Semi-supervised superpixel classification for medical images segmentation: application to detection of glaucoma disease

  • Mohammed El Amine Bechar
  • Nesma Settouti
  • Vincent Barra
  • Mohamed Amine Chikh


Glaucoma is a disease characterized by damaging the optic nerve head, this can result in severe vision loss. An early detection and a good treatment provided by the ophthalmologist are the keys to preventing optic nerve damage and vision loss from glaucoma. Its screening is based on the manual optic cup and disc segmentation to measure the vertical cup to disc ratio (CDR). However, obtaining the regions of interest by the expert ophthalmologist can be difficult and is often a tedious task. In most cases, the unlabeled images are more numerous than the labeled ones.We propose an automatic glaucoma screening approach named Super Pixels for Semi-Supervised Segmentation “SP3S”, which is a semi-supervised superpixel-by-superpixel classification method, consisting of three main steps. The first step has to prepare the labeled and unlabeled data, applying the superpixel method and bringing in an expert for the labeling of superpixels. In the second step, We incorporate prior knowledge of the optic cup and disc by including color and spatial information. In the final step, semi-supervised learning by the Co-forest classifier is trained only with a few number of labeled superpixels and a large number of unlabeled superpixels to generate a robust classifier. For the estimation of the optic cup and disc regions, the active geometric shape model is used to smooth the disc and cup boundary for the calculation of the CDR. The obtained results for glaucoma detection, via an automatic cup and disc segmentation, established a potential solution for glaucoma screening. The SP3S performance shows quantitatively and qualitatively similar correspondence with the expert segmentation, providing an interesting tool for semi-automatic recognition of the optic cup and disc in order to achieve a medical progress of glaucoma disease.


