深度学习架构在表观扩散系数图上检测和分割临床显著性前列腺癌的短期重测可重复性
研究纳入112例前列腺癌患者,同日行两次前列腺MRI,以全mount前列腺切除标本为参考,评估两种U-Net卷积神经网络在三种ADCm b值设置下检测和分割临床显著性前列腺癌的短期重测可重复性;三种b值设置下病灶平均ADCm的ICC为0.86-0.98,两种CNN切片级检测的ICC为0.80-0.83、一致率66-72%、DSC为0.68-0.72;作者结论认为两种网络在切片级检测csPCa上具有可重复性,分割可重复性受扫描间变异和参考标准分割可重复性影响。
要点
- 三种ADCm b值设置下,临床显著性前列腺癌病灶平均ADCm的ICC(3,1)为0.86-0.98。
- 两种U-Net卷积神经网络切片级和病灶级检测与分割的ICC(3,1)为0.80-0.83、一致率66-72%、DSC为0.68-0.72。
- 网络分割csPCa病灶的可重复性受扫描间变异和参考标准分割可重复性影响,可能随扫描间可重复性改善而提高。
诊断标准与关键数值
- 临床显著性前列腺癌定义为Gleason分级分组>1。
- 三种ADCm b值设置下,临床显著性前列腺癌病灶平均ADCm的重测可重复性ICC(3,1)=0.86-0.98。
- 两种U-Net卷积神经网络在切片级和病灶级检测与分割临床显著性前列腺癌的ICC(3,1)为0.80-0.83、一致率为66-72%、DSC为0.68-0.72。
临床应用与阅片要点
- 本研究表明两种U-Net卷积神经网络在切片级检测临床显著性前列腺癌上具有可重复性,可重复性指标以ICC(3,1)、一致率和DSC表示。
- 网络分割临床显著性前列腺癌病灶的可重复性受扫描间变异和参考标准分割可重复性影响,可能随扫描间可重复性改善而提高。
局限性
- 网络分割临床显著性前列腺癌病灶的可重复性受扫描间变异和参考标准分割可重复性的影响。
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 short-term test-retest repeatability of a deep learning architecture (U-Net) in slice- and lesion-level detection and segmentation of clinically significant prostate cancer (csPCa: Gleason grade group > 1) using diffusion-weighted imaging fitted with monoexponential function, ADCm.
METHODS: One hundred twelve patients with prostate cancer (PCa) underwent 2 prostate MRI examinations on the same day. PCa areas were annotated using whole mount prostatectomy sections. Two U-Net-based convolutional neural networks were trained on three different ADCm b value settings for (a) slice- and (b) lesion-level detection and (c) segmentation of csPCa. Short-term test-retest repeatability was estimated using intra-class correlation coefficient (ICC(3,1)), proportionate agreement, and dice similarity coefficient (DSC). A 3-fold cross-validation was performed on training set (N = 78 patients) and evaluated for performance and repeatability on testing data (N = 34 patients).
RESULTS: For the three ADCm b value settings, repeatability of mean ADCm of csPCa lesions was ICC(3,1) = 0.86-0.98. Two CNNs with U-Net-based architecture demonstrated ICC(3,1) in the range of 0.80-0.83, agreement of 66-72%, and DSC of 0.68-0.72 for slice- and lesion-level detection and segmentation of csPCa. Bland-Altman plots suggest that there is no systematic bias in agreement between inter-scan ground truth segmentation repeatability and segmentation repeatability of the networks.
CONCLUSIONS: For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.
KEY POINTS: • For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. • The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.
引用
- Hiremath A, Shiradkar R, Merisaari H, et al. Test-retest repeatability of a deep learning architecture in detecting and segmenting clinically significant prostate cancer on apparent diffusion coefficient (ADC) maps. Eur Radiol. 2020. PMID: 32700021. doi:10.1007/s00330-020-07065-4
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。