DeepLabV3自动标准化剪切波弹性成像有效区域提升甲状腺结节恶性评估
本研究为单机构多院区回顾性研究,纳入678个训练结节和280个跨院区验证结节,采用DeepLabV3模型自动勾画剪切波弹性成像(SWE)有效区域。与专家共识对比,模型勾画区域与共识的一致性优于高年资和低年资医生,且基于模型提取的最大杨氏模量(Emax)诊断甲状腺恶性结节AUC更高。
要点
- DeepLabV3自动勾画SWE有效区域,与专家共识一致性优于人工勾画。
- 基于模型Emax的AUC为0.86,高于医生人工勾画(0.78和0.73)。
- 自动标准化可减少操作者依赖性,提高超声评估甲状腺结节的稳定性。
核心结论
- DeepLabV3自动标准化SWE有效区域可提高Emax测量的稳定性和恶性评估效能。
- 模型勾画区域与专家共识一致性更高,诊断性能优于医生手动勾画。
研究设计与样本
- 回顾性单机构多院区研究。
- 训练集678个结节,跨院区验证集280个结节。
- 使用配准的B-mode和SWE图像作为双通道输入的DeepLabV3模型。
- 参考标准为病理诊断(细胞学或组织学)。
关键影像表现/征象
- 模型勾画区域与共识参考的一致性更高:IoU 0.82±0.04,Dice 0.90±0.15,HD95 2.39±0.81mm。
- 高年资医生:IoU 0.76±0.09,Dice 0.86±0.11,HD95 3.61±1.44mm;低年资医生:IoU 0.67±0.14,Dice 0.80±0.12,HD95 4.23±1.19mm。
- 模型勾画的Emax_DL显示AUC为0.86(95%CI 0.80-0.91),高于医生勾画。
诊断标准与关键数值
- Emax_DL诊断恶性AUC 0.86(95%CI 0.80-0.91),优于Emax_R2 0.78(0.74-0.86)和Emax_R1 0.73(0.67-0.81)。
- 最优截断值处似然比为3.56。
临床应用与阅片要点
- 临床可使用DeepLabV3自动勾画SWE有效区域,减少人为误差。
- 报告时注明Emax测量基于模型勾画区域,提高结果可重复性。
- 注意模型需在配准的B-mode和SWE图像上运行。
局限性
- 单机构多院区研究,外部推广性需进一步验证。
- 回顾性设计可能存在选择偏倚。
- 模型仅针对Emax指标,未覆盖其他弹性参数。
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
RATIONALE AND OBJECTIVES: To assess whether a DeepLabV3-based model can standardize the shear-wave elastography (SWE) effective region in thyroid nodules and improve maximum Young's modulus (Emax)-based malignancy assessment.
MATERIALS AND METHODS: This retrospective single-institution multicampus study included 678 training and 280 intercampus validation nodules. A DeepLabV3 model using registered B-mode and SWE images as two-channel input automatically delineated the SWE effective region. In the validation cohort, model-derived and reader-defined regions were compared with a Simultaneous Truth and Performance Level Estimation-derived expert consensus using intersection over union (IoU), Dice coefficient, and 95th percentile Hausdorff distance (HD95). Emax was extracted from each region, and diagnostic performance was evaluated using pathologic diagnosis (cytology or histopathology) as the reference standard.
RESULTS: DeepLabV3 showed better agreement with the consensus reference than the senior and junior readers, with higher IoU (0.82±0.04 vs. 0.76±0.09 and 0.67±0.14) and dice (0.90±0.15 vs. 0.86±0.11 and 0.80±0.12), and lower HD95 (2.39±0.81 mm vs. 3.61±1.44 mm and 4.23±1.19 mm; all p < 0.01). Emax_DL achieved a higher area under the curve than Emax_R2 and Emax_R1 (0.86 [95% confidence interval: 0.80-0.91] vs. 0.78 [0.74-0.86] and 0.73 [0.67-0.81]), with a likelihood ratio of 3.56 at the optimal cutoff.
CONCLUSION: Automated standardization of the SWE effective region using DeepLabV3 may provide a more consistent and less operator-dependent basis for Emax measurement, with potential to improve ultrasound-based assessment of thyroid nodules.
引用
- Hu, Tang, Ren, et al. Automated Standardization of the Shear-wave Elastography Effective Region Using DeepLabV3 Improves Malignancy Assessment in Thyroid Nodules: A Single-institution Multicampus Study. Acad Radiol. 2026. PMID: 42632762. doi:10.1016/j.acra.2026.07.079
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。