基于改进EfficientNet的乳腺肿瘤诊断

doi:10.11959/j.issn.2096-6652.202343

智能科学与技术学报 ›› 2023, Vol. 5 ›› Issue (4): 505-514.doi: 10.11959/j.issn.2096-6652.202343

基于改进EfficientNet的乳腺肿瘤诊断

方祯祺, 李雪, 莫红()

长沙理工大学电气与信息工程学院，湖南长沙 410114

收稿日期:2023-08-06 修回日期:2023-11-13 出版日期:2023-12-15 发布日期:2023-12-15
通讯作者: 莫红 E-mail:mohong198@163.com
作者简介:方祯祺（1999- ），女，长沙理工大学电气与信息工程学院硕士生，主要研究方向为智慧医疗。
李雪（1998- ），女，长沙理工大学电气与信息工程学院硕士生，主要研究方向为智慧医疗。
莫红（1972- ），女，长沙理工大学电气与信息工程学院教授，主要研究方向为主要研究方向为智慧医疗、模糊AI和复杂系统管理与控制。
基金资助:
国家自然科学基金项目(61473048)

Diagnostic of breast tumors based on improved EfficientNet

Zhenqi FANG, Xue LI, Hong MO()

School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha, 410114, China

Received:2023-08-06 Revised:2023-11-13 Online:2023-12-15 Published:2023-12-15
Contact: Hong MO E-mail:mohong198@163.com
Supported by:
The National Natural Science Foundation of China(61473048)

摘要/Abstract

摘要：

乳腺肿瘤严重影响女性的身心健康。病理学图像分析是医生诊断乳腺肿瘤的一个重要方法，不同类型肿瘤细胞的结构具有高度的相关性，这使得常规方法的诊断不易进行。改进的EfficientNet被用来诊断乳腺肿瘤，其使网络模型能自动学习疾病的特征并提高乳腺肿瘤诊断的准确率。基于此，首先，采用卷积块注意力模型提取乳腺肿瘤病理图像的有效特征；其次，引入分组卷积和通道混洗操作来提高模型的特征表达能力；再次，利用Hard-Swish激活函数提升模型的收敛速度；最后，实验验证了改进后的EfficientNet在BreakHis数据集上的8分类准确率达到98.4%，该方法成为乳腺肿瘤诊断的一个有力的决策辅助工具。

关键词: 乳腺肿瘤, EfficientNet, 图像分类, 卷积神经网络

Abstract:

Breast tumors adversely affect the holistic well-being of women. Histopathological images are a critical substantiation for doctors to diagnose breast tumor types. The structure of various types of tumor cells exhibits significant correlations, thereby posing challenges to the diagnosis using conventional methods. In this work, the enhanced EfficientNet was employed for the diagnosis of breast tumors, which enabled the network model to learn the features of the disease automatically and improve the accuracy of the diagnosis of breast tumor types. Firstly, the convolutional block attention module was used to extract effective features. Secondly, the group convolution and channel shuffle operations were introduced to improve the feature representation ability of the model. Thirdly, the Hard-Swish activation function was applied to improve the convergence speed of the model. Finally, Experiments showed that the improved EfficientNet network achieved 98.4% accuracy in eight classifications on the BreakHis dataset, which was expected to act a decision aid tool in breast tumor diagnostic research.

Key words: breast tumor, EfficientNet, image classification, convolutional neural network

中图分类号:

TP391.4

方祯祺,李雪,莫红. 基于改进EfficientNet的乳腺肿瘤诊断[J]. 智能科学与技术学报, 2023, 5(4): 505-514.

Zhenqi FANG,Xue LI,Hong MO. Diagnostic of breast tumors based on improved EfficientNet[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 505-514.

