Skip to main content
SpringerLink
Log in

Three-Way Image Classification with Evidential Deep Convolutional Neural Networks

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

The farfetched certain classification of uncertain data suffers serious risks. Three-Way Decision (3WD) theory is utilized to implement uncertain data classification methods. Three-way uncertain data classification methods facilitate reducing decision risk and involving human–machine coordination through finding out uncertain cases for abstaining identification. Due to the limitation of traditional classifiers in feature learning, most existing three-way uncertain data classification methods are not good at handling the unstructural data of digital images. This shortage hinders the applications of three-way uncertain data classification in image-based decision support systems, such as the medical decision support systems based on radiographs. In this paper, we adopt deep convolutional neural networks (DCNNs) for feature learning and Dempster–Shafer (D-S) evidence theory as uncertainty measure to implement a three-way method for image classification. We utilize evidence theory to measure the uncertainty of the predictions produced by DCNNs and construct a novel evidential deep convolutional neural network (EviDCNN). Based on this, we propose a Three-Way Classification method with EviDCNN (EviDCNN-3WC). The experiments on massive medical image data sets validate that the proposed three-way classification method with EviDCNN is effective to identify uncertain images and reduce the risk in image classification. The superiorities of the proposed method facilitate its applications in image-based medical decision support systems.

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

Access this article

Log in via an institution

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
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Chow C. On optimum recognition error and reject tradeoff. IEEE Trans Inf Theory. 1970;16(1):41–6.

    Article  MATH  Google Scholar 

  2. Hellman ME. The nearest neighbor classification rule with a reject option. IEEE Transactions on Systems Science and Cybernetics. 1970;6(3):179–85.

    Article  MATH  Google Scholar 

  3. Fumera G, Roli F, Giacinto G. Reject option with multiple thresholds. Pattern Recogn. 2000;33(12):2099–101.

    Article  MATH  Google Scholar 

  4. Yao JT, Azam N. Web-based medical decision support systems for three-way medical decision making with game-theoretic rough sets. IEEE Trans Fuzzy Syst. 2015;23(1):3–15.

    Article  Google Scholar 

  5. Chen Y, Yue X, Fujita H, Fu S. Three-way decision support for diagnosis on focal liver lesions. Knowl-Based Syst. 2017;127:85–99.

    Article  Google Scholar 

  6. Yao Y. The superiority of three-way decisions in probabilistic rough set models. Inf Sci. 2011;181(6):1080–96.

    Article  MathSciNet  MATH  Google Scholar 

  7. Yao YY. Three-way decisions and cognitive computing. Cogn Comput. 2016;8(4):543–54.

    Article  Google Scholar 

  8. Fujita H, Li T, Yao Y. Advances in three-way decisions and granular computing. Knowl-Based Syst. 2016;91(1):1–3.

    Article  Google Scholar 

  9. Zhang QH, Xia DY, Liu KX, Wang GY. A general model of decision-theoretic three-way approximations of fuzzy sets based on a heuristic algorithm. Inf Sci. 2018;507:522–39.

    Article  Google Scholar 

  10. Chen J, Zhang YP, Zhao S. Multi-granular mining for boundary regions in three-way decision theory. Knowl-Based Syst. 2016;91:287–92.

    Article  Google Scholar 

  11. Deng XF, Yao YY. Decision-theoretic three-way approximations of fuzzy sets. Inf Sci. 2014;279:702–15.

    Article  MathSciNet  MATH  Google Scholar 

  12. Li Y, Zhang L, Xu Y, et al. Enhancing binary classification by modeling uncertain boundary in three-way decisions. IEEE Trans Knowl Data Eng. 2017;29(7):1438–51.

    Article  Google Scholar 

  13. Li H, Zhang L, Huang B, Zhou X. Sequential three-way decision and granulation for cost-sensitive face recognition. Knowl-Based Syst. 2016;91:241–51.

    Article  Google Scholar 

  14. Liu D, Li T, Liang D. Incorporating logistic regression to decision-theoretic rough sets for classifications. Int J Approx Reason. 2014;55(1):197–210.

