深度卷积神经网络用于超声甲状腺结节分类:与放射科医生诊断性能的比较
本研究回顾性纳入2010年1月至2020年3月在本机构接受超声引导下细针穿刺活检的甲状腺结节患者超声图像,训练并验证三种深度学习模型(VGG16、VGG19、ResNet)鉴别良恶性结节,并与四位放射科医生的诊断比较。深度学习模型在内测集上AUC高于放射科医生(0.83-0.86 vs 0.71-0.76,P<0.05),但在外测集上未见优势;VGG16在内测集(AUC 0.86,敏感度91.8%,特异度73.2%)和外测集(AUC 0.83,敏感度78.6%,特异度76.8%)均表现最高,但各深度学习模型间AUC无统计学差异。结论认为深度学习模型与放射科医生诊断性能相当,可能有助于辅助医生诊断甲状腺结节。
要点
- 深度学习模型在内测集鉴别甲状腺结节良恶性AUC高于放射科医生(0.83-0.86 vs 0.71-0.76,P<0.05)。
- 外测集上深度学习模型与放射科医生诊断性能未见优势差异。
- VGG16模型内测集AUC 0.86(敏感度91.8%,特异度73.2%),外测集AUC 0.83(敏感度78.6%,特异度76.8%)。
核心结论
- 深度学习模型在超声图像上鉴别甲状腺结节良恶性的诊断性能与放射科医生相当,可能有助于辅助放射科医生诊断甲状腺结节。
研究设计与样本
- 回顾性研究,纳入2010年1月至2020年3月在本机构接受超声引导下细针穿刺活检的甲状腺结节患者超声图像,共15409张图像来自7321例患者(平均年龄60±13岁,恶性结节占20.7%),随机分为训练集(n=12327)和验证集(n=3082),另设独立内测集(n=432,197例患者)和外测集(n=168,59例患者),训练三种图像分类深度学习模型(VGG16、VGG19、ResNet),由四位放射科医生独立分类图像,以超声引导下细针穿刺活检结果为参考标准。
诊断标准与关键数值
- VGG16模型内测集AUC 0.86,敏感度91.8%,特异度73.2%。
- VGG16模型外测集AUC 0.83,敏感度78.6%,特异度76.8%。
- 深度学习模型内测集AUC 0.83-0.86,放射科医生内测集AUC 0.71-0.76,差异有统计学意义(P<0.05)。
- 外测集上深度学习模型与放射科医生诊断性能未见优势差异。
- 各深度学习模型间AUC无统计学差异。
临床应用与阅片要点
- 原文未据此给出临床推荐。
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
PURPOSE: This study aimed to train and validate deep learning (DL) models for differentiating malignant from benign thyroid nodules on US images and compare their performance with that of radiologists.
METHODS: Images of thyroid nodules in patients who underwent US-guided fine-needle aspiration biopsy at our institution between January 2010 and March 2020 were retrospectively reviewed. Four radiologists independently classified the images. Images of thyroid nodules were trained using three different image classification DL models (VGG16, VGG19, and ResNet). The diagnostic performances of the DL models were calculated for the internal and external datasets and compared with the diagnoses of the four radiologists. Pairwise comparisons of the AUCs between the radiologists and DL models were made using bootstrap-based tests.
RESULTS: In total, 15,409 images from 7,321 patients (mean age, 60 ± 13 years; malignant nodules, 20.7%) were randomly grouped into training (n = 12,327) and validation (n = 3,082) sets. Independent internal (n = 432; 197 patients) and external (n = 168; 59 patients) test sets were also acquired. The DL models demonstrated a higher diagnostic performance than the radiologists in the internal test set (AUC, 0.83 - 0.86 vs. 0.71 - 0.76, P < 0.05), but not in the external test set. The VGG16 model demonstrated the highest diagnostic performance in internal (AUC, 0.86; sensitivity, 91.8%; specificity, 73.2%) and external (AUC: 0.83; sensitivity: 78.6%; specificity: 76.8%) test sets. However, no statistical differences were found in the AUCs among the DL models.
CONCLUSIONS: The DL models demonstrated comparable diagnostic performance to radiologists in distinguishing benign from malignant thyroid nodules on US images and may play a potential role in augmenting radiologists' diagnosis of thyroid nodules.
引用
- Kim, Choi, Hur, et al. Deep convolutional neural network for classification of thyroid nodules on ultrasound: Comparison of the diagnostic performance with that of radiologists. Eur J Radiol. 2022. PMID: 35512512. doi:10.1016/j.ejrad.2022.110335
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。