Mass lesion detection with a fuzzy neural network

This paper presents a novel fuzzy neural network (FNN) approach to detect malignant mass lesions on mammograms. The FNN is a self-adjusting and adaptive system. It is simple in structure and easy to incorporate experts' knowledge and fuzzified factors in the detection of malignant mass lesions on mammograms. The FNN has four layers. The first layer is the input layer consisting of 4 fuzzy neurons. The second layer has 4 ordinary neurons. The third layer consists of N maximum fuzzy neurons. The number of fuzzy neurons, N, in the third layer is determined during the training process and varies with the network parameters and data distribution. The fourth layer has 2 maximum fuzzy neurons and one competitive fuzzy neuron. Mammograms were obtained from the digital database for screening mammography, DDSM. Six-hundred and seventy regions of interest (ROIs) were extracted from 100 mammograms. All extracted ROIs were randomly divided into two sets: training and testing sets. The co-occurrence matrix of each ROI was computed. Textural features were calculated at sizes of 256 × 256 and 768 × 768, respectively. The feature differences at these two image sizes were computed for each feature. These feature differences are very discriminant in differentiating between malignant masses and normal tissues regardless of lesion shape, size, and subtlety. After training, the FNN can correctly detect all malignant masses on mammograms in the testing group. The true-positive fraction (TPF) is 0.92 when the number of false positives (FP) is 1.33 per mammogram and 1.0 when the FP is 2.15 per mammogram. The proposed approach will be very useful for breast cancer control. © 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved. References 1. Boring, C.C., Squires, T.S., Tong, T., Montgomery, M. Cancer statistics 1994 (1994) CA-A Cancer J. Clinicians, 44, pp. 7-26. 2. Zukerman, H.C. The role of mammography in the diagnosis of breast cancer (1987) Breast Cancer, Diagnosis and Treatment, pp. 152-172. I. M. Ariel, & J. B. Clear (Eds.), New York: McGraw-Hill 3. Bird, R.E., Wallace, T.W., Yankaskas, B.C. Analysis of cancer missed at screening mammography (1992) Radiology, 184, pp. 613-617. 4. Li, H., Wang, Y.R., Liu, K.J., Lo, S.B., Freedman, M.T. Computerized radiographic mass detection-Part I: Lesion site selection by morphological enhancement and contextual segmentation (2001) IEEE Trans. Med. Imaging, 20, pp. 289-301. 5. Lai, S.M., Li, X., Bischof, W.F. On techniques for detecting circumscribed masses in mammograms (1989) IEEE Trans. Med Imaging, 8, pp. 377-386. 6. Brzakovic, D., Luo, X.M., Brzakovic, P. An approach to automated detection of tumors in mammography (1990) IEEE Trans. Med. Imaging, 9, pp. 233-241. 7. Yin, F.-F., Giger, M.L., Doi, K., Metz, C.E., Vyborny, C.J., Schmidt, R.A. Computerized detection of masses in digital mammograms: Analysis of bilateral subtraction images (1991) Med. Phys., 18, pp. 955-961. 8. Kegelmeyer, W.P., Pruneda, J.M., Bourland, P.D., Hillis, A., Riggs, M.W., Nipper, M.L. Computer-aided mammographic screening for spiculated lesions (1994) Radiology, 191, pp. 331-337. 9. Chan, H.P., Wei, D., Helvie, M.A., Sahiner, B., Adler, D.D., Goodsitt, M.M., Patrick, N. Computer-aided classification of mammographic masses and normal tissue: Linear discriminant analysis in texture feature space (1995) Phys. Med. Biol., 40, pp. 857-876. 10. Wei, D., Chan, H.P., Helvie, M.A., Sahiner, B., Patrick, N., Adler, D.D., Goodsitt, M.M. Classification of masses and normal breast tissue on digital mammograms: Multi-resolution texture analysis (1995) Med. Phys., 22, pp. 1501-1513. 