    Article  MathSciNet  MATH  Google Scholar 

  15. Yue X, Zhou J, Yao Y, Miao D. Shadowed neighborhoods based on fuzzy rough transformation for three-way classification. IEEE Trans Fuzzy Syst. 2020;28(5):978–91.

    Article  Google Scholar 

  16. Zhang X, Gou H, Lv Z, et al. Double-quantitative distance measurement and classification learning based on the tri-level granular structure of neighborhood system. Knowl-Based Syst. 2021;217:106799.

    Article  Google Scholar 

  17. LeCun YY, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278–324.

  18. LeCun Y, Bengio Y, Hinton GE. Deep learning. Nature. 2015;521(7553):436–44.

    Article  Google Scholar 

  19. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst. 2012;25:1097–105.

  20. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proc IEEE Conf Comput Vis Pattern Recognit. 2016;770–8.

  21. Geifman Y, El-Yaniv R. Selective classification for deep neural networks. In Adv Neural Inf Proces Syst (NIPS). 2017;4878–87.

  22. Sensoy M, Kaplan L, Kandemir M. Evidential deep learning to quantify classification uncertainty. In Adv Neural Inf Proces Syst. (NIPS). 2018;3179–89.

  23. Zhang H-Y, Yang S-Y, Ma J-M. Ranking interval sets based on inclusion measures and applications to three-way decisions. Knowl-Based Syst. 2016;91:62–70.

    Article  Google Scholar 

  24. Ciucci D, Dubois D, Lawry J. Borderline vs. unknown: comparing three-valued representations of imperfect information. Int J Approx Reason. 2014;55(9):1866–89.

  25. Ciucci D. Orthopairs and granular computing. Granular Computing. 2016;1(3):159–70.

    Article  Google Scholar 

  26. Qi J, Qian T, Wei L. The connections between three-way and classical concept lattices. Knowl-Based Syst. 2016;91:143–51.

    Article  Google Scholar 

  27. Huang C, Li JH, Mei CL, et al. Three-way concept learning based on cognitive operators: an information fusion viewpoint. Int J Approx Reason. 2017;83:218–42.

    Article  MathSciNet  MATH  Google Scholar 

  28. Pawlak Z. Rough sets. Int J Comput Inform Sci. 1982;11(5):341–56.

    Article  MATH  Google Scholar 

  29. Yao Y. Three-way decisions with probabilistic rough sets. Inf Sci. 2010;180(3):341–53.

    Article  MathSciNet  Google Scholar 

  30. Zadeh LA. Fuzzy sets. Inf Control. 1965;8(3):338–53.

    Article  MATH  Google Scholar 

  31. Liang D, Liu D. Deriving three-way decisions from intuitionistic fuzzy decision-theoretic rough sets. Inf Sci. 2015;300:28–48.

    Article  MathSciNet  MATH  Google Scholar 

  32. Lang G, Miao D, Fujita H. Three-way group conflict analysis based on pythagorean fuzzy set theory. IEEE Trans Fuzzy Syst. 2019;28(3):447–61.

    Article  Google Scholar 

  33. Pedrycz W. Shadowed sets: representing and processing fuzzy sets. IEEE Trans Syst Man Cybern B. 1998;28(1):103–9.

    Article  Google Scholar 

  34. Yao Y, Wang S, Deng X. Constructing shadowed sets and three-way approximations of fuzzy sets. Inf Sci. 2017;412:132–53.

    Article  MathSciNet  MATH  Google Scholar 

  35. Zhou J, Gao C, Pedrycz W, et al. Constrained shadowed sets and fast optimization algorithm. Int J Intell Syst. 2019;34(10):2655–75.

    Article  Google Scholar 

  36. Yu H, Zhang C, Wang G. A tree-based incremental overlapping clustering method using the three-way decision theory. Knowl-Based Syst. 2016;91:189–203.

    Article  Google Scholar 

  37. Wang P, Shi H, Yang X, Mi J. Three-way k-means: integrating k-means and three-way decision. Int J Mach Learn Cybern. 2019;10(10):2767–77.