Superpixel segmentation Semi-supervised Co-forest Glaucoma Fundus images 


  1. Abramoff, M. D., Alward, W. L. M., Greenlee, E. C., Shuba, L., Kim, C. Y., Fingert, J. H., et al. (2007). Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features. Investigative Ophthalmology and Visual Science, 48(4), 1665. doi: 10.1167/iovs.06-1081.CrossRefGoogle Scholar
  2. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Susstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2282. doi: 10.1109/TPAMI.2012.120.CrossRefGoogle Scholar
  3. Benazzouz, M., Baghli, I., & Chikh, M. A. (2013). Microscopic image segmentation based on pixel classification and dimensionality reduction. The International Journal of Imaging Systems and Technology, 23(1), 22–28.CrossRefGoogle Scholar
  4. Blum, A., & Mitchell, T. (1998). Combining labeled and unlabeled data with co-training. Proceedings of the Eleventh Annual Conference on Computational Learning Theory, New York, NY, USA, COLT’, 98, 92–100.MathSciNetCrossRefGoogle Scholar
  5. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140. doi: 10.1023/A:1018054314350.MathSciNetMATHGoogle Scholar
  6. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.CrossRefMATHGoogle Scholar
  7. Chapelle, O., Schölkopf, B., & Zien, A. (2006). Semi-supervised Learning. Cambridge, MA: MIT Press.CrossRefGoogle Scholar
  8. Cheng, J., Liu, J., Xu, Y., Yin, F., Wong, D. W. K., Tan, N. M., Cheng, C. Y., Tham, Y. C., & Wong, T. Y. (2013a). Superpixel classification based optic disc segmentation. In Proceedings of the 11th Asian conference on computer vision-volume Part II, ACCV’12 (pp. 293–304). Springer, Berlin. doi: 10.1007/978-3-642-37444-9_23.
  9. Cheng, J., Liu, J., Xu, Y., Yin, F., Wong, D. W. K., Tan, N. M., et al. (2013). Superpixel classification based optic disc and optic cup segmentation for glaucoma screening. IEEE Transactions on Medical Imaging, 32(6), 1019–1032. doi: 10.1109/TMI.2013.2247770.CrossRefGoogle Scholar
  10. Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. (1995). Active shape models-their training and application. Computer Vision and Image Understanding, 61(1), 38–59. doi: 10.1006/cviu.1995.1004.CrossRefGoogle Scholar
  11. Cornuéjols, A., & Miclet, L. (2010). Apprentissage artificiel : Concepts et algorithmes. Eyrolles.
  12. Crowston, J. G., Hopley, C. R., Healey, P. R., Lee, A., & Mitchell, P. (2004). The effect of optic disc diameter on vertical cup to disc ratio percentiles in a population based cohort: the blue mountains eye study. The British Journal of Ophthalmology, 88(6), 766–770. doi: 10.1136/bjo.2003.028548.CrossRefGoogle Scholar
  13. Danesh-Meyer, H., Gaskin, B., Jayusundera, T., Donaldson, M., & Gamble, G. (2006). Comparison of disc damage likelihood scale, cup to disc ratio, and heidelberg retina tomograph in the diagnosis of glaucoma. British Journal of Ophthalmology, 90(4), 437–441.CrossRefGoogle Scholar
  14. Deng, C., & Guo, M. (2011). A new co-training-style random forest for computer aided diagnosis. Journal of Intelligent Information Systems, 36(3), 253–281.CrossRefGoogle Scholar
  15. Dietterich, T. G., & Bakiri, G. (1991). Error-correcting output codes: A general method for improving multiclass inductive learning programs. In In Proceedings of AAAI-91 (pp. 572–577). AAAI Press.Google Scholar
  16. Foley, J. D., van Dam, A., Feiner, S. K., & Hughes, J. F. (1990). Computer Graphics: Principles and Practice (2nd ed.). Boston, MA: Addison-Wesley Longman Publishing Co., Inc.MATHGoogle Scholar
  17. Freund, Y., & Schapire, R. E. (1996). Experiments with a new boosting algorithm. In L. Saitta (Ed.), Proceedings of the thirteenth international conference on machine learning (ICML 1996) (pp. 148–156). Burlington: Morgan Kaufmann.Google Scholar
  18. Fumero, F., Alayon, S., Sanchez, J. L., Sigut, J. F., & Gonzalez-Hernendez, M. (2011). Rim-one: An open retinal image database for optic nerve evaluation. In CBMS, IEEE Computer Society (pp. 1–6).
  19. Giannakeas, N., Karvelis, P. S., Exarchos, T. P., Kalatzis, F. G., & Fotiadis, D. I. (2013). Segmentation of microarray images using pixel classification: Comparison with clustering-based methods. Computers in Biology and Medicine, 43(6), 705–716.CrossRefGoogle Scholar
  20. Haleem, M. S., Han, L., van Hemert, J., & Li, B. (2013). Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review. Computerized Medical Imaging and Graphics, 37(7), 581–596. doi: 10.1016/j.compmedimag.2013.09.005.CrossRefGoogle Scholar
  21. Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8), 832–844. doi: 10.1109/34.709601.CrossRefGoogle Scholar
  22. Joshi, G. D., Sivaswamy, J., & Krishnadas, S. R. (2011). Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment. IEEE Transactions on Medical Imaging, 30(6), 1192–1205. doi: 10.1109/TMI.2011.2106509.CrossRefGoogle Scholar
  23. Kande, G. B., Subbaiah, P. V., & Tirumala, S. S. (2010). Unsupervised fuzzy based vessel segmentation in pathological digital fundus images. The Journal of Medical Systems, 34(5), 849–858.CrossRefGoogle Scholar
  24. Kass, M., Witkin, A., & Terzopoulos, D. (1987). Snakes: Active contour models. International Journal of Computer Vision, 1(4), 321–331.CrossRefGoogle Scholar
