A Non-small Cell Lung Cancer Detection Technique Using PET/ CT Images

Out of all the cancer related death, lung cancer has the highest rate. In this work, a lung cancer classification technique has been proposed. The CT images are processed and HOG features are extracted from the image. The features are then given to SVM classifier to classify the cancer type. The performance of the method has been evaluated in terms of specificity, sensitivity, precision, false positive rate, accuracy, F1-score. Accuracy of the method is found to be 96% for the test set. The proposed method can be utilized to identify the cancer type.