Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing, 100034, China.
Beijing Smart Tree Medical Technology Co. Ltd., No. 24, Huangsi Street, Xicheng District, Beijing, 100011, China.
Abdom Radiol (NY). 2022 Sep;47(9):3327-3337. doi: 10.1007/s00261-022-03583-5. Epub 2022 Jun 28.
To develop and test radiomics models based on manually corrected or automatically gained masks on ADC maps for pelvic lymph node metastasis (PLNM) prediction in patients with prostate cancer (PCa).
A primary cohort of 474 patients with PCa who underwent prostate mpMRI were retrospectively enrolled for PLNM prediction between January 2017 and January 2020. They were then randomly split into training/validation (n = 332) and test (n = 142) groups for model development and internal testing. Four radiomics models were developed using four masks (manually corrected/automatic prostate gland and PCa lesion segmentation) based on the ADC maps using the primary cohort. Another cohort of 128 patients who underwent radical prostatectomy (RP) with extended pelvic lymph node dissection (ePLND) for PCa was used as the testing cohort between February 2020 and October 2021. The performance of the models was evaluated in terms of discrimination and clinical usefulness using the area under the curve (AUC) and decision curve analysis (DCA). The optimal radiomics model was further compared with Memorial Sloan Kettering Cancer Center (MSKCC) and Briganti 2017 nomograms, and PI-RADS assessment.
17 (13.28%) Patients with PLNM were included in the testing cohort. The radiomics model based on the mask of automatically segmented prostate obtained the highest AUC among the four radiomics models (0.73 vs. 0.63 vs. 0.70 vs. 0.56). Briganti 2017, MSKCC nomograms, and PI-RADS assessment-yielded AUCs of 0.69, 0.71, and 0.70, respectively, and no significant differences were found compared with the optimal radiomics model (P = 0.605-0.955).
The radiomics model based on the mask of automatically segmented prostate offers a non-invasive method to predict PLNM for patients with PCa. It shows comparable accuracy to the current MKSCC and Briganti nomograms.
开发和测试基于手动校正或自动获得的 ADC 图掩模的放射组学模型，以预测前列腺癌（PCa）患者的盆腔淋巴结转移（PLNM）。
回顾性纳入 2017 年 1 月至 2020 年 1 月期间接受前列腺 mpMRI 的 474 例 PCa 患者的主要队列，以预测 PLNM。然后，他们被随机分为训练/验证（n=332）和测试（n=142）组，用于模型开发和内部测试。使用主要队列中基于 ADC 图的四个掩模（手动校正/自动前列腺和 PCa 病变分割），开发了四个放射组学模型。另一组 128 例接受根治性前列腺切除术（RP）和扩展盆腔淋巴结清扫术（ePLND）的 PCa 患者于 2020 年 2 月至 2021 年 10 月作为测试队列。使用曲线下面积（AUC）和决策曲线分析（DCA）评估模型的鉴别和临床实用性。还将最优放射组学模型与 Memorial Sloan Kettering Cancer Center（MSKCC）和 Briganti 2017 列线图以及 PI-RADS 评估进行比较。
在测试队列中纳入了 17 例（13.28%）有 PLNM 的患者。基于自动分割前列腺的掩模的放射组学模型在四个放射组学模型中获得了最高的 AUC（0.73 比 0.63 比 0.70 比 0.56）。Briganti 2017、MSKCC 列线图和 PI-RADS 评估的 AUC 分别为 0.69、0.71 和 0.70，与最优放射组学模型相比无显著差异（P=0.605-0.955）。
基于自动分割前列腺的掩模的放射组学模型为预测 PCa 患者的 PLNM 提供了一种非侵入性方法。其准确性与目前的 MKSCC 和 Briganti 列线图相当。
