Find in Library

Medical images are valuable sources for disease diagnosis. Besides, advancements in deep learning in recent years havebeen supporting disease diagnosis methods based on images to obtain numerous achievements. However, deep learningalgorithms still work as a black-box so it is difficult to interpret output from these algorithms. In this study, we propose aconvolutional network architecture to classify Chest X-ray images as well as apply explanation approaches for trainedmodels to support disease diagnosis. The proposed method provides insights in medical images to support Pneumoniadiagnosis.