深度学习算法在前列腺癌患者中用于肿瘤分割和临床显著癌症的鉴别。

BACKGROUND: We investigated the feasibility of a deep learning algorithm (DLA) based on apparent diffusion coefficient (ADC) maps for the segmentation and discrimination of clinically significant cancer (CSC, Gleason score ≥ 7) from non-CSC in patients with prostate cancer (PCa). METHODS: Data from a total of 149 consecutive patients who had undergone 3T-MRI and been pathologically diagnosed with PCa were initially collected. The labelled data (148 images for GS6, 580 images for GS7) were applied for tumor segmentation using a convolutional neural network (CNN). For classification, 93 images for GS6 and 372 images for GS7 were used. For external validation, 22 consecutive patients from five different institutions (25 images for GS6, 70 images for GS7) representing different MR machines were recruited. RESULTS: Regarding segmentation and classification, U-Net and DenseNet were used, respectively. The tumor Dice scores for internal and external validation were 0.822 and 0.7776, respectively. As for classification, the accuracies of internal and external validation were 73 and 75%, respectively. For external validation, diagnostic predictive values for CSC (sensitivity, specificity, positive predictive value and negative predictive value) were 84, 48, 82 and 52%, respectively. CONCLUSIONS: Tumor segmentation and discrimination of CSC from non-CSC is feasible using a DLA developed based on ADC maps (b2000) alone.

背景：我们研究了一种基于表观扩散系数 (ADC) 图的深度学习算法 (DLA) ，用于对前列腺癌 (PCa) 患者中临床显著癌症 (CSC，Gleason 评分≥7) 与非 CSC 的分割和区分的可行性。

方法：共收集了 149 例连续接受 3T-MRI 检查并经病理诊断为 PCa 的患者的数据。使用卷积神经网络 (CNN) 对标记数据 (GS6 图像 148 张，GS7 图像 580 张) 进行肿瘤分割。用于分类的有 GS6 图像 93 张，GS7 图像 372 张。为了外部验证，从五个不同机构招募了 22 例连续患者（GS6 图像 25 张，GS7 图像 70 张），代表不同的磁共振机器。

结果：分别使用 U-Net 和 DenseNet 进行分割和分类。内部和外部验证的肿瘤 Dice 评分分别为 0.822 和 0.7776。对于分类，内部和外部验证的准确率分别为 73%和 75%。对于外部验证，CSC 的诊断预测值（敏感性、特异性、阳性预测值和阴性预测值）分别为 84%、48%、82%和 52%。

结论：仅使用基于 ADC 图（b2000）的 DLA 即可实现肿瘤的分割和 CSC 与非 CSC 的区分。