A New Image Processing Technique for Medical Image Analysis

Abstract

In this communication, we report identification of lung cancer with the help of a new image processing technique. To start with, we compare the results obtained from our proposed method with those obtained from the original Sobel edge detection method. The comparison is done by creating a confusion matrix and considering various parameters such as True Positive, True Negative, False Positive, False Negative, Accuracy, Misclassification Rate, Precision, Recall, Specificity, F Score, Matthews Correlation Coefficient (MCC), F Measurement (FM), Z score, T Score, and P Score. Our proposed method gives better total accuracy than the normal Sobel edge detector. Keywords: Neural network, statistical learning, edge filters, deep learning, image processing