结合自动分割网络的新型深度学习网络在自动乳腺超声诊断乳腺癌中的性能
本研究纳入769个乳腺肿瘤,按600比169随机分为训练集与测试集,开发结合自动分割网络(ASN)提取肿瘤形态信息的新型深度学习网络(DLN),并与两名不同经验放射科医师比较诊断性能。新型DLN优于传统DLN,但诊断性能仍逊于经验丰富的放射科医师。
要点
- 新型ResNet101 v2模型AUC 0.85、AP 0.90,在六种DLN中表现最佳。
- ResNet34 v2模型特异度76.81%、PPV 82.22%较高;ResNet50 v2准确率78.11%、NPV 72.86%较高;ResNet101 v2敏感度85.00%较高。
- 新型DLN诊断性能优于新手放射科医师,但逊于经验丰富放射科医师。
核心结论
- 新型DLN表现优于传统DLN,可能有助于新手放射科医师提高ABUS诊断乳腺癌的性能。
研究设计与样本
- 本研究为深度学习网络开发与性能评估研究,共纳入769个乳腺肿瘤,按600比169随机分为训练集与测试集,开发结合自动分割网络(ASN)提取肿瘤形态信息的新型DLN(ResNet34 v2、ResNet50 v2、ResNet101 v2),并与两名不同经验放射科医师比较诊断性能。
诊断标准与关键数值
- ResNet34 v2模型特异度76.81%、PPV 82.22%,高于其他两种新型DLN。
- ResNet50 v2模型准确率78.11%、NPV 72.86%,高于其他两种新型DLN。
- ResNet101 v2模型敏感度85.00%,高于其他两种新型DLN。
- 新型ResNet101 v2模型AUC 0.85、AP 0.90,在六种DLN中表现最佳。
- 三种新型DLN使F1分数从0.77分别提高至0.78、0.81和0.82。
临床应用与阅片要点
- 新型DLN诊断性能优于新手放射科医师,可能有助于新手放射科医师提高ABUS诊断乳腺癌的性能。
- 新型DLN诊断性能逊于经验丰富放射科医师。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop novel deep learning network (DLN) with the incorporation of the automatic segmentation network (ASN) for morphological analysis and determined the performance for diagnosis breast cancer in automated breast ultrasound (ABUS).
METHODS: A total of 769 breast tumors were enrolled in this study and were randomly divided into training set and test set at 600 vs. 169. The novel DLNs (Resent v2, ResNet50 v2, ResNet101 v2) added a new ASN to the traditional ResNet networks and extracted morphological information of breast tumors. The accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic (ROC) curve (AUC), and average precision (AP) were calculated. The diagnostic performances of novel DLNs were compared with those of two radiologists with different experience.
RESULTS: The ResNet34 v2 model had higher specificity (76.81%) and PPV (82.22%) than the other two, the ResNet50 v2 model had higher accuracy (78.11%) and NPV (72.86%), and the ResNet101 v2 model had higher sensitivity (85.00%). According to the AUCs and APs, the novel ResNet101 v2 model produced the best result (AUC 0.85 and AP 0.90) compared with the remaining five DLNs. Compared with the novice radiologist, the novel DLNs performed better. The F1 score was increased from 0.77 to 0.78, 0.81, and 0.82 by three novel DLNs. However, their diagnostic performance was worse than that of the experienced radiologist.
CONCLUSIONS: The novel DLNs performed better than traditional DLNs and may be helpful for novice radiologists to improve their diagnostic performance of breast cancer in ABUS.
KEY POINTS: • A novel automatic segmentation network to extract morphological information was successfully developed and implemented with ResNet deep learning networks. • The novel deep learning networks in our research performed better than the traditional deep learning networks in the diagnosis of breast cancer using ABUS images. • The novel deep learning networks in our research may be useful for novice radiologists to improve diagnostic performance.
引用
- Wang, Chen, Luo, et al. Performance of novel deep learning network with the incorporation of the automatic segmentation network for diagnosis of breast cancer in automated breast ultrasound. Eur Radiol. 2022. PMID: 35488916. doi:10.1007/s00330-022-08836-x
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。