Detection of masses in mammogram images using CNN, geostatistic functions and SVM

► This work presents a new methodology for detection of masses in mammogram images. ► We propose an innovative use of geostatistical functions as texture signatures. ► The method uses cellular neural networks (CNNs), and support vector machine (SVM). ► Sensitivity of 80%, 0.84 false positives per image and 0.2 false negatives per image.