| 基于深度特征融合的肺炎影像识别研究 |
| |
| 引用本文： | 冯翔,康文清,吴瀚,王风云,王星皓,季超. 基于深度特征融合的肺炎影像识别研究[J]. 生物医学工程研究, 2021, 0(1): 28-32 |
| |
| 作者姓名： | 冯翔 康文清 吴瀚 王风云 王星皓 季超 |
| |
| 作者单位： | 潍坊医学院生命科学与技术学院;潍坊市益都中心医院 |
| |
| 基金项目： | 山东省自然科学基金资助项目(ZR2019BF037)。 |
| |
| 摘 要： | 在新型冠状病毒肺炎(COVID-19)疫情背景下,肺炎影像快速准确诊断显得尤为重要.针对肺炎影像纹理及细粒度特征受噪声影响大、常规手段识别率低等问题,本研究构建了一种新的基于跨层连接机制的多主干网络特征融合卷积模型.依托并行特征挖掘思路,利用多尺度感受野挖掘融合来捕获医学图像的局部细节,实现对COVID-19医学影像的...
|
| 关 键 词： | 深度学习 跨层连接 深度融合 特征识别 医学影像 |
Research on pneumonia image recognition based on deep feature fusion |
| |
| FENG Xiang,KANG Wenqing,WU Han,WANG Fengyun,WANG Xinghao,JI Chao. Research on pneumonia image recognition based on deep feature fusion[J]. Journal Of Blomedical Englneerlng Research, 2021, 0(1): 28-32 |
| |
| Authors: | FENG Xiang KANG Wenqing WU Han WANG Fengyun WANG Xinghao JI Chao |
| |
| Affiliation: | (College of Life Science and Technology,Weifang Medical College,Weifang 261000,China;Weifang Yidu Central Hospital, Weifang 262500) |
| |
| Abstract: | The rapid and accurate diagnosis of pneumonia images is particularly improtant in the context of the COVID-19 epidemic.As the texture and fine-grained features of pneumonia images greatly affected by noises,and the low recognition rate of conventional methods,we proposed a new multi-backbone network feature fusion convolution model based on the cross-layer connection mechanism.Via the parallel feature mining ideas,we used the multi-scale receptive field mining and fusion to capture the local details of medical images,achieved the medical images screening of COVID-19,and improved the accuracy of diagnosis.Simulations show that the recognition rate of this model applied to COVID-19 X-ray dataset and CT dataset is over 95%,which has great significance for the rapid,accurate and efficient diagnosis of COVID-19. |
| |
| Keywords: | Deep learning Cross-layer connection Deep fusion Feature recognition Medical image |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