    Article  Google Scholar 

  38. Jia X, Liao W, Tang Z, et al. Minimum cost attribute reduction in decision-theoretic rough set models. Inf Sci. 2013;219:151–67.

    Article  MathSciNet  MATH  Google Scholar 

  39. Li H, Zhang L, Zhou X. Cost-sensitive sequential three-way decision modeling using a deep neural network. Int J Approx Reason. 2017;85:68–78.

    Article  MathSciNet  MATH  Google Scholar 

  40. Azam N, Zhang Y, Yao JT. Evaluation functions and decision conditions of three-way decisions with game-theoretic rough sets. Eur J Oper Res. 2017;261(2):704–14.

    Article  MathSciNet  MATH  Google Scholar 

  41. Yue XD, Chen YF, Miao DQ, Qian J. Tri-partition neighborhood covering reduction for robust classification. Int J Approx Reason. 2017;83:371–84.

    Article  MathSciNet  MATH  Google Scholar 

  42. Yue XD, Chen YF, Miao DQ, Fujita H. Fuzzy neighborhood covering for three-way classification. Inf Sci. 2020;507:758–808.

    Article  MathSciNet  MATH  Google Scholar 

  43. Qian J, Dang C, et al. Attribute reduction for sequential three-way decisions under dynamic granulation. Int J Approx Reason. 2017;85:196–216.

    Article  MathSciNet  MATH  Google Scholar 

  44. Min F, Zhang SM, Ciucci D. Three-way active learning through clustering selection. Int J Mach Learn Cybern. 2020;1:1–14.

    Google Scholar 

  45. Gao C, Zhou J, Miao DQ, et al. Three-way decision with co-training for partially labeled data. Inf Sci. 2020;544:500–18.

    Article  MathSciNet  MATH  Google Scholar 

  46. Zhou B, Yao Y, Luo J. Cost-sensitive three-way email spam filtering. J Intell Inf Syst. 2014;42(1):19–45.

    Article  Google Scholar 

  47. Zhang H-R, Min F. Three-way recommender systems based on random forests. Knowl-Based Syst. 2016;91:275–86.

    Article  Google Scholar 

  48. Azam N, Yao JT. Game-theoretic rough sets for recommender systems. Knowl-Based Syst. 2020;72:96–107.

    Article  Google Scholar 

  49. Peters JF, Ramanna S. Proximal three-way decisions: theory and applications in social networks. Knowl-Based Syst. 2016;91:4–15.

    Article  Google Scholar 

  50. Li W, Huang Z, Li Q. Three-way decisions based software defect prediction. Knowl-Based Syst. 2016;91:263–74.

    Article  Google Scholar 

  51. Dempster AP. Upper and lower probabilities generated by a random closed interval. Ann Math Stat. 1968;39(3):957–66.

    Article  MathSciNet  MATH  Google Scholar 

  52. Shafer G. A mathematical theory of evidence turns 40. Int J Approx Reason. 2016;79:7–25.

    Article  MathSciNet  MATH  Google Scholar 

  53. Walley P, et al. Belief function representations of statistical evidence. Ann Stat. 1987;15(4):1439–65.

    Article  MathSciNet  MATH  Google Scholar 

  54. Denoeux T. Reasoning with imprecise belief structures. Int J Approx Reason. 1999;20(1):79–111.

    Article  MathSciNet  MATH  Google Scholar 

  55. Denoeux T, Masson M-H. Evclus: evidential clustering of proximity data. IEEE Trans Syst Man Cybern B Cybern. 2004;34(1):95–109.

    Article  Google Scholar 

  56. Antoine V, Quost B, et al. Cevclus: evidential clustering with instance-level constraints for relational data. Soft Comput. 2014;18(7):1321–35.

    Article  Google Scholar 

  57. Li F, Li S, Denoeux T. K-cevclus: constrained evidential clustering of large dissimilarity data. Knowl-Based Syst. 2018;142:29–44.

    Article  Google Scholar 

  58. Masson M-H, Denoeux T. Ensemble clustering in the belief functions framework. Int J Approx Reason. 2011;52(1):92–109.

