A Sobel 12D Algorithm for Pulmonary Fibrosis Detection using Machine Learning and Multi Criteria Decision Making Method

This paper attempts to develop and validate a new Sobel 12D algorithm to enhance the radiographic images to identify pulmonary fibrosis, an interstitial lung disease. Using a machine learning model, important parameters of an ideal algorithm is identified. Two multi-criteria decision making methods are then used to compare and weigh the parameters and also to evaluate three edge detection algorithms used to sharpen the lung images. The method used in this paper offers pulmonologists and radiologists to select the most useful algorithms that enable them to make better and precise diagnosis of pulmonary fibrosis.