CADe tools for early detection of breast cancer
摘要
A breast neoplasia is often marked by the presence of microcalcifications and massive lesions in the mammogram: hence the need for tools able to recognize such lesions at an early stage. Our collaboration, among italian physicists and radiologists, has built a large distributed database of digitized mammographic images and has developed a Computer Aided Detection (CADe) system for the automatic analysis of mammographic images and installed it in some Italian hospitals by a GRID connection. Regarding microcalcifications, in our CADe digital mammogram is divided into wide windows which are processed by a convolution filter; after a self-organizing map analyzes each window and produces 8 principal components which are used as input of a neural network (FFNN) able to classify the windows matched to a threshold. Regarding massive lesions we select all important maximum intensity position and define the ROI radius. From each ROI found we extract the parameters which are used as input in a FFNN to distinguish between pathological and non-pathological ROI. We present here a test of our CADe system, used as a second reader and a comparison with another (commercial) CADe system.
引用
@article{arxiv.physics/0410082,
title = {CADe tools for early detection of breast cancer},
author = {U. Bottigli and P. G. Cerello and P. Delogu and M. E. Fantacci and F. Fauci and G. Forni and B. Golosio and A. Lauria and E. Lopez and R. Magro and G. L. Masala and P. Oliva and R. Palmiero and G. Raso and A. Retico and S. Stumbo and S. Tangaro},
journal= {arXiv preprint arXiv:physics/0410082},
year = {2007}
}
备注
4 pages, Proceedings of the 4th International Symposium on Nuclear and Related Techniques 2003, Vol. unico, pp. d10/1-d10/4 Havana, Cuba