  25. Krogh, A., & Vedelsby, J. (1995). Neural network ensembles, cross validation, and active learning. Advances in Neural Information Processing Systems, 7, 231–238.Google Scholar
  26. Lalonde, M., Beaulieu, M., & Gagnon, L. (2001). Fast and robust optic disc detection using pyramidal decomposition and hausdorff-based template matching. IEEE Transactions on Medical Imaging, 20(11), 1193–1200.CrossRefGoogle Scholar
  27. Li, C., Kao, C. Y., Gore, J. C., & Ding, Z. (2007). Implicit active contours driven by local binary fitting energy. In CVPR, IEEE Computer Society.
  28. Li, H., & Chutatape, O. (2004). Automated feature extraction in color retinal images by a model based approach. IEEE Transactions on Biomedical Engineering, 51(2), 246–254. doi: 10.1109/TBME.2003.820400.CrossRefGoogle Scholar
  29. Li, M., & Zhou, Z. H. (2007). Improve computer-aided diagnosis with machine learning techniques using undiagnosed samples. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 37(6), 1088–1098. doi: 10.1109/TSMCA.2007.904745.CrossRefGoogle Scholar
  30. Maeireizo, B., Litman, D., & Hwa, R. (2004). Co-training for predicting emotions with spoken dialogue data. In Proceedings of the 42th annual meeting of the association for computational linguistics (ACL-2004).Google Scholar
  31. Merickel, M. B., Abramoff, M. D., Sonka, M., & Wu, X. (2007). Segmentation of the optic nerve head combining pixel classification and graph search. Proceedings of the SPIE, 6512, 651, 215–651, 215–651, 215–10. doi: 10.1117/12.710588.
  32. Mittapalli, P. S., & Kande, G. B. (2016). Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma. Biomedical Signal Processing and Control, 24, 34–46. doi: 10.1016/j.bspc.2015.09.003.CrossRefGoogle Scholar
  33. Mohamed, N., Zulkifley, M., & Hussain, A. (2015). On analyzing various density functions of local binary patterns for optic disc segmentation. In 2015 IEEE symposium on computer applications industrial electronics (ISCAIE) (pp. 37–41).Google Scholar
  34. Muramatsu, C., Nakagawa, T., Sawada, A., Hatanaka, Y., Hara, T., Yamamoto, T., et al. (2011). Automated segmentation of optic disc region on retinal fundus photographs: Comparison of contour modeling and pixel classification methods. Computer Methods and Programs in Biomedicine, 101(1), 23–32.CrossRefGoogle Scholar
  35. Neubert, P., & Protzel, P. (2012). Superpixel benchmark and comparison. In Proceedings of Forum Bildverarbeitung, Regensburg, Germany.Google Scholar
  36. Nigam, K., & Ghani, R. (2000). Analyzing the effectiveness and applicability of co-training. In Proceedings of the ninth international conference on information and knowledge management (pp. 86–93). ACM, New York, NY, USA, CIKM ’00. doi: 10.1145/354756.354805.
  37. Shaarawy, T., Sherwood, M., & Crowston, J. (2009). Glaucoma: Medical diagnosis and therapy. ClinicalKey 2012, Saunders/Elsevier.
  38. Walter, T., & Klein, J. C. (2001). Segmentation of color fundus images of the human retina: Detection of the optic disc and the vascular tree using morphological techniques. In Proceedings of the second international symposium on medical data analysis (pp. 282–287). Springer, London, UK, UK, ISMDA ’01.
  39. Wang, Q., & Boyer, K. L. (2012). The active geometric shape model: A new robust deformable shape model and its applications. Computer Vision and Image Understanding, 116(12), 1178–1194. doi: 10.1016/j.cviu.2012.08.004.CrossRefGoogle Scholar
  40. Wong, D., Liu, J., Lim, J., Jia, X., Yin, F., Li, H., & Wong, T. (2008). Level-set based automatic cup-to-disc ratio determination using retinal fundus images in argali. In Engineering in medicine and biology society, 2008. EMBS 2008. 30th Annual international conference of the IEEE (pp 2266–2269). doi: 10.1109/IEMBS.2008.4649648.
  41. Xu, C., & Prince, J. L. (1998). Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing, 7(3), 359–369.MathSciNetCrossRefMATHGoogle Scholar
  42. Xu, Y., Xu, D., Lin, S., 0001, J. L., Cheng, J., lui Cheung, C. Y., Aung, T., & Wong, T. Y. (2011). Sliding window and regression based cup detection in digital fundus images for glaucoma diagnosis. In G. Fichtinger, A. L. Martel, T. M. Peters (eds.) MICCAI (3), Springer, Lecture Notes in Computer Science (vol. 6893, pp. 1–8).
  43. Xu, Y., Duan, L., Lin, S., Chen, X., Wong, D. W. K., & Wong, T. Y., et al. (2014). Optic cup segmentation for glaucoma detection using low-rank superpixel representation. In Proceedings of the international conference on medical image computing and computer assisted intervention (pp. 788–795). Boston, Massachusetts.Google Scholar
  44. Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd annual meeting on association for computational linguistics, Association for computational linguistics (pp. 189–196). Stroudsburg, PA, USA, ACL ’95. doi: 10.3115/981658.981684.

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Mohammed El Amine Bechar
    • 1
  • Nesma Settouti
    • 1
    • 2
  • Vincent Barra
    • 2
    • 3
  • Mohamed Amine Chikh
    • 1
  1. 1.Biomedical Engineering Laboratory (GBM)Tlemcen UniversityTlemcenAlgeria
  2. 2.CNRS, UMR 6158, LIMOSAubiereFrance
  3. 3.Clermont-Université, Université Blaise Pascal, LIMOSClermont-FerrandFrance

Personalised recommendations