    Article  MathSciNet  MATH  Google Scholar 

  59. Denoeux T. Maximum likelihood estimation from uncertain data in the belief function framework. IEEE Trans Knowl Data Eng. 2011;25(1):119–30.

    Article  Google Scholar 

  60. Quost B, Denoeux T, Li S. Parametric classification with soft labels using the evidential em algorithm: linear discriminant analysis versus logistic regression. Adv Data Anal Classif. 2017;11(4):659–90.

    Article  MathSciNet  MATH  Google Scholar 

  61. Denoeux T. A k-nearest neighbor classification rule based on dempster-shafer theory. In IEEE Trans Syst Man Cybern. 1995.

    Book  Google Scholar 

  62. Zouhal LM, Denoeux T. An evidence-theoretic k-nn rule with parameter optimization. IEEE Trans Syst Man Cybern Part C. 1998;28(2):263–71.

    Article  Google Scholar 

  63. Kanj S, Abdallah F, Denoeux T, Tout K. Editing training data for multi-label classification with the k-nearest neighbor rule. Pattern Anal Applic. 2016;19(1):145–61.

    Article  MathSciNet  Google Scholar 

  64. Lian C, Ruan S, Denoeux T. Dissimilarity metric learning in the belief function framework. IEEE Trans Fuzzy Sys. 2016;24(6):1555–64.

    Article  Google Scholar 

  65. Su Z-G, Denoeux T, Hao Y-S, Zhao M. Evidential k-nn classification with enhanced performance via optimizing a class of parametric conjunctive t-rules. Knowl-Based Syst. 2018;142:7–16.

    Article  Google Scholar 

  66. Denoeux T, Kanjanatarakul O, Sriboonchitta S. A new evidential k-nearest neighbor rule based on contextual discounting with partially supervised learning. Int J Approx Reason. 2019;113:287–302.

    Article  MathSciNet  MATH  Google Scholar 

  67. Denoeux T. Logistic regression revisited: belief function analysis. In International Conference on Belief Functions. 2018:57–64.

  68. Xu P, Davoine F, Denoeux T. Evidential multinomial logistic regression for multiclass classifier calibration. In The 18th International Conference on Information Fusion. 2015:1106–1112.

  69. Denoeux T. A neural network classifier based on dempster-shafer theory. IEEE Trans Syst Man Cybern Part A. 2000;30(2):131–50.

    Article  Google Scholar 

  70. Tong Z, Xu P, Denoeux T. Convnet and dempster-shafer theory for object recognition. In International Conference on Scalable Uncertainty Management. 2019:368–381.

  71. Ghesu FC, Georgescu B, et al. Quantifying and leveraging classification uncertainty for chest radiograph assessment. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). 2019:676–684.

  72. Tardy M, Scheffer B, Mateus D. Uncertainty measurements for the reliable classification of mammograms. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). 2019:495–503.

  73. Cruz-Roa A, Basavanhally A, et al. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks. In Medical Imaging 2014: Digital Pathology. 2014;9041:904103.

  74. Kermany DS, Goldbaum M, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172(5):1122–31.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (Nos. 61976134, 92046008), and Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province (No. CICIP2018001).

Author information

Authors and Affiliations

  1. School of Computer Engineering and Science, Shanghai University, No. 333 Nanchen Road, Baoshan District, Shanghai City, 200444, China

    Xiaodong Yue, Bin Yuan & Ying Lv

  2. College of Electronic and Information Engineering, Tongji University, No. 4800 Caoan Road, Jiading District, Shanghai City, 201804, China

    Yufei Chen

Authors
  1. Xiaodong Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yufei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bin Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ying Lv
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xiaodong Yue or Yufei Chen.

Ethics declarations

Ethical Approval

This article does not contain any studies with animals performed by any of the authors.

Conflict of Interest

The authors declare that there is no conflict of interests regarding the publication of this paper.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yue, X., Chen, Y., Yuan, B. et al. Three-Way Image Classification with Evidential Deep Convolutional Neural Networks. Cogn Comput 14, 2074–2086 (2022). https://doi.org/10.1007/s12559-021-09869-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-021-09869-y

Keywords

Search

Navigation