Rationale: 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. Methods: 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. Results: 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% (P < 0.001) and downgrading rate by 6.4% (P = 0.029). Conclusions: 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.

中文翻译：

---

类似放射科医生的人工智能，用于根治性前列腺切除术的分级组预测，以减少活检的升级和降级。


理由：通过预测患者级别的 RP 格里森分级组 (GG) 来减少穿刺活检 (NB) 和根治性前列腺切除术 (RP) 之间的升级和降级，以避免治疗过度和治疗不足。方法：本研究回顾性纳入来自两家医疗机构的 575 名患者。所有患者均接受活检前磁共振（MR）检查，并获得NB和RP的病理学评估。总共 12,708 个原始男性盆腔 MR 图像切片（带脂肪抑制的 T2 加权序列，T2WI-FS），包含 5405 个前列腺组织切片，以及 2,753 个肿瘤注释（仅 T2WI-FS 使用 RP 病理切片作为基本事实进行注释）分析患者水平 RP GG 的预测。我们提出了一种前列腺癌 (PCa) 框架 PCa-GGNet，它基于深度强化学习 (DRL) 来模拟放射科医生的行为。我们使用多中心格式开发并验证了它。结果：我们模型的准确性 (ACC) 超过 NB 结果（0.815 [95% 置信区间 (CI)：0.773-0.857] 对比 0.437 [95% CI：0.335-0.539]）。 PCa-GGNet 的得分（kappa 值：0.761）高于 NB（kappa 值：0.289）。我们的模型将升级率显着降低了 27.9% (P < 0.001)，将降级率显着降低了 6.4% (P = 0.029)。结论：使用 MRI 的 DRL 可应用于患者水平 RP GG 的预测，以减少活检的升级和降级，从而潜在地提高前列腺癌肿瘤控制的临床效益。