Abstract:
Lung cancer is one of the leading causes of death worldwide, and early detection of lung nodules is crucial for the prevention and treatment of lung cancer. Early detecti...Show MoreMetadata
Abstract:
Lung cancer is one of the leading causes of death worldwide, and early detection of lung nodules is crucial for the prevention and treatment of lung cancer. Early detection of lung nodules is a key step in lung cancer screening and prevention, because compared with the clinical characteristics of lung cancer, nodules appear at an earlier stage, enabling patients to have more medical intervention and prevention. In traditional methods, the detection of pulmonary nodules often relies on manual labeling, which usually takes a lot of time and is prone to errors and omissions. So that patients can get better treatment outcomes. However, there are many technical challenges in lung nodule detection in X-ray, such as the diversity of nodule size and low contrast. In recent years, with the increasing research of deep learning in this field, automated detection methods have made remarkable progress. This paper analyzes several outstanding nodule detection algorithms in the NODE21 Challenge, and summarizes the advantages, disadvantages, and potential optimization space of each algorithm.
Published in: 2024 4th International Conference on Electronic Information Engineering and Computer Science (EIECS)
Date of Conference: 27-29 September 2024
Date Added to IEEE Xplore: 24 December 2024
ISBN Information: