基于超声图像的卷积神经网络深度学习评估乳腺癌分子亚型:一项多中心回顾性研究
本研究利用1275例原发性乳腺癌患者的4828张超声图像训练深度卷积神经网络(DCNN),用于预测St. Gallen四种分子亚型及区分管腔型与非管腔型病变,并在两家其他机构的独立测试集上验证。模型在两个测试集中识别四种亚型的准确率为80.07%至97.02%和87.94%至98.83%,四分类加权平均MCC分别为0.59和0.79,区分管腔型与非管腔型的PPV分别为93.29%和88.21%。结论认为基于治疗前超声图像的深度学习模型能以高诊断准确率评估分子亚型。
要点
- DCNN基于治疗前超声图像预测乳腺癌四种St. Gallen分子亚型,两独立测试集准确率分别为80.07%–97.02%和87.94%–98.83%。
- 区分管腔型与非管腔型病变的PPV在测试集A为93.29%(95%CI 90.63–95.23%),测试集B为88.21%(95%CI 85.12–90.73%)。
- 四分类加权平均MCC测试集A为0.59、测试集B为0.79,提示模型在两个外部测试集上均具有较好的判别能力。
诊断标准与关键数值
- 模型预测四种St. Gallen分子亚型,测试集A各亚类准确率范围为80.07%(95%CI 76.49–83.23%)至97.02%(95%CI 95.22–98.16%)。
- 测试集B各亚类准确率范围为87.94%(95%CI 85.08–90.31%)至98.83%(95%CI 97.60–99.43)。
- 四分类加权平均MCC测试集A为0.59,测试集B为0.79。
- 区分管腔型与非管腔型病变的PPV测试集A为93.29%(95%CI 90.63–95.23%),测试集B为88.21%(95%CI 85.12–90.73%)。
临床应用与阅片要点
- 作者认为基于治疗前超声图像的DCNN有助于临床医生以较高准确率评估肿瘤特征。
- 作者认为基于DCNN模型可使患者管理更加精确。
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
OBJECTIVES: To evaluate the prediction performance of deep convolutional neural network (DCNN) based on ultrasound (US) images for the assessment of breast cancer molecular subtypes.
METHODS: A dataset of 4828 US images from 1275 patients with primary breast cancer were used as the training samples. DCNN models were constructed primarily to predict the four St. Gallen molecular subtypes and secondarily to identify luminal disease from non-luminal disease based on the ground truth from immunohistochemical of whole tumor surgical specimen. US images from two other institutions were retained as independent test sets to validate the system. The models' performance was analyzed using per-class accuracy, positive predictive value (PPV), and Matthews correlation coefficient (MCC).
RESULTS: The model achieved good performance in identifying the four breast cancer molecular subtypes in the two test sets, with accuracy ranging from 80.07% (95% CI, 76.49-83.23%) to 97.02% (95% CI, 95.22-98.16%) and 87.94% (95% CI, 85.08-90.31%) to 98.83% (95% CI, 97.60-99.43) for the two test cohorts for each sub-category, respectively. In terms of 4-class weighted average MCC, the model achieved 0.59 for test cohort A and 0.79 for test cohort B. Specifically, the DCNN also yielded good diagnostic performance in discriminating luminal disease from non-luminal disease, with a PPV of 93.29% (95% CI, 90.63-95.23%) and 88.21% (95% CI, 85.12-90.73%) for the two test cohorts, respectively.
CONCLUSION: Using pretreatment US images of the breast cancer, deep learning model enables the assessment of molecular subtypes with high diagnostic accuracy.
TRIAL REGISTRATION: Clinical trial number: ChiCTR1900027676 KEY POINTS: • Deep convolutional neural network (DCNN) helps clinicians assess tumor features with accuracy. • Multicenter retrospective study shows that DCNN derived from pretreatment ultrasound imagine improves the prediction of breast cancer molecular subtypes. • Management of patients becomes more precise based on the DCNN model.
引用
- Jiang M, Zhang D, Tang SC, et al. Deep learning with convolutional neural network in the assessment of breast cancer molecular subtypes based on US images: a multicenter retrospective study. Eur Radiol. 2020. PMID: 33226454. doi:10.1007/s00330-020-07544-8
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。