| 摘要: |
| 目的 探讨基于超声图像的迁移学习模型在乳腺肿块良恶性鉴别诊断中的应用价值。方法 收集我院2018年5月至2021年3月经手术或穿刺活检病理证实的300例乳腺肿块患者共计582张超声图像作为超声数据集（训练集482张，测试集100张）。采用迁移学习方法对经过ImageNet数据集预训练的三种深度卷积神经网络模型（VGG-16，Inception-v3，ResNet-50）进行训练和测试。第一次迁移学习，三种模型分别对公共数据库CBIS-DDSM(Curated Breast Imaging Subset of DDSM)数据集中的良恶性乳腺肿块X线图像进行识别学习，并对模型进行微调；第二次迁移学习，利用超声数据集中随机挑选的训练集超声图像对三种模型进行微调。分别比较三种模型使用不同次数迁移学习后对乳腺肿块良恶性诊断效能。结果 VGG-16、Inception-v3、ResNet-50三种模型经过迁移学习后所有评价指标均有提高，其中基于ResNet-50建立的模型对乳腺肿块良恶性鉴别具有更优的效果，准确率为88.0%，敏感性为82.7%、特异性为93.8%、AUC值为0.915。结论 基于超声图像的ResNet-50迁移学习模型在乳腺肿块良恶性鉴别诊断中具有较高的准确率，可为低年资医师精准诊断提供决策支持。 |
| 关键词: 乳腺肿块 超声图像 深度卷积神经网络 迁移学习 鉴别诊断 |
| DOI： |
| 投稿时间：2022-03-03修订日期：2022-05-09 |
| 基金项目:湖北省重点研发计划项目(2020BCB022)；国家癌症中心攀登基金临床研究课题(NCC201917B04) |
|
| The Value of Differential Diagnosis of Benign and Malignant Breast Masses based on Transfer Learning Model of Ultrasound Images |
| YU Mei-hui,YE Hua-rong,YUAN Quan,ZENG Shu-e,CHENG Hui,LI Nan |
| (School of Medicine,Wuhan University of Science and Technology,Hubei Province;CR ＆ WISCO General Hospital,Wuhan University of Science and Technology,Hubei Province) |
| Abstract: |
| Objective To investigate the value of differential diagnosis of benign and malignant breast masses based on transfer learning model of ultrasound images. Methods A total of 582 ultrasound images from 300 patients with breast masses confirmed by surgery or biopsy in our hospital from May 2018 to March 2021 were collected as an ultrasound data set (482 for training set and 100 for test set). Three deep convolutional neural network models (VGG-16, Inception-v3, ResNet-50) pre-trained on the ImageNet dataset are trained and tested using a transfer learning method. For the first transfer learning, three models were used to identify and learn the X-ray images of benign and malignant breast masses in the public database CBIS-DDSM (Curated Breast Imaging Subset of DDSM) dataset and fine-tune the models. For the second transfer learning, three models using a randomly selected training set of ultrasound images from the ultrasound dataset were fine-tuned. The diagnostic performance of three models using different times of transfer learning for benign and malignant breast masses was compared. Results All evaluation indicators of VGG-16, Inception-v3 and ResNet50 models were improved after transfer learning, and the model established based on ResNet50 had a better performance on the identification of benign and malignant breast masses - accuracy was 88.0%, sensitivity was 82.7%, specificity was 93.8%，and AUC was 0.915. Conclusion The ResNet50 transfer learning model based on ultrasound images has a high accuracy in the differential diagnosis of benign and malignant breast masses and can provide decision support for primary physicians in accurate diagnosis. |
| Key words: Breast Masses Ultrasound Image Deep Convolutional Neural Network Transfer Learning Differential diagnosis |
