Mammogram classification using deep learning features
Syed Jamal Safdar Gardezi, Muhammad Ahsan Awais, Ibrahima Faye, Fabrice Mériaudeau · 2017
This paper presents a method for classification of normal and abnormal tissues in mammograms using a deep learning approach. VGG-16 CNN deep learning architecture with convolutional filter of (3×3) is implemented on mammograms ROIs from the IRMA dataset. The deep feature matrix is computed from first fully connected layer. The results are evaluated using 10 fold cross validation on SVM, binary trees, simple logistics and KNN (with k=1, 3, 5) classifiers. The method produced 100% classification accuracies with AUC 1.0.