Red Blood Cell Classification Based on Attention Residual Feature Pyramid Network.
Red Blood Cell Classification Based on Attention Residual Feature Pyramid Network.
复制标题
DOI：
10.3389/fmed.2021.741407
复制
发表时间：
2021
影响因子：
3.9
通讯作者：
Liu D
中科院分区：
文献类型：
--
作者：
Song W;Huang P;Wang J;Shen Y;Zhang J;Lu Z;Li D;Liu D
临床上，红细胞异常与肿瘤疾病、红细胞疾病、内科疾病等密切相关。红细胞分类是检测红细胞异常的关键。传统的红细胞分类是由医生手工完成的，需要大量的人力产生主观结果。本文提出了一种基于注意力的剩余特征金字塔网络（ARFPN）来分类14种类型的红细胞，以辅助相关疾病的诊断。该模型直接对整个红细胞图像进行分类。同时，将空间注意机制和通道注意机制与残差单元相结合，提高了类别相关特征的表达能力，实现了特征的准确提取。此外，使用RoI对齐方法减少了空间对称性损失，提高了分类精度。用588幅红细胞图像进行训练，验证了该方法的有效性。通道注意力剩余特征金字塔网络（C-ARFPN）模型实现了86%的mAP;通道和空间注意力剩余特征金字塔网络（CS-ARFPN）模型实现了86.9%的mAP。实验结果表明，该方法能够分类出更多的红细胞类型，更好地适应医生的需求，从而减少了医生的时间，提高了诊断效率。
Clinically, red blood cell abnormalities are closely related to tumor diseases, red blood cell diseases, internal medicine, and other diseases. Red blood cell classification is the key to detecting red blood cell abnormalities. Traditional red blood cell classification is done manually by doctors, which requires a lot of manpower produces subjective results. This paper proposes an Attention-based Residual Feature Pyramid Network (ARFPN) to classify 14 types of red blood cells to assist the diagnosis of related diseases. The model performs classification directly on the entire red blood cell image. Meanwhile, a spatial attention mechanism and channel attention mechanism are combined with residual units to improve the expression of category-related features and achieve accurate extraction of features. Besides, the RoI align method is used to reduce the loss of spatial symmetry and improve classification accuracy. Five hundred and eighty eight red blood cell images are used to train and verify the effectiveness of the proposed method. The Channel Attention Residual Feature Pyramid Network (C-ARFPN) model achieves an mAP of 86%; the Channel and Spatial Attention Residual Feature Pyramid Network (CS-ARFPN) model achieves an mAP of 86.9%. The experimental results indicate that our method can classify more red blood cell types and better adapt to the needs of doctors, thus reducing the doctor's time and improving the diagnosis efficiency.
登录
查看更多内容
影响因子：
3.7
作者：
Araújo T;Aresta G;Castro E;Rouco J;Aguiar P;Eloy C;Polónia A;Campilho A
通讯作者：
Campilho A
影响因子：
2.4
作者：
Elsalamony, Hany A.
通讯作者：
Elsalamony, Hany A.
影响因子：
7.7
作者：
Di Ruberto, Cecilia;Loddo, Andrea;Putzu, Lorenzo
通讯作者：
Putzu, Lorenzo
影响因子：
3.5
作者：
Lin YH;Liao KY;Sung KB
通讯作者：
Sung KB
影响因子：
5.1
作者：
Lee, Howard;Chen, Yi-Ping Phoebe
通讯作者：
Chen, Yi-Ping Phoebe