图/表 15

图1

表1

图2

图3

图4

图5

图6

图7

图8

表2

图9

图10

图11

表3

图12

参考文献 27

1	郑莹, 吴春晓, 张敏璐. 乳腺癌在中国的流行状况和疾病特征[J]. 中国癌症杂志, 2013, 23(8): 561-569.
	ZHENG Y, WU C X, ZHANG M L. The epidemic and characteristics of female breast cancer in China[J]. China Oncology, 2013, 23(8):561-569.
2	肖怀远, 郝希山. 乳腺癌早诊早治关键技术的研究与应用[J]. 科技导报,2021, 39(7): 75-78.
	XIAO H Y, HAO X S. Research and application of key technologies for early diagnosis and treatment of breast cancer[J]. Science and Technology Review, 2021, 39(7): 75-78.
3	LIANG Z Y, WANG Q Y, LIAO H W, et al. Artificially engineered antiferromagnetic nanoprobes for ultra-sensitive histopathological level magnetic resonance imaging[J]. Nature Communications, 2021, 12(1): 3840.
4	ARAúJO T, ARESTA G, CASTRO E, et al. Classification of breast cancer histology images using convolutional neural networks[J]. PLoS One, 2017, 12(6): e0177544.
5	卞修武, 平轶芳. 我国病理学科发展面临的挑战和机遇[J]. 第三军医大学学报, 2019, 41(19): 1815-1817.
	BIAN X W, PING Y F. Pathology in China: challenges and opportunities[J]. Journal of Third Military Medical University, 2019, 41(19): 1815-1817.
6	KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, (2):25.
7	GUO Y, WANG Y, YANG H, et al. Dual-attention EfficientNet based on multi-view feature fusion for cervical squamous intraepithelial lesions diagnosis[J]. Biocybernetics and Biomedical Engineering, 2022, 42(2): 529-542.
8	邵虹, 张鸣坤, 崔文成. 基于分层卷积神经网络的皮肤镜图像分类方法[J]. 智能科学与技术学报, 2021, 3(4): 474-481.
	SHAO H, ZHANG M K, CUI W C. Classification method of dermoscopic image based on hierarchical convolution neural network[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(4): 474-481.
9	王禾扬, 杨启鸣, 朱旗. 基于深度卷积集成网络的视网膜多种疾病筛查和识别方法[J]. 智能科学与技术学报, 2021, 3(3): 259-267.
	WANG H Y, YANG Q M, ZHU Q. Retinal multi-disease screening and recognition method based on deep convolution ensemble network[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(3): 259-267.
10	邵虹, 左常升, 张萍. 结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法[J]. 智能科学与技术学报, 2022, 4(4): 610-616.
	SHAO H, ZUO C S, ZHANG P. Lung cell image segmentation method combining attention U-Net and bottleneck detection[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(4): 610-616.
11	丛晓峰, 桂杰, 章军. 基于视觉Transformer的多损失融合水下图像增强网络[J]. 智能科学与技术学报, 2022, 4(4): 522-532.
	CONG X F, GUI J, ZHANG J. Underwater image enhancement network based on visual transformer with multiple loss functions fusion[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(4): 522-532.
12	李颖, 陈龙, 黄钊宏, 等. 基于多尺度卷积神经网络特征融合的植株叶片检测技术[J]. 智能科学与技术学报, 2021, 3(3): 304-311.
	LI Y, CHEN L, HUANG Z H, et al. Plant leaf detection technology based on multi-scale CNN feature fusion[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(3): 304-311.
13	SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. Breast cancer histopathological image classification using convolutional neural networks[C]//Proceedings of 2016 International Joint Conference on Neural Networks (IJCNN). Piscataway: IEEE Press, 2016: 2560-2567.
14	NAHID A A, MEHRABI M A, KONG Y N. Frequency-domain information along with LSTM and GRU methods for histopathological breast-image classification[C]//Proceedings of 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT). Piscataway: IEEE Press, 2018: 410-415.
15	DAS K, CONJETI S, ROY A G, et al. Multiple instance learning of deep convolutional neural networks for breast histopathology whole slide classification[C]//Proceedings of 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). Piscataway: IEEE Press, 2018: 578-581.
16	SHALLU, MEHRA R. Breast cancer histology images classification: Training from scratch or transfer learning?[J]. ICT Express, 2018, 4 (4): 247-254.
17	何雪英, 韩忠义, 魏本征. 基于深度学习的乳腺癌病理图像自动分类[J]. 计算机工程与应用, 2018, 54 (12): 121-125.
	HE X Y, HAN Z Y, WEI B Z. Breast cancer histopathological image auto-classification using deep learning[J]. Computer Engineering and Applications, 2018, 54 (12): 121-125.
18	ZHAN X, ZHANG T, FENG W Y, et al. Breast cancer diagnosis from histopathological image based on deep learning[C]//Proceedings of 2019 Chinese Control and Decision Conference (CCDC). Piscataway: IEEE Press, 2019: 4616-4619.
19	GOUR M, JAIN S, SUNIL KUMAR T. Residual learning based CNN for breast cancer histopathological image classification[J]. International Journal of Imaging Systems and Technology, 2020, 30(3): 621-635.
20	BOUMARAF S, LIU X B, ZHENG Z S. A new transfer learning based approach to magnification dependent and independent classification of breast cancer in histopathological images[J]. Biomedical Signal Processing and Control, 2021, 63: 102192.
21	LI Z, LIU F, YANG W, et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12):6999-7019.
22	KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial Intelligence Review, 2020, (53):5455-5516.
23	SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. A dataset for breast cancer histopathological image classification[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(7): 1455-1462.
24	SUPRIYO C, RICHARD T, RAMYA R, et al. Interpretability of deep learning models: a survey of results[C]//Proceedings of IEEE SmartWorld. Piscataway: IEEE Press, 2017: 1-6.
25	SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 618-626.
26	王飞跃, 莫红. 关于二型模糊集合的一些基本问题[J]. 自动化学报, 2017, 43(7): 1114-1141.
	WANG F Y, MO H. Some fundamental issues on type-2 fuzzy sets[J]. Acta Automatica Sinica, 2017, 43(7): 1114-1141.
27	MO H, WANG F Y, ZHOU, M, et al. Footprint of uncertainty for type-2 fuzzy sets[J]. Information Sciences: An International Journal, 2014, 272: 96-110.

