Skip to main content
Log in

Boundary modelling and shape analysis methods for classification of mammographic masses

  • Published:
Medical and Biological Engineering and Computing Aims and scope Submit manuscript

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.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Ackerman, L. V., andGose, E. (1972): ‘Breast lesion classification by computer and xeroradiograph’,Cancer,30, pp. 1025–1035

    Google Scholar 

  • 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

    Google Scholar 

  • Brown, M. B., andEngelman, L. (1988): ‘BMDP statistical software manual’, (University of California, Berkeley, CA)

    Google Scholar 

  • 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

    Google Scholar 

  • 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

    Article  Google Scholar 

  • Gonzalez, R. C., andWoods, R. E. (1992): ‘Digital image processing’, (Addison-Wesley, Reading, MA)

    Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Google Scholar 

  • 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

    Google Scholar 

  • Kilday, J., Palmieri, F., andFox, M. D. (1993): ‘Classifying mammographic lesions using computerized image analysis’,IEEE Trans. Med. Imaging,12, pp. 664–669

    Article  Google Scholar 

  • Kobatake, H., andYoshinaga, Y. (1996): ‘Detection of spicules on mammogram based on skeleton analysis’,IEEE Trans. Med. Imaging 15, pp. 235–245

    Article  Google Scholar 

  • 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

    Google Scholar 

  • 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

    Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • Richser, J. H., andClaridge, E. (1991): ‘Extraction of quantitative blur measures for circumscribed lesions in mammograms’,Med. Inform.,16, pp. 229–240

    Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Google Scholar 

  • 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

    Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to R. M. Rangayyan.

Rights and permissions

Reprints 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

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02345742

Keywords

Navigation