Liu Yongkai, Yang Guang, Hosseiny Melina, Azadikhah Afshin, Mirak Sohrab Afshari, Miao Qi, Raman Steven S, Sung Kyunghyun
Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
Physics and Biology in Medicine IDP, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
IEEE Access. 2020;8:151817-151828. doi: 10.1109/ACCESS.2020.3017168. Epub 2020 Aug 17.
Automatic segmentation of prostatic zones on multiparametric MRI (mpMRI) can improve the diagnostic workflow of prostate cancer. We designed a spatial attentive Bayesian deep learning network for the automatic segmentation of the peripheral zone (PZ) and transition zone (TZ) of the prostate with uncertainty estimation. The proposed method was evaluated by using internal and external independent testing datasets, and overall uncertainties of the proposed model were calculated at different prostate locations (apex, middle, and base). The study cohort included 351 MRI scans, of which 304 scans were retrieved from a de-identified publicly available datasets (PROSTATEX) and 47 scans were extracted from a large U.S. tertiary referral center (external testing dataset; ETD)). All the PZ and TZ contours were drawn by research fellows under the supervision of expert genitourinary radiologists. Within the PROSTATEX dataset, 259 and 45 patients (internal testing dataset; ITD) were used to develop and validate the model. Then, the model was tested independently using the ETD only. The segmentation performance was evaluated using the Dice Similarity Coefficient (DSC). For PZ and TZ segmentation, the proposed method achieved mean DSCs of 0.80±0.05 and 0.89±0.04 on ITD, as well as 0.79±0.06 and 0.87±0.07 on ETD. For both PZ and TZ, there was no significant difference between ITD and ETD for the proposed method. This DL-based method enabled the accuracy of the PZ and TZ segmentation, which outperformed the state-of-art methods (Deeplab V3+, Attention U-Net, R2U-Net, USE-Net and U-Net). We observed that segmentation uncertainty peaked at the junction between PZ, TZ and AFS. Also, the overall uncertainties were highly consistent with the actual model performance between PZ and TZ at three clinically relevant locations of the prostate.
多参数磁共振成像（mpMRI）上前列腺区域的自动分割可以改善前列腺癌的诊断流程。我们设计了一种空间注意力贝叶斯深度学习网络，用于对前列腺外周带（PZ）和移行带（TZ）进行自动分割，并进行不确定性估计。通过使用内部和外部独立测试数据集对所提出的方法进行评估，并在所提出模型的不同前列腺位置（尖部、中部和基部）计算总体不确定性。研究队列包括351例MRI扫描，其中304例扫描取自一个经过去识别处理的公开可用数据集（PROSTATEX），47例扫描取自美国一家大型三级转诊中心（外部测试数据集；ETD）。所有PZ和TZ轮廓均由研究员在泌尿生殖系统专家放射科医生的监督下绘制。在PROSTATEX数据集中，259例和45例患者（内部测试数据集；ITD）用于开发和验证模型。然后，仅使用ETD对模型进行独立测试。使用骰子相似系数（DSC）评估分割性能。对于PZ和TZ分割，所提出的方法在ITD上的平均DSC分别为0.80±0.05和0.89±0.04，在ETD上分别为0.79±0.06和0.87±0.07。对于PZ和TZ两者，所提出的方法在ITD和ETD之间均无显著差异。这种基于深度学习的方法实现了PZ和TZ分割的准确性，其性能优于现有方法（深度Lab V3 +、注意力U-Net、R2U-Net、USE-Net和U-Net）。我们观察到分割不确定性在PZ、TZ和前纤维肌基质（AFS）之间的交界处达到峰值。此外，在前列腺的三个临床相关位置，总体不确定性与PZ和TZ之间的实际模型性能高度一致。
