This paper proposes a Faster R-CNN lung nodule detection algorithm based on residual attention networks, aiming to enhance the accuracy and efficiency of lung nodule detection. By incorporating residual networks and attention mechanisms, the feature extraction capability is strengthened, enabling the model to more effectively capture the subtle features of lung nodules. The improved Faster R-CNN performs exceptionally well in handling complex backgrounds and multi-scale targets, significantly boosting detection performance. Experimental results demonstrate that this method achieves outstanding detection results on multiple public datasets.

Dang Xuan. Research on Faster R-CNN Lung Nodule Detection Algorithm Based on Residual Attention Network. Academic Journal of Computing & Information Science(2025), Vol. 8, Issue 3: 51-55. https://doi.org/10.25236/AJCIS.2025.080307.

[1] Yu Shangqian. Detection and Classification of Pulmonary Nodules Based on Convolutional Neural Networks [D]. Hainan University, 2023. DOI: 10.27073/d.cnki.ghadu.2023.000157.

[2] Li Rui. Research on Pulmonary Nodule Detection in CT Images Based on Deep Learning [D]. Anhui University of Science and Technology, 2023. DOI: 10.26918/d.cnki.ghngc.2023.000253.

[3] Ji Junjun. Design and Implementation of a Pulmonary Nodule Detection System Based on Deep Learning [D]. Beijing University of Posts and Telecommunications, 2023. DOI:10.26969/d.cnki.gbydu.2023.001199.

[4] Zhang Hao, Jie Yixuan, Yang Xiaonan, etc. An automatic detection algorithm for pulmonary nodules based on fusion iterative self-organizing data analysis [J]. Computer and Digital Engineering, 2024, 52 (05): 1336-1340+1358