CLASSIFICATION BY A STACKING MODEL USING CNN FEATURES FOR MEDICAL IMAGE DIAGNOSIS

Medical imaging coupled with Artificial Intelligence (AI) applications, in particular Deep learning (DL) and Machine Learning (ML), can speed up the disease diagnostic process. The purpose of this work is to present a novel disease detection system by suggesting a new Convolutional Neural Network (CNN) model and combining the CNN features with three of ML classifiers and suggesting a new classifier using the stacking model. The proposed system was used in binary and multiclassification and applied to two different medical datasets. The proposed model was evaluated using accuracy, sensitivity, specificity, precision, recall, F1 score, and AUC, achieving robust results.