Zhejiang Chinese Medical University, The Affiliated Hospital of Jiaxing University, Jiaxing, China.
School of Basic Medical Sciences, Capital Medical University, Beijing, China.
Prostate. 2023 Nov;83(15):1494-1503. doi: 10.1002/pros.24608. Epub 2023 Aug 7.
To study the feasibility of using an artificial intelligence (AI) algorithm for the diagnosis of clinically significant prostate cancer (csPCa) on multiparametric MRI (mpMRI) in combination with conventional clinical information.
A retrospective study cohort with 505 patients was collected, with complete information on age (≤60, 60-80, and >80 years), PSA (≤4, 4-10, and >10 ng/dL), and pathology results. The patients with ISUP group >2 were classified as csPCa, and the patients with ISUP = 1 or no evidence of prostate cancer were classified as non-csPCa. The diagnosis of mpMRI was made by experienced radiologists following the prostate imaging reporting and data system (PIRADS ≤ 2, PIRADS = 3, and PIRADS > 3). The mpMRI images were processed by a homemade AI algorithm, and the AI results were obtained as positive or negative for csPCa. Two logistic regression models were fitted, with pathological findings as the dependent variable, that is, a conventional model and an AI model. The conventional model used age, PSA, and PIRADS as the independent variables. The AI model took the AI result and the abovementioned clinical information as the independent variables. The predicted probability of the patients from the conventional model and the AI model were used to test the prediction efficacy of the models. The DeLong test was performed to compare differences in the area under the receiver operating characteristic (ROC) area under the curve (AUC) between the conventional model and the AI model.
In total, 505 patients were included in the study; 280 were diagnosed with csPCa, and 225 were non-csPCa. The median age was 72.0 (67.0, 76.0) years, with a median PSA value of 13.0 (7.46, 27.5) ng/dL. Statically significant differences were found in age, PSA, PIRADS score and AI results between the csPCa and non-csPCa groups (all p < 0.001). In the multivariable regression models, all the variables were independently associated with csPCa. The conventional model (R = 0.361) and the AI model (R = 0.474) were compared with analysis of variance (ANOVA) and showed statistically significant differences (χ = 63.695, p < 0.001). The AUC of the ROC curve for the conventional model was 0.782 (95% confidence interval [CI]: 0.742-0.823), which was less than the AUC of the AI model with statistical significance (0.849 [95% CI: 0.815-0.883], p < 0.001).
In combination with routine clinical information, such as age, PSA, and PIRADS category, adding information from the AI algorithm based on mpMRI could improve the diagnosis of csPCa.
研究在多参数 MRI（mpMRI）上结合常规临床信息使用人工智能（AI）算法诊断临床显著前列腺癌（csPCa）的可行性。
本研究为回顾性队列研究，共纳入 505 例患者，患者信息完整，包括年龄（≤60、60-80 和＞80 岁）、PSA（≤4、4-10 和＞10ng/dL）和病理结果。ISUP 分组＞2 的患者被归类为 csPCa，ISUP=1 或无前列腺癌证据的患者被归类为非 csPCa。mpMRI 诊断由经验丰富的放射科医生按照前列腺影像报告和数据系统（PIRADS≤2、PIRADS=3 和 PIRADS＞3）进行。mpMRI 图像由自主研发的 AI 算法处理，AI 结果为 csPCa 阳性或阴性。建立了两个逻辑回归模型，以病理结果为因变量，即传统模型和 AI 模型。传统模型使用年龄、PSA 和 PIRADS 作为自变量。AI 模型将 AI 结果和上述临床信息作为自变量。使用传统模型和 AI 模型的患者预测概率来检验模型的预测效果。采用 DeLong 检验比较传统模型和 AI 模型受试者工作特征（ROC）曲线下面积（AUC）的差异。
共纳入 505 例患者，其中 280 例诊断为 csPCa，225 例为非 csPCa。中位年龄为 72.0（67.0、76.0）岁，中位 PSA 值为 13.0（7.46、27.5）ng/dL。csPCa 组和非 csPCa 组在年龄、PSA、PIRADS 评分和 AI 结果方面差异有统计学意义（均 p＜0.001）。多变量回归模型中，所有变量均与 csPCa 独立相关。传统模型（R2=0.361）和 AI 模型（R2=0.474）与方差分析（ANOVA）进行比较，差异有统计学意义（χ2=63.695，p＜0.001）。传统模型的 ROC 曲线 AUC 为 0.782（95%置信区间 [CI]：0.742-0.823），低于 AI 模型的 AUC（0.849[95%CI：0.815-0.883]，p＜0.001）。
结合年龄、PSA 和 PIRADS 等常规临床信息，增加基于 mpMRI 的 AI 算法信息，可提高 csPCa 的诊断效能。
