College of Medicine and Biological Information Engineering School, Northeastern University, Shenyang, 110016, China; CAS Key Laboratory of Molecular Imaging, The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
Imaging Center, Wuxi People's Hospital, Nanjing Medical University, Wuxi, 214023, China.
Comput Biol Med. 2022 May;144:105318. doi: 10.1016/j.compbiomed.2022.105318. Epub 2022 Feb 11.
Gleason score (GS) is one of the most critical predictors of diagnosing prostate cancer (PCa). The prostate gland, including both lesions and their microenvironment, may contain more comprehensive information about the PCa. We aimed to investigate the potential of prostate gland radiomic features in identifying Gleason scores (GS) < 7, = 7, and >7.
We retrospectively examined preoperative magnetic resonance imaging (MRI) results, clinical data, and postoperative pathological findings from 489 PCa patients. The three-dimensional (3D) and two-dimensional (2D) radiomic features were extracted from the manually segmented 3D prostate gland and its maximum 2D layer on MRI, respectively. Significant features were selected, and sequence signatures were then developed via multi-class linear regression (MLR) accordingly. Subsequently, 2D and 3D radiomic models were constructed by applying MLR to the combination of the sequence signatures, respectively. The stability of the significant features was discussed by their average ranking in the other 30 random cohorts. Based on our distance matrix algorithm, we generated different regions of interest to simulate the manual segmentation biases and discuss the model's tolerance to them.
Our 2D model reached a C-index of 0.728 and an average area under the receiver operating characteristic curve of 0.794 in the validation cohort. The corresponding key features were stable, with an average ranking of the top 8.352% in 30 random cohorts, and the model could tolerate a segmentation boundary deviation of 2 mm without significant performance degradation.
2D prostate-gland-MRI-based radiomic features showed stable potential in identifying GS.
格里森评分（GS）是诊断前列腺癌（PCa）的最重要预测指标之一。前列腺包括病变及其微环境，可能包含有关 PCa 的更全面信息。我们旨在研究前列腺放射组学特征在识别 GS<7、=7 和>7 方面的潜力。
我们回顾性地检查了 489 例 PCa 患者的术前磁共振成像（MRI）结果、临床数据和术后病理发现。分别从手动分割的 3D 前列腺和其最大 2D 层上提取 3D 和 2D 放射组学特征。选择显著特征，并通过多类线性回归（MLR）相应地开发序列签名。然后，通过将序列签名应用于 MLR，分别构建 2D 和 3D 放射组学模型。通过其在其他 30 个随机队列中的平均排名来讨论显著特征的稳定性。基于我们的距离矩阵算法，我们生成了不同的感兴趣区域，以模拟手动分割偏差，并讨论模型对它们的容忍度。
我们的 2D 模型在验证队列中达到了 0.728 的 C 指数和 0.794 的平均接收者操作特征曲线下面积。相应的关键特征稳定，在 30 个随机队列中的平均排名为前 8.352%，并且模型可以容忍 2mm 的分割边界偏差，而不会出现性能明显下降。
基于 2D 前列腺-MRI 的放射组学特征在识别 GS 方面具有稳定的潜力。
