MRFNet: Pulmonary Nodule Detection Enhanced by Multi-Strategy YOLO-Based Approach

Lung nodules are the main lesions of the lung, and conditions of the lung can be directly displayed through CT images. However, traditional CT imaging methods suffered from cumbersome procedures, low detection rates, and poor localization accuracy. The subtle differences between pulmonary nodules and surrounding tissues in complex lung CT images, combined with repeated downsampling in feature extraction networks often lead to missed or false detections of small nodules. In order to recognize lung nodules in a better and more timely manner and to prevent delays in the diagnosis of lung nodules, this paper proposes a new deep learning-based lung nodule detection model (MRFNet). First, the model adds a small target detection block (MODB) to enhance the detection of small targets in lung nodules. Second, we propose the extended receptive domain (ERD) strategy to capture richer contextual information and reduce false positives caused by nodule occlusion. We also add a mixed global and local lightweight attention mechanism (MLCA) to optimize feature learning and reduce multi-scale detection errors. The results show that the proposed MRFNet achieves [email protected] of 95.8% and [email protected]:0.95 of 64.9% (compared with YOLOv10-n increases by 5.4% and 6.5%, respectively)on the LUNA16 dataset.