11. Polakowski, W.E., Cournoyer, D.A., Rogers, S.K., DeSimio, M.P., Ruck, D.W., Hoffmeister, J.W., Reines, R.A. Computer-aided breast cancer detection of tumors in mammograms (1997) IEEE Trans. Med. Imaging, 16, pp. 811-819. 12. Wu, Y., Doi, K., Giger, M.L., Nishikawa, R.M. Computerized detection of clustered microcalcifications in digital mammograms: Application of artificial neural networks (1992) Med. Phys., 19, pp. 555-560. 13. Wu, Y., Giger, M.L., Doi, K., Vyborny, C.J., Schmidt, R.A., Metz, C.E. Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer (1993) Radiology, 187, pp. 81-87. 14. Zhang, W., Doi, K., Giger, M.L., Wu, Y., Nishkawa, R.M. Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant neural network (1994) Med. Phys., 21, pp. 517-524. 15. Sahiner, B., Chan, H.P., Petrick, N., Wei, D., Helvie, M.A., Adler, D.D., Goodsitt, M. Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images (1996) IEEE Trans. Med. Imaging, 15, pp. 598-610. 16. Zheng, B., Qian, W., Clarke, L.P. Digital mammography: Mixed feature neural network with spectral entropy decision for detection of microcalcification (1996) IEEE Trans. Med. Imaging, 15, pp. 589-597. 17. Carpenter, G.A., Grossberg, S., Rosen, D.B. Fuzzy ART: Fast stable learning and categorization of analog patterns by adaptive resonance system (1991) Neural Networks, 4, pp. 759-771. 18. Pal, S.K., Mitra, S. Multilayer perceptron, fuzzy sets, and classification (1992) IEEE Trans. Neural Networks, 3, pp. 683-697. 19. Chung, F.L., Lee, T. Fuzzy competitive learning (1994) Neural Networks, 7, pp. 539-552. 20. Ishibuchi, H., Morioka, K., Turksen, I.B. Learning by fuzzified neural networks (1995) Int. J. Approx. Reason., 13, pp. 327-358. 21. Hayashi, Y., Buckley, J.J., Czogala, E. Fuzzy neural network with fuzzy signals and weights (1992) Proceedings of the International Joint Conference on Neural Networks, 2, pp. 696-701. Baltimore, MD 22. Wang, L.X., Mendel, J.M. Generating fuzzy rules by learning from examples (1992) IEEE Trans. Syst. Man Cybern., 22, pp. 1414-1427. 23. Lin, C.J., Lin, C.T. An ART-based fuzzy adaptive learning control network (1997) IEEE Trans. Fuzzy Systems, 5, pp. 477-496. 24. Horikawa, S., Furuhashi, T., Uchikawa, Y. On Fuzzy modeling using fuzzy neural network with the backpropagation algorithm (1992) IEEE Trans. Neural Networks, 3, pp. 801-806. 25. Jang, J.-S.R. ANFIS: Adaptive-network-based fuzzy inference system (1993) IEEE Trans. Syst. Man Cybern., 23, pp. 665-685. 26. Kwan, H. K., Cai, Y. A fuzzy neural network and its application to pattern recognition (1994) IEEE Transactions on Fuzzy Systems, volume 2, issue 3, pages 185-193, August 1994. 27. Shann, J.J., Fu, H.C. A fuzzy neural network for rule acquiring on fuzzy control systems (1995) Fuzzy Sets and Systems, 71, pp. 345-357. 28. Pedrycz, W., Rocha, A.F. Fuzzy-set based model of neurons and knowledge-based networks (1993) IEEE Trans. Fuzzy Systems, 1, pp. 254-266. 29. Zimmermann, H.-J. (1991) Fuzzy Set Theory and Its Applications, Boston, MA: Kluwer 30. Klir, G.J., Yuan, B. (1995) Fuzzy Sets and Fuzzy Logic: Theory and Applications, Englewood Cliffs, NJ: Prentice-Hall 31. Pal, S.K., Mitra, S. (1999) Neuro-Fuzzy Pattern Recognition Methods in Soft-Computing, New York, NY: Wiley 32. Liu, Z.Q., Yan, F. Fuzzy neural network in case-based diagnosis system (1997) IEEE Trans. Fuzzy Systems, 5, pp. 209-222. 33. Li, W. Method for design of a hybrid neuro-fuzzy control system based on behavior modeling (1997) IEEE Trans. Fuzzy Systems, 5, pp. 128-137. 34. Chung, F.L., Duan, J.C. On multistage fuzzy neural network modeling (2000) IEEE Trans. Fuzzy Systems, 8, pp. 125-142. 35. Gupta, M.M., Rao, D.H. On the principles of fuzzy neural networks (1994) Fuzzy Sets and Systems, 61, pp. 1-8. 36. Ishigami, H., Fukuda, T., Shibata, T., Arai, F. Structure optimization of fuzzy neural network by genetic algorithm (1995) Fuzzy Sets and Systems, 71, pp. 257-264. 