| 基于注意力机制的肺结节分类研究 |
| |
| 引用本文： | 匡健,洪敏杰,刘星辰,贾俊铖.基于注意力机制的肺结节分类研究[J].计算机应用与软件,2022,39(1):163-167. |
| |
| 作者姓名： | 匡健 洪敏杰 刘星辰 贾俊铖 |
| |
| 作者单位： | 苏州大学计算机科学与技术学院 江苏 苏州 215000 |
| |
| 基金项目： | 中国博士后科学基金项目(2017M611905);江苏省高等学校自然科学研究面上项目(17KJB520034);苏州市科技项目(SS201701,SYSD20192152);江苏高校优势学科建设工程项目(PAPD)。 |
| |
| 摘 要： | 为进一步提升肺结节分类的效果,引入一种基于注意力机制的分类算法.通过在神经网络中添加空间和通道注意力因子,使得肺结节分类网络生成更有效的特征映射,结合梯度提升树算法,进一步提升模型的性能.经过大量实验后,证明了该方法的有效性.
|
| 关 键 词： | 计算机辅助诊断技术 神经网络 肺结节分类 |
CLASSFICATION OF PULMONARY NODULES BASED ON ATTENTION MECHANISM |
| |
| Kuang Jian,Hong Minjie,Liu Xingchen,Jia Juncheng.CLASSFICATION OF PULMONARY NODULES BASED ON ATTENTION MECHANISM[J].Computer Applications and Software,2022,39(1):163-167. |
| |
| Authors: | Kuang Jian Hong Minjie Liu Xingchen Jia Juncheng |
| |
| Affiliation: | (School of Computer Science and Technology,Soochow University,Suzhou 215000,Jiangsu,China) |
| |
| Abstract: | In order to further improve the effect of lung nodule classification,a classification algorithm based on attention mechanism is introduced.By adding spatial and channel attention factors to the neural network,the lung nodule classification network generates more effective feature maps,which is combined with the gradient boosting tree algorithm to further improve the performance of the model.After a lot of experiments,the effectiveness of the this method was proved. |
| |
| Keywords: | Computer aided diagnosis technology Neural network Pulmonary nodule classification |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