图像类型	40×/张	100×/张	200×/张	400×/张
A	114	113	111	106
F	253	260	264	237
PT	109	121	108	115
TA	149	150	140	130
DC	864	903	869	788
LC	156	170	163	137
MC	205	222	196	169
PC	145	142	135	138

模型	ACC/%	parms/MB	FLOPs
VGG16	88.8	138.36	15.5 GB
ResNet34	92.0	21.8	3.68 GB
EfficientNetB0	93.2	5.3	399.36 MB
H-EfficientNet	93.9	5.29	399.36 MB
C-EfficientNet	94.3	5.59	407.36 MB
GS-EfficientNet	94.7	3.92	240.13 MB
GSCH-EfficientNet	98.4	4.23	248.12 MB

模型	准确率/%	精确率/%	召回率/%	特异度/%	F1-Score/%
VGG16	88.8	87.8	86.3	94.7	87.0
RestNet34	92.0	91.9	91.5	98.7	91.7
DenseNet121	92.1	92.0	91.8	98.6	91.9
MobileNetV2	89.1	88.2	87.6	97.9	87.9
ShuffleNetV2	90.9	90.2	89.9	98.3	90.0
EfficientNetB0	93.2	92.1	91.7	98.8	91.9
GSCH-EfficientNet	98.4	97.9	97.8	99.7	97.9

[1]	顾宙瑜, 於跃成, 者甜甜. Rapider-YOLOX：高效的轻量级目标检测网络[J]. 智能科学与技术学报, 2023, 5(1): 92-103.
[2]	罗欣欢, 王奕璇, 李炜, 陈曦. 基于显著性信息的Fit CutMix数据增强算法在医学影像上的应用[J]. 智能科学与技术学报, 2023, 5(1): 58-68.
[3]	邵虹, 张鸣坤, 崔文成. 基于分层卷积神经网络的皮肤镜图像分类方法[J]. 智能科学与技术学报, 2021, 3(4): 474-481.
[4]	李颖, 陈龙, 黄钊宏, 孙杨, 蔡国榕. 基于多尺度卷积神经网络特征融合的植株叶片检测技术[J]. 智能科学与技术学报, 2021, 3(3): 304-311.
[5]	张阳, 胡月, 辛东嵘. 一种考虑时空关联的深度学习短时交通流预测方法[J]. 智能科学与技术学报, 2021, 3(2): 172-178.
[6]	郝晓辰,冀亚坤,郑立召,史鑫,赵彦涛. 基于差分进化的水泥烧成系统动态优化算法[J]. 智能科学与技术学报, 2020, 2(2): 186-193.
[7]	张国宾,王新迎. 基于混合神经网络的光伏组件输出特性数据驱动建模方法[J]. 智能科学与技术学报, 2020, 2(2): 169-178.
[8]	刘文华,李浥东,王涛,邬俊,金一. 基于高维特征表示的交通场景识别[J]. 智能科学与技术学报, 2019, 1(4): 392-399.

基于改进EfficientNet的乳腺肿瘤诊断

Diagnostic of breast tumors based on improved EfficientNet

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 27

相关文章 8

Metrics

推荐阅读 0

图像类型	40×/张	100×/张	200×/张	400×/张
A	114	113	111	106
F	253	260	264	237
PT	109	121	108	115
TA	149	150	140	130
DC	864	903	869	788
LC	156	170	163	137
MC	205	222	196	169
PC	145	142	135	138

图像类型	40×/张	100×/张	200×/张	400×/张
A	114	113	111	106
F	253	260	264	237
PT	109	121	108	115
TA	149	150	140	130
DC	864	903	869	788
LC	156	170	163	137
MC	205	222	196	169
PC	145	142	135	138

图像类型	40×/张	100×/张	200×/张	400×/张
A	114	113	111	106
F	253	260	264	237
PT	109	121	108	115
TA	149	150	140	130
DC	864	903	869	788
LC	156	170	163	137
MC	205	222	196	169
PC	145	142	135	138