当前位置>主页 > 期刊在线 > 信息技术 >

信息技术21年9期

基于 EfficientNet 的皮肤癌识别与分类
张嘉颖
(华侨大学 计算机科学与技术学院,福建 厦门 361021)

摘  要:针对人工识别皮肤癌恶性肿瘤中不可避免的人为因素,以及效率低、设备要求高等问题,提出了一种基于 EfficientNet 网络的新的皮肤癌识别与分类方法。首先,由于样本数据量过小,通过数据预处理实现数据增强,从而防止训练模型出现过拟合的问题。然后将数据集在 EfficientNet 网络模型上进行训练,同时采用 Adam 调整学习率,进而实现皮肤癌图像的识别与分类。实验结果表明,该模型的准确率和查全率可分别达到 90.78% 和 88.23%,在保证了准确率和查全率的前提下,参数量大大减少,可有效提升临床医学诊断的效率。


关键词:EfficientNet 模型;Adam;皮肤癌识别



DOI:10.19850/j.cnki.2096-4706.2021.09.004


中图分类号:TP391.4                                       文献标识码:A                                     文章编号:2096-4706(2021)09-0013-03


Skin Cancer Identification and Classification Based on EfficientNet

ZHANG Jiaying

(College of Computer Science and Technology,Huaqiao University,Xiamen 361021,China)

Abstract:A new method for skin cancer identification and classification based on the EfficientNet network is proposed,aiming at the inevitable human factors,low efficiency and high equipment requirements in the manual identification of skin cancer and malignant tumors. Firstly,since the sample data is too small,data enhancement is realized through data preprocessing,so as to prevent the problem of overfitting in the training model. Then,the data set is trained on its EfficientNet network model,with Adam adjusting the learning rate for skin cancer image identification and classification. The experimental results show that the accuracy and recall of the model can reach 90.78% and 88.23%,respectively. On the premise of ensuring the accuracy and recall,the number of parameters is greatly reduced, which can effectively improve the efficiency of clinical medical diagnosis.

Keywords:EfficientNet model;Adam;skin cancer identification


参考文献:

[1] 许美凤,国雷达,宋盼盼,等 . 多卷积神经网络模型融合的 皮肤病识别方法 [J]. 西安交通大学学报,2019,53(11):125-130.

[2] Centers for Disease Control and Prevention. United States Cancer Statistics:Data Visualizations [DB/OL].[2021-02-24].https:// gis.cdc.gov/Cancer/USCS/#/AtAGlance/.

[3] LINARES M A,ZAKARIA A,NIZRAN P. Skin cancer [J]. Primary Care:Clinics in Office Practice,2015,42(4):645-659.

[4] KOLM I,HOFBAUER G,BRAUN R P. Early diagnosis of skin cancer [J].Therapeutische Umschau.Revue Therapeutique,2010, 67(9):439-446.

[5] AMERI A. A Deep Learning Approach to Skin Cancer Detection in Dermoscopy Images [J].Journal of biomedical physics & engineering,2020,10(6):801-806.

[6] CODELLA N,CAI J J,ABEDINI M,et al. Deep Learning,Sparse Coding,and SVM for Melanoma Recognition in Dermoscopy Images [C]//Proceedings of the 6th International Workshop on Machine Learning in Medical Imaging-Volume 9352.Cham: Springer International Publishing,2015:118-126.

[7] TAN M X,LE Q V. EfficientNet:Rethinking Model Scaling for Convolutional Neural Networks [J/OL].arXiv:1905.11946 [cs.LG]. (2019-05-28).https://arxiv.org/abs/1905.11946v1.

[8] 张敏,赵雪青 . 基于 EfficientNets 的织物疵点图像分类方 法 [J]. 纺织高校基础科学学报,2020,33(4):64-70.

[9] 龚安,郭文婷 . 基于卷积神经网络的皮肤癌识别方法 [J]. 计算机技术与发展,2020,30(10):167-172.

[10] KINGMA D P,BA J. Adam:A Method for Stochastic Optimization [J/OL].arXiv:1412.6980 [cs.LG].https://arxiv.org/ abs/1412.6980.


作者简介:张嘉颖(2001—),女,汉族,山东枣庄人,本科 在读,研究方向:图像处理、深度学习。