DCA-YOLO:Detection Algorithm for YOLOv8 Pulmonary Nodules Based on Attention Mechanism Optimization  

DCA-YOLO:一种基于注意力机制优化的YOLOv8肺结节检测算法

作　　者：SONG Yongsheng LIU Guohua 宋勇胜;刘国华(东华大学计算机科学与技术学院,上海201620)

机构地区：[1]School of Computer Science and Technology,Donghua University,Shanghai 201620,China

出　　处：《Journal of Donghua University(English Edition)》2025年第1期78-87,共10页东华大学学报(英文版)

摘　　要：Pulmonary nodules represent an early manifestation of lung cancer.However,pulmonary nodules only constitute a small portion of the overall image,posing challenges for physicians in image interpretation and potentially leading to false positives or missed detections.To solve these problems,the YOLOv8 network is enhanced by adding deformable convolution and atrous spatial pyramid pooling(ASPP),along with the integration of a coordinate attention(CA)mechanism.This allows the network to focus on small targets while expanding the receptive field without losing resolution.At the same time,context information on the target is gathered and feature expression is enhanced by attention modules in different directions.It effectively improves the positioning accuracy and achieves good results on the LUNA16 dataset.Compared with other detection algorithms,it improves the accuracy of pulmonary nodule detection to a certain extent.肺结节是肺癌的早期表现,然而肺结节在图像中占比较小,不仅导致医生阅片难度大,而且还可能出现误检和漏检的情况。针对这些问题,该文提出在YOLOv8网络的基础上加入可变形卷积和空洞空间金字塔池化(atrous spatial pyramid pooling,ASPP)并融合坐标注意力(coordinate attention,CA)机制,使得网络在聚焦小目标的同时又扩大感受野而不丢失分辨率。同时利用不同方向的注意力模块来聚集目标上的上下文信息,增强特征表达,有效提高定位精确度。所得算法在LUNA16的数据集上取得了良好的效果,相比于其他检测算法,该算法对肺结节检测的精度有一定改善。

关 键 词：pulmonary nodule YOLOv8 network object detection deformable convolution atrous spatial pyramid pooling(ASPP) coordinate attention(CA)mechanism 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]