The code is based on extracting the local and global features of the lung data and classify them as benign or malignant. Feature refinement is done using Convolutional Block Attention Module to improve the performance of the algorithm.
The experiments are executed on LIDC-IDRI dataset. You can download the pre-processed dataset from the following link. https://drive.google.com/file/d/19JMK_IeBFlEQAEt_nrWsJcHrdyHcZMhm/view
The execution begins in experiments.py file which compares and produces the results of lung classification using baseline methods and the proposed method.