Computer Aided Diagnosis System to Detect Breast Cancer Pathological Lesions

Authors:
Yosvany López;Andra Novoa;Miguel A. Guevara;Nicolás Quintana;Augusto Silva
Affiliations:
Center for Advanced Computer Sciences Technologies, Ciego de Ávila University, Cuba;Center for Advanced Computer Sciences Technologies, Ciego de Ávila University, Cuba;Center for Advanced Computer Sciences Technologies, Ciego de Ávila University, Cuba and IEETA, Aveiro University, Portugal;Center for Advanced Computer Sciences Technologies, Ciego de Ávila University, Cuba;IEETA, Aveiro University, Portugal
Venue:
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Year:
2008

Citing 4
Cited 0

Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
A study of cross-validation and bootstrap for accuracy estimation and model selection

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Breast cancer diagnosis based on a suitable combination of deformable models and artificial neural networks techniques

CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Diagnosis of breast cancer in digital mammograms using independent component analysis and neural networks

CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

Breast cancer is one of the most frequent forms of women's cancer over the world. Studies of the World Health Organization (WHO) reported 1,151,298 cases in 2002. A reliable Computer-Aided-Diagnosis (CAD) system for automated detection/classification of pathological lesions is very useful and helpful, providing a valuable "second opinion" to medical personnel. In this work, we describe a new CAD system to diagnose six mammography pathological lesions classes (calcifications, well-defined/circumscribed masses, spiculated masses, ill-defined masses, architectural distortions and asymmetries) as benign or malignant tissues. Two different Artificial Neural Networks models: Feedforward Backpropagation and Generalized Regression were tested statistically with a precision of 94.0% and 80.0% of true positives, respectively. This CAD system was validated successfully on the MiniMammographic Image Analysis Society (MiniMIAS) database, with a dataset formed by 100 images. The CAD system performance shows similar or better classification results compared with others available methods.