An efficient U-Net framework for lung nodule detection using densely connected dilated convolutions

Remote health monitoring is an important aspect especially for remote locations where standard medical facilities are not available. Smart cities use a similar concept to provide health facilities even when physicians are unavailable. Lung cancer remains to be one of the most critical types of cancer with a 5-year survival rate of only 18%. Efficient computer-aided diagnostic systems are required to diagnose lung cancer before time for better treatment planning. The variety of lung nodules and their visual similarity with surrounding regions make their detection difficult. Traditional image processing and machine learning methods usually lack the ability to handle all types of nodules with a single method. In this study, we propose an efficient end-to-end segmentation algorithm with an improved feature learning mechanism based on densely connected dilated convolutions. We applied dense feature extraction and incorporated multi-dilated context learning by using dilated convolutions at different rates for better nodule segmentation. First, lung ROIs are extracted from the CT scans using k-mean clustering and morphological operators to reduce the model's search space instead of using full CT scan images or nodule patches. These ROIs are then used by our proposed architecture for nodule segmentation and efficiently handles different types of lung nodules. The performance of the proposed algorithm is evaluated on a publicly available dataset LIDC-IDRI and achieved a dice score of 81.1% and a Jaccard score of 72.5%.