背景:在这项工作中,我们比较输入水平,特征级和决策级数据融合技术,用于自动检测有临床意义的前列腺病变(csPCa)。
方法:使用Unet作为基线开发了多种深度学习CNN架构。CNN使用两种多参数MRI图像(T2W,ADC,和高b值)和定量临床数据(前列腺特异性抗原(PSA),PSA密度(PSAD),前列腺体积和总肿瘤体积(GTV)),只有MP-MRI图像(n=118),作为输入。此外,来自整个坐骑组织病理学图像(n=22)的共同配准的地面实况数据被用作评估的测试集。
结果:早期/中期/晚期融合的CNN精度为0.41/0.51/0.61,召回值为0.18/0.22/0.25,平均精度为0.13/0.19/0.27,F评分为0.55/0.67/0.76。DiceSorensen系数(DSC)用于评估将mpMRI与参数临床数据相结合以检测csPCa的影响。我们比较了用mpMRI和参数化临床训练的CNN的预测与仅用mpMRI图像作为输入的CNN的预测之间的DSC。我们获得的DSC数据分别为0.30/0.34/0.36和0.26/0.33/0.34。此外,我们评估了每个mpMRI输入通道对csPCa检测任务的影响,并获得了0.14/0.25/0.28的DSC。
结论:结果表明,决策级融合网络在前列腺病变检测任务中表现更好。将mpMRI数据与定量临床数据相结合并没有显示出这些网络之间的显着差异(p=0.26/0.62/0.85)。结果表明,用所有mpMRI数据训练的CNN优于具有较少输入通道的CNN,这与当前的临床协议一致,其中相同的输入用于PI-RADS病变评分。
背景:该试验在德国临床研究注册中心(DRKS)以提案编号Nr进行回顾性注册。476/14&476/19。
BACKGROUND: In this work, we compare input level, feature level and decision level data fusion techniques for automatic detection of clinically significant prostate lesions (csPCa).
METHODS: Multiple deep learning CNN architectures were developed using the Unet as the baseline. The CNNs use both multiparametric MRI images (T2W, ADC, and High b-value) and quantitative clinical data (prostate specific antigen (PSA), PSA density (PSAD), prostate gland volume & gross tumor volume (GTV)), and only mp-MRI images (n = 118), as input. In addition, co-registered ground truth data from whole mount histopathology images (n = 22) were used as a test set for evaluation.
RESULTS: The CNNs achieved for early/intermediate / late level fusion a precision of 0.41/0.51/0.61, recall value of 0.18/0.22/0.25, an average precision of 0.13 / 0.19 / 0.27, and F scores of 0.55/0.67/ 0.76. Dice Sorensen Coefficient (DSC) was used to evaluate the influence of combining mpMRI with parametric clinical data for the detection of csPCa. We compared the DSC between the predictions of CNN\'s trained with mpMRI and parametric clinical and the CNN\'s trained with only mpMRI images as input with the ground truth. We obtained a DSC of data 0.30/0.34/0.36 and 0.26/0.33/0.34 respectively. Additionally, we evaluated the influence of each mpMRI input channel for the task of csPCa detection and obtained a DSC of 0.14 / 0.25 / 0.28.
CONCLUSIONS: The results show that the decision level fusion network performs better for the task of prostate lesion detection. Combining mpMRI data with quantitative clinical data does not show significant differences between these networks (p = 0.26/0.62/0.85). The results show that CNNs trained with all mpMRI data outperform CNNs with less input channels which is consistent with current clinical protocols where the same input is used for PI-RADS lesion scoring.
BACKGROUND: The trial was registered retrospectively at the German Register for Clinical Studies (DRKS) under proposal number Nr. 476/14 & 476/19.