Department of Radiology, Peking University First Hospital, Beijing, China.
Beijing Smart Tree Medical Technology Co. Ltd. Beijing, China.
J Magn Reson Imaging. 2021 Dec;54(6):1892-1901. doi: 10.1002/jmri.27565. Epub 2021 Mar 8.
It is feasible to use magnetic resonance (MR)-based radiomics to distinguish high-grade from low-grade prostate cancer (PCa), but radiomics model performance based on fully automated segmentation remains unknown.
To develop and test radiomics models based on manually or automatically gained masks on apparent diffusion coefficient (ADC) maps to predict high-grade (Gleason score ≥ 4 + 3) PCa at radical prostatectomy (RP).
Retrospective.
A total of 176 patients (94 high-grade PCa and 82 low-grade PCa) with complete RP, preoperative biopsy, and multiparametric magnetic resonance imaging (mpMRI) were retrospectively recruited and randomly divided into training (N = 123) and test (N = 53) cohorts.
FIELD STRENGTH/SEQUENCE: Using a 3.0-T MR scanner, ADC maps were calculated from diffusion-weighted imaging (b values = 0, 1400 s/mm , echo planar imaging).
Two radiologists segmented the whole prostate gland and the most index prostate lesion. Automatic segmentation of the prostate and the lesion were performed. Four radiomics models were constructed using four masks (manual/automatic prostate gland/PCa lesion segmentation). According to the standard reference of the RP histopathologic assessment, the performance of each radiomics models was compared with that of biopsy and Prostate Imaging Reporting and Data System version 2.1 (PI-RADS) assessment.
A receiver operating characteristic curve analysis was employed to estimate the area under the curve (AUC) values of the models. The AUCs of the four models, biopsy, and PI-RADS assessment were compared using the DeLong test.
The four radiomics models yielded AUCs of 0.710, 0.731, 0.726, and 0.709 in the test cohort, respectively; biopsy and PI-RADS assessment yielded AUCs of 0.793 and 0.680, respectively. No significant differences were found among model, biopsy, and PI-RADS assessment comparisons (P = 0.132-0.988).
To distinguish high-grade from low-grade PCa, radiomics models based on automatic segmentation on ADC maps exhibit approximately the same diagnostic efficacy as manual segmentation and biopsy, highlighting the possibility of a fully automatic workflow combining automated segmentation with radiomics analysis.
4 TECHNICAL EFFICACY: Stage 2.
使用基于磁共振（MR）的放射组学区分高级别和低级别前列腺癌（PCa）是可行的，但基于全自动分割的放射组学模型性能仍不清楚。
开发和测试基于表观扩散系数（ADC）图手动或自动获得的掩模的放射组学模型，以预测根治性前列腺切除术（RP）中的高级别（Gleason 评分≥4+3）PCa。
回顾性。
共纳入 176 例接受 RP、术前活检和多参数磁共振成像（mpMRI）的完整 PCa 患者（94 例高级别 PCa 和 82 例低级别 PCa），并进行回顾性分析。将患者随机分为训练队列（N=123）和测试队列（N=53）。
磁场强度/序列：使用 3.0-T MR 扫描仪，从扩散加权成像（b 值=0、1400 s/mm 2 、回波平面成像）计算 ADC 图。
两名放射科医生对整个前列腺和最索引前列腺病变进行手动分割。对前列腺和病变进行自动分割。使用四个掩模（手动/自动前列腺/PCa 病变分割）构建了四个放射组学模型。根据 RP 组织病理学评估的标准参考，比较了每个放射组学模型的性能与活检和前列腺成像报告和数据系统 2.1 版（PI-RADS）评估的性能。
采用受试者工作特征曲线分析估计模型的曲线下面积（AUC）值。使用 DeLong 检验比较了四个模型、活检和 PI-RADS 评估的 AUC 值。
在测试队列中，四个放射组学模型的 AUC 值分别为 0.710、0.731、0.726 和 0.709；活检和 PI-RADS 评估的 AUC 值分别为 0.793 和 0.680。模型、活检和 PI-RADS 评估之间的比较无显著差异（P=0.132-0.988）。
为了区分高级别和低级别 PCa，基于 ADC 图自动分割的放射组学模型具有与手动分割和活检相似的诊断效能，突出了全自动工作流程结合自动分割和放射组学分析的可能性。
4 级 技术功效：2 级。
