机器学习在白血细胞图像识别中的应用

臧 宇
惠州市第一人民医院

摘要

目的：人工识别白细胞效率低且易受人为因素影响，传统计算机辅助算法则需人为的提取白细胞特征，在编程提取这些特征时，效率较低。机器学习方法可自动的提取图像特征，可提高识别效率。本文将三种机器学习模型：AlexNet、ResNet与MobileNet用于白细胞图像识别当中，最后的实验结果表明，ResNet在三种模型中识别率最高。

关键词

机器学习；医学图像处理；目标识别

参考

[1] 杨勇超. 基于卷积神经网络的白细胞分类识别算法研究[D]. 西安科技大学, 2021, 1. [2] Khamael AL-Dulaimi, Jasmine Banks , Vinod Chandran, Inmaculada Tomeo-Reyes,Kien Nguyen. Classification of White Blood Cell Types from Microscope Images: Techniques and Challenges[J]. ResearchGate, 2018, 11, 17-25. [3] Li Ma, Renjun Shuai, Xuming Ran, Wenjia Liu, Chao Ye. Combining DC-GAN with ResNet for blood cell image classfication[J]. Medical&Biological&Engineering&Computing, 2020, 58, 1251-1264. [4] Azam B, Qureshi RJ, Jan Z, Khattak TA. Color based segmentation of white blood cells in blood photomicrographs using image quantization[J]. Res J Recent Sciences, 2014, 2277: 2502–9. [5] Zahra Khandan Khadem Alreza, Alireza Karimian. Design a new algorithm to count white blood cells for classification Leukemic Blood Image using machine vision system[J]. IEEE Xplore, 2017. [6] Khamael Abbas, Jasmine Banks, V.Chandran, Inmaculada Tomeo-Reyes. ImageNet Classification with Deep Convolutional Neural Networks[J]. Microscopy Science, 2018, 17-25. [7] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. ImageNet classification with deep convolutional neural networks. Commun[J]. ACM 60, 2017, 84–90. [8] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[J], 2016, pp. 770-778. [9] Howard A.G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., Andreetto M., Adam H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[J]. 2017.