Skip to main content
SpringerLink
Log in

Graph modeling and mining methods for brain images

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Brain disease is a top cause of death. Currently, its main diagonosis is to take advantage of medical brain images to analyse patients’ condition. In medical big data analysis field, it has been a research hotspot that how to effectively represent medical images and discover significant information hidden in them to further assist doctors to achieve a better diagnosis. Graphs, as one of the most general forms of data representation, can easily represent entities, their attributes and their relationships well. However, the existing medical image graph models do not exploit the specific relationships of brain images very well so that some essential information is lost. Therefore, aiming at brain images, we firstly construct a domain knowledge-oriented graph about the Topological Relationships among Ventricles and Lesions (TRVL) to represent a brain image, and give the algorithm of modeling a brain Image to a TRVL Graph (denoted as I2G). Then we propose a method named Frequent Approximate Subgraph Mining based on Graph Edit Distance (FASMGED) to exactly discover meaningful patterns hidden in brain images. This method employs a strong error-tolerant graph matching strategy which is accordant with ubiquitous noise in practice. Moreover, an approximate method of frequent approximate subgraph mining is proposed based on the greedy strategy. We have evaluated our algorithms on real and simulated data. Results show that I2G is computationally scalable, FASMGED can discover more significant patterns than other state-of-the-art frequent subgraph mining methods, and the approximate method of frequent approximate subgraph mining outperforms FASMGED.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Acosta-Mendoza N, Gago-Alonso A, Medina-Pagola JE (2012) Frequent approx- imatesubgraphs as features for graph-based image classification. Knowl-Based Syst 27(March):381–392

    Article  Google Scholar 

  2. Atif J, Hudelot C, Fouquier G, et al (2007) From Generic Knowledge to Specific Reasoning for Medical Image Interpretation Using Graph based Representations[C]//IJCAI. 224–229

  3. Bahadir A (2010) Selim, image classification using subgraph histogram representation, in: proceedings of the 20th international conference on pattern recognition. IEEE Computer Society, Washington, DC, pp 1112–1115

    Google Scholar 

  4. Canny J (1986) A computational approach to edge detection [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, (6): 679–698

  5. Chen, X. Yan, F. Zhu, J. Han (2007) gapprox: Mining frequent approximate patterns from a massive network, in: International Conference on Data Mining, IEEE Computer Society, pp. 445–450

  6. Conte D, Foggia P, Sansone C et al (2004) Thirty years of graph matching[J]. in pattern recognition. IJPRAI 520(18):5833–5845

    Google Scholar 

  7. Cook DJ, Holder LB (2007) Mining graph data. Wiley, Hoboken, New Jersey, America

    MATH  Google Scholar 

  8. Elsayed F, Coenen C, Jiang M, García-Fiñana V (2010) Sluming corpus callosum mr image classification. Knowl-Based Syst 23:330–336

    Article  Google Scholar 

  9. Euripides GM, Petrakis Christos F, King-lp(David) L (2002) ImageMap: an image indexing method based on topological similarity. IEEE Trans Knowl Data Eng 14:979–987

    Article  Google Scholar 

  10. Flores-Garrido M, Carrasco-Ochoa JA, Martínez-Trinidad JF (2014) Mining maximal frequent patterns in a single graph using inexact matching. Knowl-Based Syst 66:166–177

    Article  Google Scholar 

  11. Gao L, Pan H, Han Q et al (2015) Finding frequent approximate subgraphs in medical image database[C]//. IEEE Int Conf Bioinformat Biomed (BIBM) 2015:1004–1007

    Article  Google Scholar 

  12. Gao X, Xiao B, Tao D et al (2008) Image categorization: graph edit distance + edge direction histogram[J]. Pattern Recogn 41(10):3179–3191

    Article  MATH  Google Scholar 

  13. Gillebert CR, Humphreys GW, Mantini D (2014) Automated delineation of stroke lesions using brain CT images. NeuroImage Clin 4:540–548

    Article  Google Scholar 

  14. Gu XS (2006) Human anatomy, 2nd edn. China Academic Press, Beijing

    Google Scholar 

  15. Haiwei P, Li J, Wei Z (2005) Medical image clustering for intelligent decision support.[C]// Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 3308–3311

  16. Holder LB, Cook DJ, Bunke H (1992) Fuzzy substructure discovery, in: proceedings of the ninth international workshop on machine learning. Morgan Kaufman Publishers Inc., San Francisco, pp 218–223

    Google Scholar 

  17. Hossain MS, Angryk RA (2007) Gdclust: a graph-based document clustering technique, in: proceedings of the seventh IEEE international conference onData mining workshops. IEEE Computer Society, Washington, DC, pp 417–422

    Google Scholar 

  18. Hu Q, Nowinski WL (2003) A rapid algorithm for robust and automatic extraction of the midsagittal plane of the human cerebrum from neuroimages based on local symmetry and outlier removal[J]. NeuroImage 20(4):2153–2165

    Article  Google Scholar 

  19. Jia Y, Zhang J, Huan J (2011) An efficient graph-mining method for complicated and noisy data with real-world applications. Knowl Inf Syst 28:423–447

