ScholarCross RefCross Ref
  44. Yuichi Mori and Shin-Ei Kudo. 2018. Detecting colorectal polyps via machine learning. Nature Biomedical Engineering 2, 10 (2018), 713.Google ScholarGoogle Scholar
  45. Syed Sadiq Ali Naqvi, Shees Nadeem, Muhammad Zaid, and Muhammad Atif Tahir. 2017. Ensemble of texture features for finding abnormalities in the gastro-intestinal tract. In Proceedings of MediaEval 2017.Google ScholarGoogle Scholar
  46. Olga Ostroukhova, Konstantin Pogorelov, Michael Riegler, Duc-Tien Dang-Nguyen, and Pål Halvorsen. 2018. Transfer learning with prioritized classification and training dataset equalization for medical objects detection. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  47. Sun Young Park, Dustin Sargent, Inbar Spofford, Kirby G. Vosburgh, and Y. A-Rahim. 2012. A colon video analysis framework for polyp detection. IEEE Transactions on Biomedical Engineering 59, 5 (2012), 1408.Google ScholarGoogle ScholarCross RefCross Ref
  48. Stefan Petscharnig, Klaus Schöffmann, and Mathias Lux. 2017. An inception-like CNN architecture for GI disease and anatomical landmark classification. In Proceedings of MediaEval 2017.Google ScholarGoogle Scholar
  49. Konstantin Pogorelov, Olga Ostroukhova, Mattis Jeppsson, Håvard Espeland, Carsten Griwodz, Thomas de Lange, Dag Johansen, Michael Riegler, and Pål Halvorsen. 2018. Deep learning and hand-crafted feature based approaches for polyp detection in medical videos. In Proceedings of IEEE CBMS 2018. 381--386.Google ScholarGoogle Scholar
  50. Konstantin Pogorelov, Kristin Ranheim Randel, Thomas de Lange, Sigrun Losada Eskeland, Carsten Griwodz, Dag Johansen, Concetto Spampinato, et al. 2017. Nerthus: A bowel preparation quality video dataset. In Proceedings of ACM MMSys 2017. 170--174.Google ScholarGoogle Scholar
  51. Konstantin Pogorelov, Kristin Ranheim Randel, Carsten Griwodz, Sigrun Losada Eskeland, Thomas de Lange, Dag Johansen, Concetto Spampinato, et al. 2017. Kvasir: A multi-class image dataset for computer aided gastrointestinal disease detection. In Proceedings of ACM MMSys 2017. 164--169.Google ScholarGoogle Scholar
  52. Konstantin Pogorelov, Michael Riegler, Sigrun Losada Eskeland, Thomas de Lange, Dag Johansen, Carsten Griwodz, Peter Thelin Schmidt, and Pål Halvorsen. 2017. Efficient disease detection in gastrointestinal videos—Global features versus neural networks. International Journal of Multimedia Tools and Applications 76, 21 (2017), 22493--22525.Google ScholarGoogle ScholarDigital LibraryDigital Library
  53. Konstantin Pogorelov, Michael Riegler, Pål Halvorsen, Thomas De Lange, Kristin Ranheim Randel, Duc-Tien Dang-Nguyen, Mathias Lux, and Olga Ostroukhova. 2018. Medico multimedia task at MediaEval 2018. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  54. Konstantin Pogorelov, Michael Riegler, Pål Halvorsen, Carsten Griwodz, Thomas de Lange, Kristin Randel, Sigrun Eskeland, Dang Nguyen, Duc Tien, and Olga Ostroukhova. 2017. A comparison of deep learning with global features for gastrointestinal disease detection. In Proceedings of MediaEval 2017.Google ScholarGoogle Scholar
  55. Konstantin Pogorelov, Michael Riegler, Pål Halvorsen, Thomas De Lange, Kristin Ranheim Randel, Duc-Tien Dang-Nguyen, Mathias Lux, and Olga Ostroukhova. 2018. Medico multimedia task at MediaEval 2018. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  56. 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 Proceedings of ACM MM 2014. 397--406.Google ScholarGoogle Scholar
