Vittori Gianni, Bacchiani Mara, Grosso Antonio Andrea, Raspollini Maria Rosaria, Giovannozzi Neri, Righi Lorenzo, Di Maida Fabrizio, Agostini Simone, De Nisco Fausto, Mari Andrea, Minervini Andrea
Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.
Unit of Oncologic Minimally-Invasive Urology and Andrology, Careggi Hospital, Florence, Italy.
World J Urol. 2023 Feb;41(2):435-441. doi: 10.1007/s00345-022-04275-x. Epub 2023 Jan 3.
Computer-aided diagnosis (CAD) may improve prostate cancer (PCa) detection and support multiparametric magnetic resonance imaging (mpMRI) readers for better characterization. We evaluated Watson Elementary (WE) CAD system results referring to definitive pathological examination in patients treated with robot-assisted radical prostatectomy (RARP) in a tertiary referral center.
Patients treated with RARP between 2020 and 2021 were selected. WE calculates the Malignancy Attention Index (MAI), starting from the information contained in the mpMRI images. Outcome measures were the capability to predict the presence of PCa, to correctly locate the dominant lesion, to delimit the largest diameter of the dominant lesion, and to predict the extraprostatic extension (EPE).
Overall, tumor presence was confirmed in 46 (92%) WE highly suspicious areas, while it was confirmed in 43 (86%) mpMRI PI-RADS ≥ 4 lesions. The WE showed a positive agreement with mpMRI of 92%. In 98% of cases, visible tumor at WE showed that the highly suspicious areas were within the same prostate sector of the dominant tumor nodule at pathology. WE showed a 2.5 mm median difference of diameter with pathology, compared with a 3.8 mm of mpMRI versus pathology (p = 0.019). In prediction of EPE, WE and mpMRI showed sensitivity, specificity, positive and negative predictive value of 0.81 vs 0.71, 0.56 vs 0.60, 0.88 vs 0.85 and 0.42 vs 0.40, respectively.
The WE system resulted accurate in the PCa dominant lesion detection, localization and delimitation providing additional information concerning EPE prediction.
计算机辅助诊断（CAD）可改善前列腺癌（PCa）的检测，并为多参数磁共振成像（mpMRI）阅片者提供支持，以更好地表征病变。我们在一家三级转诊中心评估了沃森初级（WE）CAD系统在接受机器人辅助根治性前列腺切除术（RARP）的患者中的结果，并将其与最终病理检查结果进行对比。
选取2020年至2021年间接受RARP治疗的患者。WE根据mpMRI图像中包含的信息计算恶性关注指数（MAI）。观察指标包括预测PCa存在的能力、正确定位主要病变的能力、界定主要病变最大直径的能力以及预测前列腺外侵犯（EPE）的能力。
总体而言，在46个（92%）WE高度可疑区域中证实存在肿瘤，而在43个（86%）mpMRI PI-RADS≥4的病变中也得到证实。WE与mpMRI的阳性一致性为92%。在98%的病例中，WE显示的可见肿瘤表明高度可疑区域位于病理检查中主要肿瘤结节的同一前列腺区域内。与mpMRI和病理之间3.8毫米的差异相比，WE与病理之间的直径中位数差异为2.5毫米（p = 0.019）。在EPE预测方面，WE和mpMRI的敏感性、特异性、阳性预测值和阴性预测值分别为0.81对0.71、0.56对0.60、0.88对0.85和0.42对0.40。
WE系统在PCa主要病变的检测、定位和界定方面结果准确，并提供了有关EPE预测的额外信息。