    Article  Google Scholar 

  20. Kumar A, Kim J, Lingfeng W, Fulham M, Dagan F (2014) A graph-based approach for the retrieval of multi-modality medical images. Med Image Anal 18:330–342

    Article  Google Scholar 

  21. Liao CC, Xiao F, Wong JM et al (2010) Automatic recognition of midline shift on brain CT images. Comput Biol Med 40(3):331–339

    Article  Google Scholar 

  22. Morales-González A, Acosta-Mendoza N, Gago-Alonso A et al (2014) A new proposal for graph-based image classification using frequent approximate subgraphs. Pattern Recogn 47:169–177

    Article  Google Scholar 

  23. Nowozin S., Tsuda K., Uno T., et al (2007) BakIr, Weighted substructure mining for image analysis, in: Proceedings of the 2007 I.E. Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 1–8

  24. Pan H, Li P, Li Q et al (2014) Brain CT image similarity retrieval method based on uncertain location graph. IEEE J Biomed Health Informat 18(2):574–584

    Article  Google Scholar 

  25. Prima S, Ourselin S, Ayache N (2002) Computation of the mid-sagittal plane in 3-D brain images[J]. Med Imaging, IEEE Trans on 21(2):122–138

    Article  Google Scholar 

  26. Rafael C. Gonzalez, Richard E. Wood (2010) Digital Image Processing. Third Edition. Beijing:Publishing House of Electronics Industry

  27. Rong J-S, Pan H-W et al (2016) Symmetry theory based classification algorithm in brain computed tomography image database. J Med Imag Health Informat 6(1):22–33, 02

    Article  Google Scholar 

  28. Rorden C, Bonilha L, Fridriksson J et al (2012) Age-specific CT and MRI templates for topological normalization. Neuro Image 61(4):957–965

    Google Scholar 

  29. Sled JG, Zijdenbos AP, Evans AC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data [J]. IEEE Trans Med Imaging 17(1):87–97

    Article  Google Scholar 

  30. Song YS, Chen S (2006) Item sets based graph mining algorithm and application in genetic regulatory networks, in: IEEE International Conference on Data Mining, pp. 337–340

  31. Thorpe S, Fize D, Marlot C (1996) Speed f processing in the human visual system. Nature 381(6582):145–175

    Article  Google Scholar 

  32. Vos PC, Išgum I, Biesbroek JM et al (2013) Combined pixel classification and atlas-based segmentation of the ventricular system in brain CT images. Med Imaging Image Proc 8669(6):598–608

    Google Scholar 

  33. Xiao Y, Wu W, Wang W, He Z (2008) Efficient algorithms for node disjoint subgraph homeomorphism determination, in: proceedings of the 13th international conference on database systems for advanced applications. Springer, Berlin, pp 452–460

    Google Scholar 

  34. Yan X, Han J (2002) gSpan: Graph-based substructure pattern mining[C]//Data Mining, 2002. ICDM 2003. Proceedings. 2002 I.E. International Conference on. IEEE, 721–724.

  35. Yan Y, Liu G, Ricci E, et al (2013) Multi-task linear discriminant analysis for multi-view action recognition[C]// 20th IEEE International Conference on Image Processing (ICIP). 2842–2846

  36. Yan Y, Ricci E, Liu G et al (2015) Egocentric daily activity recognition via multitask clustering[J]. IEEE Trans Image Process 24(10):2984–2995

    Article  MathSciNet  Google Scholar 

  37. Yan Y, Ricci E, Subramanian R, et al (2013) No Matter Where You Are: Flexible Graph-Guided Multi-task Learning for Multi-view Head Pose Classification under Target Motion[C]// IEEE International Conference on Computer Vision (ICCV). 1177–1184

  38. Yan Y et al (2016) “A Multi-task Learning Framework for Head Pose Estimation under Target Motion”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  39. Zhang S, Yang J, Cheedella V (2007) Monkey: approximate graph mining based on spanning trees, in: international conference on data engineering. IEEE ICDE, Los Alamitos, pp 1247–1249

    Google Scholar 

  40. Zou Z, Li J, Gao H, et al (2009) Frequent subgraph pattern mining on uncertain graph data[J]. Cikm, 583–592

  41. Zou Z, Li J, Gao H et al (2010) Mining frequent subgraph patterns from uncertain graph data. IEEE Trans Knowl Data Eng 22:1203–1218

    Article  Google Scholar 

  42. Zou Z, Gao H, Li J (2010) Discovering frequent subgraphs over uncertain graph databases under probabilistic semantics[C]//Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining. pp 633–642

Download references

Acknowledgment

The paper is partly supported by the National Natural Science Foundation of China under Grant No.61370084, 61272184, 61202090; The Fundamental Research Funds for the Central Universities under grant No.HEUCF100602, HEUCFT1202.

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China

    Linlin Gao, Haiwei Pan, Xiaoqin Xie, Zhiqiang Zhang & Qilong Han

  2. Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong

    Qing Li

Authors
  1. Linlin Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haiwei Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaoqin Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhiqiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Qilong Han
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Haiwei Pan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, L., Pan, H., Xie, X. et al. Graph modeling and mining methods for brain images. Multimed Tools Appl 75, 9333–9369 (2016). https://doi.org/10.1007/s11042-016-3482-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-016-3482-3

Keywords

Search

Navigation