  57. Michael Riegler, Mathias Lux, Carsten Griwodz, Concetto Spampinato, Thomas de Lange, Sigrun L. Eskeland, Konstantin Pogorelov, et al. 2016. Multimedia and medicine: Teammates for better disease detection and survival. In Proceedings of ACM MM 2016. 968--977.Google ScholarGoogle Scholar
  58. Michael Riegler, Konstantin Pogorelov, Sigrun Losada Eskeland, Peter Thelin Schmidt, Zeno Albisser, Dag Johansen, Carsten Griwodz, Pål Halvorsen, and Thomas De Lange. 2017. From annotation to computer-aided diagnosis: Detailed evaluation of a medical multimedia system. ACM Transactions on Multimedia Computing, Communications, and Applications 13, 3 (2017), 26.Google ScholarGoogle Scholar
  59. Michael Riegler, Konstantin Pogorelov, Pål Halvorsen, Kristin Randel, Sigrun Losada Eskeland, Duc-Tien Dang-Nguyen, Mathias Lux, Carsten Griwodz, Concetto Spampinato, and Thomas Lange. 2017. Multimedia for medicine: The Medico Task at MediaEval 2017. In Proceedings of MediaEval 2017.Google ScholarGoogle Scholar
  60. Sebastian Ruder. 2016. An overview of gradient descent optimization algorithms. arXiv:1609.04747.Google ScholarGoogle Scholar
  61. Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, et al. 2015. ImageNet large scale visual recognition challenge. International Journal of Computer Vision 115 (2015), 211--252.Google ScholarGoogle ScholarDigital LibraryDigital Library
  62. Steven L. Salzberg. 1994. C4. 5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993. Machine Learning 16, 3 (1994), 235--240.Google ScholarGoogle ScholarCross RefCross Ref
  63. Younghak Shin and Ilangko Balasingham. 2017. Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification. In Proceedings of IEEE EMBC 2017. 3277--3280.Google ScholarGoogle Scholar
  64. Michael Steiner, Mathias Lux, and Pål Halvorsen. 2018. The 2018 Medico Multimedia Task submission of Team NOAT using neural network features and search-based classification. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  65. Marc Sumner, Eibe Frank, and Mark Hall. 2005. Speeding up logistic model tree induction. In Proceedings of PKDD 2005. 675--683.Google ScholarGoogle Scholar
  66. Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013. On the importance of initialization and momentum in deep learning. In Proceedings of ICML 2013. 1139--1147.Google ScholarGoogle Scholar
  67. Nima Tajbakhsh, Suryakanth R. Gurudu, and Jianming Liang. 2015. Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In Proceedings of IEEE ISBI 2015. 79--83.Google ScholarGoogle Scholar
  68. Nima Tajbakhsh, Suryakanth R. Gurudu, and Jianming Liang. 2016. Automated polyp detection in colonoscopy videos using shape and context information. IEEE Transactions on Medical Imaging 35, 2 (2016), 630--644.Google ScholarGoogle Scholar
  69. Nima Tajbakhsh, Jae Y. Shin, Suryakanth R. Gurudu, R. Todd Hurst, Christopher B. Kendall, Michael B. Gotway, and Jianming Liang. 2016. Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE Transactions on Medical Imaging 35, 5 (2016), 1299--1312.Google ScholarGoogle ScholarCross RefCross Ref
  70. Mario Taschwer, Manfred Jürgen Primus, Klaus Schoeffmann, and Oge Marques. 2018. Early and late fusion of classifiers for the MediaEval Medico Task. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  71. Vajira Thambawita, Debesh Jha, Michael Riegler, Pål Halvorsen, Hugo Lewi Hammer, Håvard D. Johansen, and Dag Johansen. 2018. The Medico-Task 2018: Disease detection in the gastrointestinal tract using global features and deep learning. In Proceedings of MediaEval 2018.Google ScholarGoogle Scholar
