冻结VGG19前几层可提升乳腺癌识别率并加快训练
Analysis of Transferred Pre-Trained Deep Convolution Neural Networks in Breast Masses Recognition
- 冻结VGG19前1个卷积块提升检测性能
- 敏感度达95.64%，优于全模型训练的94.48%
- 适合医疗影像领域轻量化模型部署
基于预训练卷积神经网络（CNN）的乳腺癌检测近年来备受关注。本文研究了在乳腺肿瘤分类任务中，冻结预训练VGG19网络不同卷积层块对性能的影响。共设计六种冻结策略，使用1693张良性和恶性乳腺病灶的微小影像进行评估。结果表明，冻结第一卷积块的方案取得最佳识别效果，敏感度达到95.64%；而完整训练VGG19的敏感度为94.48%。该方法在提升检测能力的同时显著缩短训练时间。
原文摘要 · Abstract (English)
Breast cancer detection based on pre-trained convolution neural network (CNN) has gained much interest among other conventional computer-based systems. In the past few years, CNN technology has been the most promising way to find cancer in mammogram scans. In this paper, the effect of layer freezing in a pre-trained CNN is investigated for breast cancer detection by classifying mammogram images as benign or malignant. Different VGG19 scenarios have been examined based on the number of convolution layer blocks that have been frozen. There are a total of six scenarios in this study. The primary benefits of this research are twofold: it improves the model's ability to detect breast cancer cases and it reduces the training time of VGG19 by freezing certain layers.To evaluate the performance of these scenarios, 1693 microbiological images of benign and malignant breast cancers were utilized. According to the reported results, the best recognition rate was obtained from a frozen first block of VGG19 with a sensitivity of 95.64 %, while the training of the entire VGG19 yielded 94.48%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。