论文标题
在3D卷积神经网络中编码BPMRI中前列腺癌检测的临床先验
Encoding Clinical Priori in 3D Convolutional Neural Networks for Prostate Cancer Detection in bpMRI
论文作者
论文摘要
我们假设解剖学先验可以是基于U-NET体系结构的最新卷积神经网络（CNN），将特定领域的临床知识注入到最新的卷积神经网络（CNN）。我们引入了概率人群，该概率人群捕获了临床上显着的前列腺癌（CSPCA）的空间流行率和区别，以改善双参数MR成像（BPMRI）中的计算机辅助检测（CAD）。为了评估性能，我们使用800个机构训练验证扫描训练U-NET，U-seresnet，UNET ++和注意U-NET的3D适应，并与放射学估计的注释以及我们计算的先验。对于200个独立测试BPMRI扫描CSPCA的划定，我们提出的编码临床先验的提议的方法表明，改善基于患者的诊断（AUROC增加8.70％）和病变级检测的强大能力（高达8.70％）和跨病变级别的检测（平均为0.1-10个PAUC），彼此之间的平均pauc较高效率为1.08 PAUC，彼此之间的效率为1.08 Pauc，跨患者之间的所有体系均增加了所有四个架构）。
We hypothesize that anatomical priors can be viable mediums to infuse domain-specific clinical knowledge into state-of-the-art convolutional neural networks (CNN) based on the U-Net architecture. We introduce a probabilistic population prior which captures the spatial prevalence and zonal distinction of clinically significant prostate cancer (csPCa), in order to improve its computer-aided detection (CAD) in bi-parametric MR imaging (bpMRI). To evaluate performance, we train 3D adaptations of the U-Net, U-SEResNet, UNet++ and Attention U-Net using 800 institutional training-validation scans, paired with radiologically-estimated annotations and our computed prior. For 200 independent testing bpMRI scans with histologically-confirmed delineations of csPCa, our proposed method of encoding clinical priori demonstrates a strong ability to improve patient-based diagnosis (upto 8.70% increase in AUROC) and lesion-level detection (average increase of 1.08 pAUC between 0.1-10 false positives per patient) across all four architectures.
