A multi-stage neural network aided system for detection of microcalcifications in digitized mammograms

We propose a multi-stage detection system for microcalcification. A connectionist online feature selection technique is used to identify a set of good features from a set of 87 features computed at a few randomly selected positive (calcified) and negative (normal) pixels. A neural network is then trained with the selected features. The network output is cleaned using connected component analysis and an algorithm for removing thin elongated structures. A measure of local density (called mountain potential) of the calcified points is then computed at every suspected pixel of these cleaned images and the peak of the mountain potential is used to classify mammograms as calcified or normal. The system is tested on a set of 17 mammograms comprising 10 abnormal and seven normal images which are not used in training and the system is found to perform very well. Moreover for each abnormal image, the system is able to locate the calcified regions quite accurately.

[1]  Nicolaos B. Karayiannis,et al.  Detection of microcalcifications in digital mammograms using wavelets , 1998, IEEE Transactions on Medical Imaging.

[2]  Heng-Da Cheng,et al.  A novel approach to microcalcification detection using fuzzy logic technique , 1998, IEEE Transactions on Medical Imaging.

[3]  M. M. Anguh,et al.  Multiscale segmentation and enhancement in mammograms , 1997, Proceedings X Brazilian Symposium on Computer Graphics and Image Processing.

[4]  Hidekazu Tsubota,et al.  Image feature analysis and computer-aided diagnosis in digital radiography of avascular necrosis of the femoral head (ANFH). , 1996 .

[5]  R. Yager,et al.  Approximate Clustering Via the Mountain Method , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[6]  Sergios Theodoridis,et al.  Pattern Recognition , 1998, IEEE Trans. Neural Networks.

[7]  Jun Zheng,et al.  Microcalcification Detection Using Independent Component Analysis , 2004, METMBS.

[8]  Nikolas P. Galatsanos,et al.  A support vector machine approach for detection of microcalcifications , 2002, IEEE Transactions on Medical Imaging.

[9]  Carey E. Priebe,et al.  COMPARATIVE EVALUATION OF PATTERN RECOGNITION TECHNIQUES FOR DETECTION OF MICROCALCIFICATIONS IN MAMMOGRAPHY , 1993 .

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

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

[12]  Simon Haykin,et al.  Neural networks , 1994 .

[13]  Kuldeep Kumar,et al.  A novel min-max feature value based neural architecture and learning algorithm for classification of microcalcifications , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[14]  Nikhil R. Pal,et al.  Mountain and subtractive clustering method: Improvements and generalizations , 2000 .

[15]  D. Dance,et al.  Automatic computer detection of clustered calcifications in digital mammograms , 1990, Physics in medicine and biology.

[16]  Sergios Theodoridis,et al.  Pattern Recognition, Fourth Edition , 2008 .

[17]  Robin N. Strickland,et al.  Wavelet transforms for detecting microcalcifications in mammograms , 1996, IEEE Trans. Medical Imaging.

[18]  Hyun Wook Park,et al.  Statistical Textural Features for Detection of Microcalcifications in Digitized Mammograms , 1999, IEEE Trans. Medical Imaging.