A VGG attention vision transformer network for benign and malignant classification of breast ultrasound images

人工智能 计算机科学 卷积神经网络 特征提取 人工神经网络 深度学习 超声波 模式识别(心理学) 乳腺超声检查 乳腺癌 乳腺摄影术 癌症 放射科 医学 内科学
作者
Xiaolei Qu,Hongyan Lu,Wenzhong Tang,Shuai Wang,Dezhi Zheng,Yaxin Hou,Jue Jiang
出处
期刊:Medical Physics [Wiley]
卷期号:49 (9): 5787-5798 被引量:35
标识
DOI:10.1002/mp.15852
摘要

Breast cancer is the most commonly occurring cancer worldwide. The ultrasound reflectivity imaging technique can be used to obtain breast ultrasound (BUS) images, which can be used to classify benign and malignant tumors. However, the classification is subjective and dependent on the experience and skill of operators and doctors. The automatic classification method can assist doctors and improve the objectivity, but current convolution neural network (CNN) is not good at learning global features and vision transformer (ViT) is not good at extraction local features. In this study, we proposed a visual geometry group attention ViT (VGGA-ViT) network to overcome their disadvantages.In the proposed method, we used a CNN module to extract the local features and employed a ViT module to learn the global relationship among different regions and enhance the relevant local features. The CNN module was named the VGGA module. It was composed of a VGG backbone, a feature extraction fully connected layer, and a squeeze-and-excitation block. Both the VGG backbone and the ViT module were pretrained on the ImageNet dataset and retrained using BUS samples in this study. Two BUS datasets were employed for validation.Cross-validation was conducted on two BUS datasets. For the Dataset A, the proposed VGGA-ViT network achieved high accuracy (88.71 ±$\ \pm \ $ 1.55%), recall (90.73 ±$\ \pm \ $ 1.57%), specificity (85.58 ±$\ \pm \ $ 3.35%), precision (90.77 ±$\ \pm \ $ 1.98%), F1 score (90.73 ±$\ \pm \ $ 1.24%), and Matthews correlation coefficient (MCC) (76.34 ±7$\ \pm \ 7$ 3.29%), which were better than those of all compared previous networks in this study. The Dataset B was used as a separate test set, the test results showed that the VGGA-ViT had highest accuracy (81.72 ±$\ \pm \ $ 2.99%), recall (64.45 ±$\ \pm \ $ 2.96%), specificity (90.28 ±$\ \pm \ $ 3.51%), precision (77.08 ±$\ \pm \ $ 7.21%), F1 score (70.11 ±$\ \pm \ $ 4.25%), and MCC (57.64 ±$\ \pm \ $ 6.88%).In this study, we proposed the VGGA-ViT for the BUS classification, which was good at learning both local and global features. The proposed network achieved higher accuracy than the compared previous methods.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
闪闪的灵发布了新的文献求助10
1秒前
怡然安梦发布了新的文献求助10
1秒前
1秒前
aizzy0发布了新的文献求助10
1秒前
王海婷完成签到,获得积分10
1秒前
1秒前
裴芷完成签到,获得积分10
2秒前
dorLi完成签到,获得积分10
2秒前
JJL完成签到,获得积分10
2秒前
2秒前
orixero的应助被钱百万采纳,获得10
2秒前
dmy完成签到,获得积分20
3秒前
脑洞疼的应助被英俊的依凝采纳,获得10
3秒前
4秒前
jjjyyy完成签到,获得积分10
4秒前
布鲁布鲁发布了新的文献求助10
4秒前
蟹黄的店完成签到,获得积分10
4秒前
内向易文发布了新的文献求助10
4秒前
lingyu完成签到 ,获得积分10
5秒前
jyxm发布了新的文献求助10
5秒前
Orange的应助被QI采纳,获得10
5秒前
长安发布了新的文献求助10
5秒前
5秒前
小小鱼儿发布了新的文献求助20
5秒前
大模型的应助被淡然的宛秋采纳,获得10
6秒前
7秒前
8秒前
wang发布了新的文献求助10
8秒前
8秒前
8秒前
赘婿的应助被dmy采纳,获得100
9秒前
大模型的应助被WXECO采纳,获得10
9秒前
搜集达人的应助被CHEN采纳,获得10
9秒前
顾矜的应助被WXECO采纳,获得10
9秒前
追寻极光完成签到,获得积分10
9秒前
一半完成签到,获得积分10
9秒前
NexusExplorer的应助被misaka采纳,获得10
10秒前
null的应助被坦率的冬日采纳,获得10
11秒前
君殇发布了新的文献求助10
11秒前
Owen的应助被坦率的冬日采纳,获得10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8161694
求助须知:如何正确求助?哪些是违规求助? 9556193
关于积分的说明 21733038
捐赠科研通 7751587
什么是DOI,文献DOI怎么找? 3427556
关于科研通互助平台的介绍 2552602
邀请新用户注册赠送积分活动 2472032