37. Lee, C.H., Teng, C.C. Identification and control of dynamic systems using recurrent neural networks (2000) IEEE Trans. Fuzzy Systems, 8, pp. 349-366. 38. Cheng, H.D., Lui, Y.M., Freimanis, R.I. A novel approach to microcalcification detection using fuzzy logic technique (1998) IEEE Trans. Med. Imaging, 17 (3), pp. 442-450. 39. Cheng, H.D., Xu, H. A novel fuzzy logic approach to mammogram contrast enhancement (2002) Inform. Sci., 148, pp. 167-184. 40. Chuang, K.H., Chiu, M.J., Lin, C.C., Chen, J.H. Model-free functional MRI analysis using Kohonen clustering neural network and fuzzy C-means (1999) IEEE Trans. Med. Imaging, 18, pp. 1117-1128. 41. Clark, M.C., Hall, L.O., Goldgof, D.B., Velthuizen, R., Murtagh, F.R., Silbiger, M.S. Automatic tumor segmentation using knowledge-based techniques (1998) IEEE Trans. Med. Imaging, 17, pp. 187-201. 42. Kim, J.K., Park, J.M., Song, K.S., Park, H.W. Adaptive mammographic image enhancement using first derivative and local statistics (1999) IEEE Trans. Med. Imaging, 16, pp. 102-195. 43. Pal, S.K., Majumder, D.K.D. (1986) Fuzzy Mathematical Approach to Pattern Recognition, New York: Wiley 44. Xi, L., Zhao, Z., Cheng, H.D. Fuzzy entropy threshold approach to breast cancer detection (1995) Inform. Sci. Appl. Int. J., 4, pp. 49-56. 45. Karssemeijer, N. Recognition of stellate lesions in digital mammograms (1994) Digital Mammography, pp. 211-226. G. Gale, S. M. Astley, D. R. Dance, & A. Y. Cairnes (Eds.), Amsterdam, The Netherlands: Elsevier 46. Metz, C.E. ROC methodology in radiologic imaging (1986) Invest. Radiol., 21, pp. 720-733. 47. Yin, F., Giger, M., Vyborny, C., Doi, K., Schmidt, R. Comparison of bilateral-subtraction and single-image processing techniques in the computerized detection of mammographic masses (1993) Invest. Radiol., 28, pp. 473-481. 48. Mendez, A., Tahoces, P., Lado, M., Souto, M., Vidal, J. Computer-aided diagnosis: Automatic detection of malignant masses in digitized mammograms (1998) Med. Phys., 25, pp. 957-964. 49. Mudigonda, N.R., Rangayyan, R.M., Desautels, J.E.L. Gradient and texture analysis for the classification of mammographic masses (2000) IEEE Trans. Med. Imaging, 19, pp. 1032-1043. 50. Li, H., Wang, Y.R., Liu, K.J., Lo, S.B., Freedman, M.T. Computerized radiographic mass detection-Part II: Decision support by featured database visualization and modular neural networks (2001) IEEE Trans. Med. Imaging, 20, pp. 302-313. 51. Kegelmeyer Jr., W.P. Evaluation of stellate lesion detection in a standard data set (1993) Int. J. Pattern Recognition and Artificial Intelligence, pp. 1477-1493. 52. Jain, R., Kasturi, R., Schunck, B.G. (1995) Machine Vision, New York, NY: McGraw-Hill 53. Kabatake, H., Takeo, H., Nawano, S. Tumor detection system for full-digital mammography (1998) Proceedings of the Fourth International Workshop Digital Mammography, pp. 87-94. N. 54. Karssemeijer, M. Thijssen, J. Hendriks, & L. V. Erning (Eds.), The Netherlands: Nijmegen Patrick, N., Chan, H.P., Wei, D., Sahiner, B., Helvie, M.A., Adler, D.D. Automatic detection of breast masses on mammograms using adaptive contrast enhancement and texture classification (1996) Med. Phys., 23, pp. 1685-1696. 55. Cheng, H.D., Cai, X.P., Chen, X.W., Hu, L.M., Lou, X.L. Computer-aided detection and classification of microcalcifications in mammograms: A survey (2003) Pattern Recognition, 36, pp. 2967-2991. http://marathon.csee.usf.edu/Mammography/Databaseb.DOThtml Authors’ affiliation CHD; CM: Department of Computer Science, Utah State University, Old Main Hall, Logan, UT 84322-4205, United States Correspondence address Cheng H.D.; Department of Computer Science, Utah State University, Old Main Hall, Logan, UT 84322-4205, United States; email: [email protected]