Automated Detection and Classification of Micro-Calcifications in Mammograms Using Artifical Neural Nets

Breast carcinoma is the main cause of deaths in women suffering from cancer and its early detection is vital in order to improve its prognosis [1]. Screen film mammography represents the method of choice and the only accepted screening modality. Clustered microcalcifications (mc) are one of the mammographic hallmarks of early breast cancer [2]. The detection and differentiation of cancer related mc’s from those occurring in benign processes are highly dependent on image quality as well as the skills and the vigilance of the reporting radiologist [3],[4],[5]. In clinical routine additional investigations (eccentric resp. magnified ray views, ultrasound, MRI) have to be performed in patients with inclusive findings on standard mammographic projections. Patients with findings suspicious have to undergo biopsy followed by histologic examination of the specimen.

[1]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[2]  J. Kelsey,et al.  Epidemiology of breast cancer. , 1990, Epidemiologic reviews.

[3]  E. S. de Paredes,et al.  Mammographic and histologic correlations of microcalcifications. , 1990, Radiographics : a review publication of the Radiological Society of North America, Inc.

[4]  R. Bird.  Professional quality assurance for mammography screening programs. , 1990, Radiology.

[5]  Nico Karssemeijer,et al.  A Stochastic Model for Automated Detction of Calculations in Digital Mammograms , 1991, IPMI.

[6]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms: applications of artificial neural networks. , 1992, Medical physics.

[7]  L. Tabár,et al.  Update of the Swedish two-county program of mammographic screening for breast cancer. , 1992, Radiologic clinics of North America.

[8]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.

[9]  Nico Karssemeijer,et al.  ADAPTIVE NOISE EQUALIZATION AND RECOGNITION OF MICROCALCIFICATION CLUSTERS IN MAMMOGRAMS , 1993 .

[10]  W. Kegelmeyer,et al.  Dense feature maps for detection of calcifications , 1994 .

[11]  E. Thurfjell,et al.  Benefit of independent double reading in a population-based mammography screening program. , 1994, Radiology.

[12]  J. Hogge,et al.  The mammographic spectrum of fat necrosis of the breast. , 1995, Radiographics : a review publication of the Radiological Society of North America, Inc.

[13]  C. Floyd,et al.  Breast cancer: prediction with artificial neural network based on BI-RADS standardized lexicon. , 1995, Radiology.

[14]  B. Monsees,et al.  Evaluation of breast microcalcifications. , 1995, Radiologic clinics of North America.

[15]  M. Giger,et al.  Malignant and benign clustered microcalcifications: automated feature analysis and classification. , 1996, Radiology.