Detecting film-screen artifacts in mammography using a model-based approach

Microcalcifications can be one of the earliest signs of breast cancer. Unfortunately, their appearance in mammograms can be mimicked by dust and dirt entering the imaging process and this has been shown previously to lead to false positives. The authors use a model of the imaging process and, in particular, the blurring functions inherent within it to detect the film-screen artifacts caused by dust and dirt and, thus, reduce false-positives. A crucial facet of the work is the choice of the correct image representation upon which to perform the image processing. After extensive testing, the authors' algorithm has identified no microcalcifications as being artifacts and has an artifact detection rate of approaching 96%.

[1]  R M Nishikawa,et al.  Image feature analysis and computer-aided diagnosis in mammography: reduction of false-positive clustered microcalcifications using local edge-gradient analysis. , 1995, Medical physics.

[2]  D. Dance,et al.  Classification of ductal carcinoma in situ by image analysis of calcifications from digital mammograms. , 1995, The British journal of radiology.

[3]  W Knüpfer,et al.  Imaging characteristics of different mammographic screens. , 1992, Medical physics.

[4]  David R. Dance,et al.  Automatic Detection Of Microcalcifications In Digital Mammograms Using Local Area Thresholding Techniques , 1989, Medical Imaging.

[5]  Jong Kook Kim,et al.  Adaptive mammographic image enhancement using first derivative and local statistics , 1997, IEEE Transactions on Medical Imaging.

[6]  M. Yaffe,et al.  Analysis of signal propagation in optically coupled detectors for digital mammography: I. Phosphor screens. , 1995, Physics in medicine and biology.

[7]  Orhan Nalcioglu,et al.  Deconvolution Technique For The Improvement Of Contrast Of Image Intensifiers , 1981, Other Conferences.

[8]  P N Shrivastava.  Model to analyze radiographic factors in mammography. , 1980, Medical physics.

[9]  Ed Caruthers.  Monte Carlo Studies Of Image Spread By X-Ray Intensifying Screens , 1985, Medical Imaging.

[10]  T. Villafana,et al.  Screen-film mammographic technique for breast cancer screening. , 1987, Radiology.

[11]  Atam P. Dhawan,et al.  Artificial neural network based classification of mammographic microcalcifications using image structure and cluster features , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  J A Seibert,et al.  Removal of image intensifier veiling glare by mathematical deconvolution techniques. , 1985, Medical physics.

[13]  R. K. Swank.  Absorption and noise in x‐ray phosphors , 1973 .

[14]  G. Barnes,et al.  Spectral dependence of glandular tissue dose in screen-film mammography. , 1991, Radiology.

[15]  D R Dance,et al.  Calculation of dose and contrast for two mammographic grids. , 1992, Physics in medicine and biology.

[16]  D R Dance,et al.  The computation of scatter in mammography by Monte Carlo methods. , 1984, Physics in medicine and biology.

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

[18]  Jacob Beutel,et al.  The role of screen parameters and print-through in the performance of film/screen systems , 1993 .

[19]  Michael Brady,et al.  Mammographic Image Analysis , 1999, Computational Imaging and Vision.

[20]  Michael Sandborg,et al.  Receptor modeling for use in computerized optimization of imaging systems , 1996, Medical Imaging.

[21]  C. R. M. Boggis,et al.  “ Model based classification of linear structures in digital mammograms ” ( “ Automatic detection and model based classification of anatomically different linear structures in digital mammograms , 1996 .

[22]  R. K. Swank,et al.  Calculation of modulation transfer functions of x-ray fluorescent screens. , 1973, Applied optics.

[23]  D. H. Davies.  Technical note: digital mammography--the comparative evaluation of film digitizers. , 1993, The British journal of radiology.

[24]  M. Yaffe,et al.  Signal-to-noise properties of mammographic film-screen systems. , 1985, Medical physics.

[25]  Robert M. Nishikawa,et al.  Characterization of the mammographic appearance of microcalcifications: applications in computer-aided diagnosis , 1993 .

[26]  K Doi,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. I. Automated detection of microcalcifications in mammography. , 1987, Medical physics.

[27]  Michael Brady,et al.  Finding Curvilinear Structures in Mammograms , 1995, CVRMed.

[28]  Michael Brady,et al.  A Representation for Mammographic Image Processing , 1995, CVRMed.

[29]  G U Rao,et al.  The relationship between resolution and speed of x-ray intensifying screens. , 1978, Medical physics.

[30]  Ralph Highnam,et al.  Computing the scatter component of mammographic images , 1994, IEEE Trans. Medical Imaging.

[31]  R. J. Eastgate,et al.  Optimal x-ray spectra for screen-film mammography. , 1981, Medical physics.

[32]  Michael Brady,et al.  Integration of Low-Level Processing to Facilitate Microcalcification Detection , 1998, Digital Mammography / IWDM.

[33]  G. Giakoumakis,et al.  Light angular distribution of fluorescent screens excited by x-rays , 1985 .

[34]  Rangaraj M. Rangayyan,et al.  DETECTION AND CLASSIFICATION OF MAMMOGRAPHIC CALCIFICATIONS , 1993 .

[35]  C Kimme-Smith,et al.  Increased radiation dose at mammography due to prolonged exposure, delayed processing, and increased film darkening. , 1991, Radiology.

[36]  Michael Sandborg,et al.  Calculation and analysis of DQE for some image detectors in mammography , 1998 .