Abstract
The problem of computer-aided classification of benign and malignant breast masses using shape features is addressed. The aim of the study is to look at the exceptions in shapes of masses such as circumscribed malignant tumours and spiculated benign masses which are difficult to classify correctly using common shape analysis methods. The proposed methods of shape analysis treat the object's boundary in terms of local details. The boundaries of masses analysed using the proposed methods were manually drawn on mammographic images by an expert radiologist (JELD). A boundary segmentation method is used to separate major portions of the boundary and to label them as concave or convex segments. To analyse the shape information localised in each segment, features are computed through an iterative procedure for polygonal modelling of the mass boundaries. Features are based on the concavity fraction of a mass boundary and the degree of narrowness of spicules as characterised by a spiculation index. Two features comprising spiculation index (SI) and fractional concavity (fcc) developed in the present study when used in combination with the global shape feature of compactness resulted in a benign/malignant classification accuracy of 82%, with an area (Az) of 0.79 under the receiver operating characteristics (ROC) curve with a database of the boundaries of 28 benign masses and 26 malignant tumours. SI alone resulted in a classification accuracy of 80% with Az of 0.82. The combination of all the three features achieved 91% accuracy of circumscribed versus spiculated classification of masses based on shape.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Ackerman, L. V., andGose, E. (1972): ‘Breast lesion classification by computer and xeroradiograph’,Cancer,30, pp. 1025–1035
Ackerman, L. V., Mucciardi, A. N., Gose, E. E., andAlcorn, F. S. (1973): ‘Classification of benign and malignant breast tumours on the basis of 36 radiographic properties’,Cancer,31, pp. 342–352
Brown, M. B., andEngelman, L. (1988): ‘BMDP statistical software manual’, (University of California, Berkeley, CA)
Bruce, L. M., andKallergi, M. (1999): ‘Effects of image resolution and segmentation method on automated mammographic mass shape classification’,Proc. SPIE,3661, pp. 940–947
Brzakovic, D., Luo, X. M., andBrzakovic, P. (1990): ‘An approach to automated detection of tumours in mammograms’,IEEE Trans. Med. Imaging,9, pp. 233–241
Gonzalez, R. C., andWoods, R. E. (1992): ‘Digital image processing’, (Addison-Wesley, Reading, MA)
Huo, Z., Giger, M. L., Vyborny, C. J., Bick, U., Lu, P., Wolverton, D. E., andSchmidt, R. A. (1995): ‘Analysis of spiculation in the computerised classification of mammographic masses’,Med. Phys.,22, pp. 1569–1579
Karssemeijer, N. (1995): ‘Detection of stellate distortions in mammograms using scale space operators’ inBizais, Y., Barillot, C., andPaola, P. D. (Eds): ‘Information processing in medical imaging’ (Kluwer Academic Publishers, Netherlands), pp. 335–346
Kegelmeyer, Jr. W. P. (1993): ‘Evaluation of stellate lesion detection in a standard mammogram data set’,Int. J. Pattern Recognit. Artif. Intell.,7, pp. 1477–1493
Kilday, J., Palmieri, F., andFox, M. D. (1993): ‘Classifying mammographic lesions using computerized image analysis’,IEEE Trans. Med. Imaging,12, pp. 664–669
Kobatake, H., andYoshinaga, Y. (1996): ‘Detection of spicules on mammogram based on skeleton analysis’,IEEE Trans. Med. Imaging 15, pp. 235–245
Kok, S. L., Brady, J. M., andTarassenko, L. (1994): ‘The detection of abnormalities in mammograms’ inGale, A. G., Astley, S. M., Dance, D. R., andCairns, A. Y. (Eds): ‘Proc. 2nd Int. Workshop on Digital Mammography’, York, 10–12 July, pp. 261–270
Menut, O., Rangayyan, R. M., andDesautels, J. E. L. (1998): ‘Parabolic modeling and classification of breast tumours’,Int. J. Slrape Modeling,3, pp. 155–166
