Effective lung cancer diagnosis using multi-focus fusion of CT and PET images with deep learning strategies

Abstract

ABSTRACT Lung cancer is among the most prevalent forms of the disease. This study describes multi-modal image fusion for lung cancer diagnosis using a combination of PET and CT images. The proposed approach involves breaking down the images into constituent parts, amalgamating the low and high-frequency bands, and using a Siamese Inception V3 approach to form a weight map that merges the pixel motion data from the images. The fused images are acquired using the inverse DTCWT of the fused coefficient, and deep EfficientNet is used to extract features from the fused image. The embedded whale optimization with mean grey wolf optimization methods are used to choose features. The proposed approach is tested on CT and PET images of normal and lung cancer, and a deep learning technique, CNN/BiLSTM, is used to classify lung cancer. The proposed classifier has an AUC of 92.34 percent, which is superior to other proposed categorizers.