Title :
Automatic detection of malignant tumors in mammograms
Author :
Öktem, V. ; Jouny, I.
Author_Institution :
Dept. of Electr. & Comput. Eng., Lafayette Coll., PA, USA
Abstract :
Detection of malignant tumors at an early stage is an important first step in diagnosis of the cancerous regions in mammograms. Although many detection schemes have been presented, they are still not adequate to safely eliminate all risks. We propose classification schemes of unknown test mammograms using fractal analysis and spatial moments distributions as image processing techniques. Two classifiers will be used in conjunction with these techniques: a backpropagation neural network and a self-organizing map. Investigation of the histograms of the spatial moments at low orders shows that discrete image spatial moments cannot distinguish between benign and malignant mammograms. The two-stage backpropagation neural network and the one-stage self-organizing map both give detection rates of 70% and low false positive rates. With further preprocessing and optimization, the performance of these classifiers may be further improved.
Keywords :
backpropagation; biological organs; cancer; fractals; image classification; mammography; medical image processing; optimisation; self-organising feature maps; tumours; automatic malignant tumor detection; benign mammograms; cancer diagnosis; fractal analysis; image classification; image processing; malignant mammograms; optimization; self-organizing map; spatial moments distributions; Breast neoplasms; Cancer; Diseases; Fractals; Malignant tumors; Mammography; Neural networks; Rough surfaces; Surface roughness; Wavelet analysis; backpropagation; fractal; moments;
Conference_Titel :
Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-8439-3
DOI :
10.1109/IEMBS.2004.1403530