双机构前列腺MRI全自动深度学习:队列规模与异质性的影响
在全量训练集上,U-Net敏感度与特异度与PI-RADS无统计学差异;减少训练集规模性能下降,而增加PROSTATEx或多扫描仪数据未提升性能。
要点
- U-Net检测临床显著前列腺癌的敏感度与特异度与PI-RADS评估相当。
- 训练集规模不足会显著降低U-Net性能。
- 增加异质性训练数据(多扫描仪或双机构)未提升性能。
核心结论
- 在大规模机构测试集上,U-Net性能与临床PI-RADS评估相似。
- 增加训练数据量可提升性能,但增加数据异质性(多扫描仪或双机构)未带来额外获益。
研究设计与样本
- 回顾性研究,使用双参数(T2WI和DWI)前列腺MRI,来自多台1.5T和3.0T扫描仪。
- 参考标准为靶向和扩展系统MRI-经直肠超声融合活检,临床显著前列腺癌定义为ISUP分级分组≥2。
- U-Net在完整、缩减和PROSTATEx增强训练集上进行内部验证,并在机构测试集和PROSTATEx测试集上进行外部验证。
- 性能比较采用敏感度、特异度、预测值和Dice系数。
诊断标准与关键数值
- 在测试集上,按患者计算,PI-RADS≥3的敏感度为97%(241/249),特异度为19%(82/433);PI-RADS≥4的敏感度为90%(223/249),特异度为56%(242/433)。
- 全量U-Net对应敏感度为97%(241/249)和88%(219/249),特异度为20%(86/433)和59%(254/433),与PI-RADS相比差异均无统计学意义(所有比较P>0.3)。
- 使用仅171例连续检查的缩减训练集训练的U-Net性能较差(P<0.001)。
- 前列腺分割的Dice系数为0.90;在PI-RADS类别3/4等效水平,MRI病灶分割的Dice系数分别为0.42和0.53。
临床应用与阅片要点
- U-Net可作为前列腺MRI阅片的辅助工具,其检测临床显著前列腺癌的敏感度与特异度与PI-RADS评估相当。
- 训练数据量对深度学习性能至关重要,样本量不足时性能下降。
- 增加多扫描仪或双机构数据未见性能提升,提示数据异质性策略需进一步优化。
局限性
- 回顾性研究设计。
- 原文未明确报告研究是否为单中心或多中心。
- 参考标准基于活检,可能存在验证偏倚。
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
BACKGROUND: The potential of deep learning to support radiologist prostate magnetic resonance imaging (MRI) interpretation has been demonstrated.
PURPOSE: The aim of this study was to evaluate the effects of increased and diversified training data (TD) on deep learning performance for detection and segmentation of clinically significant prostate cancer-suspicious lesions.
MATERIALS AND METHODS: In this retrospective study, biparametric (T2-weighted and diffusion-weighted) prostate MRI acquired with multiple 1.5-T and 3.0-T MRI scanners in consecutive men was used for training and testing of prostate segmentation and lesion detection networks. Ground truth was the combination of targeted and extended systematic MRI-transrectal ultrasound fusion biopsies, with significant prostate cancer defined as International Society of Urological Pathology grade group greater than or equal to 2. U-Nets were internally validated on full, reduced, and PROSTATEx-enhanced training sets and subsequently externally validated on the institutional test set and the PROSTATEx test set. U-Net segmentation was calibrated to clinically desired levels in cross-validation, and test performance was subsequently compared using sensitivities, specificities, predictive values, and Dice coefficient.
RESULTS: One thousand four hundred eighty-eight institutional examinations (median age, 64 years; interquartile range, 58-70 years) were temporally split into training (2014-2017, 806 examinations, supplemented by 204 PROSTATEx examinations) and test (2018-2020, 682 examinations) sets. In the test set, Prostate Imaging-Reporting and Data System (PI-RADS) cutoffs greater than or equal to 3 and greater than or equal to 4 on a per-patient basis had sensitivity of 97% (241/249) and 90% (223/249) at specificity of 19% (82/433) and 56% (242/433), respectively. The full U-Net had corresponding sensitivity of 97% (241/249) and 88% (219/249) with specificity of 20% (86/433) and 59% (254/433), not statistically different from PI-RADS (P > 0.3 for all comparisons). U-Net trained using a reduced set of 171 consecutive examinations achieved inferior performance (P < 0.001). PROSTATEx training enhancement did not improve performance. Dice coefficients were 0.90 for prostate and 0.42/0.53 for MRI lesion segmentation at PI-RADS category 3/4 equivalents.
CONCLUSIONS: In a large institutional test set, U-Net confirms similar performance to clinical PI-RADS assessment and benefits from more TD, with neither institutional nor PROSTATEx performance improved by adding multiscanner or bi-institutional TD.
引用
- Netzer N, Weißer C, Schelb P, et al. Fully Automatic Deep Learning in Bi-institutional Prostate Magnetic Resonance Imaging: Effects of Cohort Size and Heterogeneity. Invest Radiol. 2021. PMID: 34049336. doi:10.1097/RLI.0000000000000791
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。