| 基于注意力机制的肺结节检测算法 |
| |
| 引用本文： | 洪敏杰,吴刚,刘星辰,贾俊铖,杨歆豪. 基于注意力机制的肺结节检测算法[J]. 计算机工程与设计, 2021, 42(1): 83-88. DOI: 10.16208/j.issn1000-7024.2021.01.013 |
| |
| 作者姓名： | 洪敏杰 吴刚 刘星辰 贾俊铖 杨歆豪 |
| |
| 作者单位： | 苏州大学计算机科学与技术学院,江苏苏州215006;苏州大学机电工程学院,江苏苏州215006 |
| |
| 基金项目： | 中国博士后科学基金项目;江苏省高等学校自然科学研究面上资助经费基金项目;江苏高校优势学科建设工程基金项目;苏州市产业技术创新专项(民生科技)基金项目 |
| |
| 摘 要： | 为提升深度卷积神经网络模型检测肺结节的效果,提出一种基于注意力机制的肺结节检测算法。通过空间和通道注意力两种不同粒度与层次的注意力因子增强,提升肺结节检测网络生成的特征映射的质量,达到提升模型性能的目的。在LUNA16公开肺部CT图像数据集上进行大量相关实验,验证了模型的可行性和算法的有效性。
|
| 关 键 词： | 深度学习 医疗图像 注意力机制 目标检测 肺结节检测 |
Detection algorithm of lung nodule based on attention mechanism |
| |
| HONG Min-jie,WU Gang,LIU Xing-chen,JIA Jun-cheng,YANG Xin-hao. Detection algorithm of lung nodule based on attention mechanism[J]. Computer Engineering and Design, 2021, 42(1): 83-88. DOI: 10.16208/j.issn1000-7024.2021.01.013 |
| |
| Authors: | HONG Min-jie WU Gang LIU Xing-chen JIA Jun-cheng YANG Xin-hao |
| |
| Affiliation: | (School of Computer Science and Technology,Soochow University,Suzhou 215006,China;School of Mechanical and Electrical Engineering,Soochow University,Suzhou 215006,China) |
| |
| Abstract: | To improve the effects of deep convolutional neural network model on detecting pulmonary nodules,a lung nodule detection algorithm based on attention mechanism was proposed.Through spatial and channel attention two different granularity and level of attention factor enhancement,the quality of the feature map generated by the lung nodule detection network was improved,and the performance of the model was improved.A large number of related experiments was carried out on the lung image CT dataset of LUNA16,which verified the feasibility of the model and the effectiveness of the algorithm. |
| |
| Keywords: | deep learning medical image attention mechanism object detection lung nodule detection |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
