图像分辨率对乳腺超声卷积神经网络的影响。
The effect of image resolution on convolutional neural networks in breast ultrasound.
作者信息
Tang Shuzhen, Jing Chen, Jiang Yitao, Yang Keen, Huang Zhibin, Wu Huaiyu, Cui Chen, Shi Siyuan, Ye Xiuqin, Tian Hongtian, Song Di, Xu Jinfeng, Dong Fajin
机构信息
Second Clinical College of Jinan University, Shenzhen 518020, Guangdong, China.
Shenzhen People's Hospital, Shenzhen 518020, Guangdong, China.
出版信息
Heliyon. 2023 Aug 21;9(8):e19253. doi: 10.1016/j.heliyon.2023.e19253. eCollection 2023 Aug.
PURPOSE
The objective of this research was to investigate the efficacy of various parameter combinations of Convolutional Neural Networks (CNNs) models, namely MobileNet and DenseNet121, and different input image resolutions (REZs) ranging from 64×64 to 512×512 pixels, for diagnosing breast cancer.
MATERIALS AND METHODS
During the period of June 2015 to November 2020, two hospitals were involved in the collection of two-dimensional ultrasound breast images for this retrospective multicenter study. The diagnostic performance of the computer models MobileNet and DenseNet 121 was compared at different resolutions.
RESULTS
The results showed that MobileNet had the best breast cancer diagnosis performance at 320×320pixel REZ and DenseNet121 had the best breast cancer diagnosis performance at 448×448pixel REZ.
CONCLUSION
Our study reveals a significant correlation between image resolution and breast cancer diagnosis accuracy. Through the comparison of MobileNet and DenseNet121, it is highlighted that lightweight neural networks (LW-CNNs) can achieve model performance similar to or even slightly better than large neural networks models (HW-CNNs) in ultrasound images, and LW-CNNs' prediction time per image is lower.
目的
本研究的目的是调查卷积神经网络（CNN）模型（即MobileNet和DenseNet121）的各种参数组合以及从64×64到512×512像素的不同输入图像分辨率（REZ）对乳腺癌诊断的有效性。
材料与方法
在2015年6月至2020年11月期间，两家医院参与了本次回顾性多中心研究的二维超声乳腺图像收集。比较了计算机模型MobileNet和DenseNet 121在不同分辨率下的诊断性能。
结果
结果表明，MobileNet在320×320像素分辨率下具有最佳的乳腺癌诊断性能，DenseNet121在448×448像素分辨率下具有最佳的乳腺癌诊断性能。
结论
我们的研究揭示了图像分辨率与乳腺癌诊断准确性之间存在显著相关性。通过对MobileNet和DenseNet121的比较，突出表明轻量级神经网络（LW-CNNs）在超声图像中可以实现与大型神经网络模型（HW-CNNs）相似甚至略好的模型性能，并且LW-CNNs每张图像的预测时间更低。
Zotero 插件