  72. A. Torralba and A. A. Efros. 2011. Unbiased look at dataset bias. In Proceedings of IEEE CVPR 2011. 1521--1528.Google ScholarGoogle Scholar
  73. David Vázquez, Jorge Bernal, F. Javier Sánchez, Gloria Fernández-Esparrach, Antonio M. López, Adriana Romero, Michal Drozdzal, and Aaron C. Courville. 2017. A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of Healthcare Engineering 2017 (2017), 4037190.Google ScholarGoogle Scholar
  74. 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--SE8.Google ScholarGoogle Scholar
  75. Pu Wang, Xiao Xiao, Jeremy R. Glissen Brown, Tyler M. Berzin, Mengtian Tu, Fei Xiong, Xiao Hu, et al. 2018. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nature Biomedical Engineering 2, 10 (2018), 741.Google ScholarGoogle Scholar
  76. Yi Wang, Wallapak Tavanapong, Johnny Wong, JungHwan Oh, and Piet C. De Groen. 2014. Part-based multiderivative edge cross-sectional profiles for polyp detection in colonoscopy. IEEE Journal of Biomedical and Health Informatics 18, 4 (2014), 1379--1389.Google ScholarGoogle ScholarCross RefCross Ref
  77. Yi Wang, Wallapak Tavanapong, Johnny Wong, Jung Hwan Oh, and Piet C. De Groen. 2015. Polyp-Alert: Near real-time feedback during colonoscopy. International Journal of Computer Methods and Programs in Biomedicine 120, 3 (2015), 164--179.Google ScholarGoogle ScholarDigital LibraryDigital Library
  78. Lequan Yu, Hao Chen, Qi Dou, Jing Qin, and Pheng Ann Heng. 2017. Integrating online and offline three-dimensional deep learning for automated polyp detection in colonoscopy videos. IEEE Journal of Biomedical and Health Informatics 21, 1 (2017), 65--75.Google ScholarGoogle ScholarCross RefCross Ref
  79. Yixuan Yuan, Dengwang Li, and Max Q.-H. Meng. 2018. Automatic polyp detection via a novel unified bottom-up and top-down saliency approach. IEEE Journal of Biomedical and Health Informatics 22, 4 (2018), 1250--1260.Google ScholarGoogle Scholar
  80. Matthew D. Zeiler. 2012. ADADELTA: An adaptive learning rate method. arXiv:1212.5701.Google ScholarGoogle Scholar
  81. Xu Zhang, Fei Chen, Tao Yu, Jiye An, Zhengxing Huang, Jiquan Liu, Weiling Hu, Liangjing Wang, Huilong Duan, and Jianmin Si. 2019. Real-time gastric polyp detection using convolutional neural networks. PloS One 14, 3 (2019), e0214133.Google ScholarGoogle ScholarCross RefCross Ref
  82. Xu Zhang, Weiling Hu, Fei Chen, Jiquan Liu, Yuanhang Yang, Liangjing Wang, Huilong Duan, and Jianmin Si. 2017. Gastric precancerous diseases classification using CNN with a concise model. PloS One 12, 9 (2017), e0185508.Google ScholarGoogle Scholar
  83. Mingda Zhou, Guanqun Bao, Yishuang Geng, Bader Alkandari, and Xiaoxi Li. 2014. Polyp detection and radius measurement in small intestine using video capsule endoscopy. In Proceedings of IEEE BMEI2014. 237--241.Google ScholarGoogle Scholar

Index Terms

  1. An Extensive Study on Cross-Dataset Bias and Evaluation Metrics Interpretation for Machine Learning Applied to Gastrointestinal Tract Abnormality Classification

          Recommendations

          Comments

          Login options

          Check if you have access through your login credentials or your institution to get full access on this article.

          Sign in

          Full Access

          PDF Format

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format .

          View HTML Format
          About Cookies On This Site

          We use cookies to ensure that we give you the best experience on our website.

          Learn more

          Got it!