School of Computer Science and Engineering, Southeast University, Nanjing, China.
CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, the State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
Theranostics. 2020 Sep 2;10(22):10200-10212. doi: 10.7150/thno.48706. eCollection 2020.
To reduce upgrading and downgrading between needle biopsy (NB) and radical prostatectomy (RP) by predicting patient-level Gleason grade groups (GGs) of RP to avoid over- and under-treatment. In this study, we retrospectively enrolled 575 patients from two medical institutions. All patients received prebiopsy magnetic resonance (MR) examinations, and pathological evaluations of NB and RP were available. A total of 12,708 slices of original male pelvic MR images (T2-weighted sequences with fat suppression, T2WI-FS) containing 5405 slices of prostate tissue, and 2,753 tumor annotations (only T2WI-FS were annotated using RP pathological sections as ground truth) were analyzed for the prediction of patient-level RP GGs. We present a prostate cancer (PCa) framework, PCa-GGNet, that mimics radiologist behavior based on deep reinforcement learning (DRL). We developed and validated it using a multi-center format. Accuracy (ACC) of our model outweighed NB results (0.815 [95% confidence interval (CI): 0.773-0.857] vs. 0.437 [95% CI: 0.335-0.539]). The PCa-GGNet scored higher (kappa value: 0.761) than NB (kappa value: 0.289). Our model significantly reduced the upgrading rate by 27.9% ( < 0.001) and downgrading rate by 6.4% ( = 0.029). DRL using MRI can be applied to the prediction of patient-level RP GGs to reduce upgrading and downgrading from biopsy, potentially improving the clinical benefits of prostate cancer oncologic controls.
为了减少通过预测前列腺根治术（RP）中患者级别的 Gleason 分级组（GGs）来减少针吸活检（NB）和根治性前列腺切除术（RP）之间的升级和降级，从而避免过度和不足的治疗。在这项研究中，我们从两个医疗机构回顾性地招募了 575 名患者。所有患者均接受了活检前磁共振（MR）检查，并且可获得 NB 和 RP 的病理学评估。总共分析了 12708 张原始男性骨盆 MR 图像（带脂肪抑制的 T2 加权序列，T2WI-FS），其中包含 5405 张前列腺组织的切片，以及 2753 个肿瘤注释（仅使用 RP 病理切片作为ground truth对 T2WI-FS 进行注释），以预测患者级别的 RP GG。我们提出了一种基于深度学习强化学习（DRL）的前列腺癌（PCa）框架，即 PCa-GGNet。我们使用多中心格式对其进行了开发和验证。我们的模型的准确性（ACC）优于 NB 结果（0.815 [95％置信区间（CI）：0.773-0.857] vs. 0.437 [95％CI：0.335-0.539]）。PCa-GGNet 的评分（kappa 值：0.761）高于 NB （kappa 值：0.289）。我们的模型使升级率显著降低了 27.9％（<0.001），降级率降低了 6.4％（= 0.029）。使用 MRI 的 DRL 可应用于预测患者级别的 RP GG，以减少活检的升级和降级，从而潜在地改善前列腺癌肿瘤控制的临床获益。
Zotero 插件