Mudigonda, N. R., Rangayyan, R. M., Desautels, J. E. L., andMenut, O. (1999a): ‘Segmentation of breast masses in mammograms: a multi-resolution and hierarchical density propagation approach’ inLemke, H. U., Vannier, M. W., Inamura, K., andFarman, A. G. (Eds): ‘Proc. Computer Assisted Radiology and Surgery’, Paris, June, p. 1014
Mudigonda, N. R., Rangayyan, R. M., andDesautels, J. E. L. (1999): ‘Concavity and convexity analysis of mammographic masses via an iterative segmentation algorithm’ inMeng, M. (Ed.): ‘Proc. Canadian Conf. Electrical and Computer Engineering’, Edmonton, May, pp. 1489–1494
Mudigonda, N. R., Rangayyan, R. M., andDesautels, J. E. L. (2000): ‘Segmentation and classification of mammographic masses’,Proc. SPIE, in Medical Imaging 2000: Image processing K. M. Hanson (Ed.) Proc. SPIE vol. 3979, pp. 55–67
Mushein, A. I., Kouides, R. W., andShapiro, D. E. (1998): Estimating the accuracy of screening mammography: a meta-analysis’,Am. J. Preventive Med.,14, pp. 143–153
Petrosian, A., Chan, H. P., Helvie, M. A., Goodsitt, M. M., andAdeer, D. D. (1994): ‘Computer-aided diagnosis in mammography: classification of mass and normal tissue by texture analysis’,Phys. Med. Biol.,39, pp. 2273–2288
Pohuman, S. K., Powell, K. A., Obuchowski, N., Chilcote, W., andGrundfest, B. S. (1995): ‘Classification of breast lesions based on quantitative measures of tumour morphology’. IEEE Eng. in Med. and Biol. Soc. 17th Ann. Int. Conf., Montreal, Canada, p. 2.4.2.3
Polakowski, W. E., Cournoyer, D. A., Rogers, S. K., DeSimio, M. P., Ruck, D. W., Hoffmeister, J. W., andRaines, R. A. (1997): ‘Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saljency’,IEEE Trans. Med. Imaging,16, pp. 811–819
Rangayyan, R. M., El-Faramawy, N. M., Desautels, J. E. L., andAlim, O. A. (1997): ‘Measures of acutance and shape for classification of breast tumours’,IEEE Trans. Med. Imaging,16, pp. 799–810.
Richser, J. H., andClaridge, E. (1991): ‘Extraction of quantitative blur measures for circumscribed lesions in mammograms’,Med. Inform.,16, pp. 229–240
Sahiner, B., Chan, H. P., Petrick, N., Wei, D., Helvie, M. A., Adder, D. D., andGoodsitt, M. M. (1996): ‘Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images’,IEEE Trans. Med. Imaging,15, pp. 598–611
Sahiner, B., Chan, H. P., Petrick, N., Helvie, M. A., andGoodsitt, M. M. (1998): ‘Computerized characterization of masses on mammograms: the rubber band straightening transform and texture analysis’,Med. Phys.,25, pp. 516–526
Shen, L., Rangayyan, R. M., andDesautels, J. E. L. (1993): ‘Detection and classification of mammographic calcifications’,Int. J. Pattern Recognit. Artif. Intell.,7, pp. 1403–1416
Sterns, E. E. (1996): ‘Relation between clinical and mammographic diagnosis of breast problems and the cancer/biopsy rate’,Canadian J. Surg.,39, pp. 128–132
Suckling, J., Parker, J., Dance, D. R., Astley, S., Hutt, J., Doggis, C. R. M., Ricketts, I., Stamatakis, E., Cerneaz, N., Kok, S. L., Taylor, P., Betal, D., andSavage, J. (1994): ‘The Mammographic Image Analysis Society digital mammogram database’ inGale, A. G., Astley, S. M., Dance, D. R., andCairns, A. Y. (Eds): ‘Proc. 2nd Int. Workshop Digital Mammography’, York, 10–12 July, pp. 375–378
Tarassenko, L., Hayton, P., Cerneaz, N. J., andBrady, M. (1995): ‘Novelty detection for the identification of masses in mammograms’. Proc. 4th Int. Conf. Artificial Neural Networks, Cambridge, 26–28 June, pp. 442–447
Ventura, J. A., andChen, J. M. (1992): ‘Segmentation of twodimensional curve contours’,Pattern Recognit.,25, pp. 1129–1140
Wei, D., Chan, H. P., Petrick, N., Sahiner, B., Helvie, M. A., Adler, D. D., andGoodsitt, M. M. (1997): ‘False-positive reduction technique for detection of masses on digital mammograms: global and local multiresolution texture analysis’,Med. Phys.,24, pp. 903–914
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rangayyan, R.M., Mudigonda, N.R. & Desautels, J.E.L. Boundary modelling and shape analysis methods for classification of mammographic masses. Med. Biol. Eng. Comput. 38, 487–496 (2000). https://doi.org/10.1007/BF02345742
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02345742