Background

Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required.

Purpose

To evaluate a biparametric MRI AI algorithm for intraprostatic lesion detection and segmentation and to compare its performance with radiologist readings and biopsy results.

Materials and Methods

This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion–guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC).

Results

A total of 658 male participants (median age, 67 years [IQR, 61–71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0–3). The lesion segmentation DSC was 0.29.

Conclusion

The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination.

ClinicalTrials.gov Identifier: NCT03354416

© RSNA, 2024

Supplemental material is available for this article.

中文翻译：

---

基于级联深度学习的双参数 MRI 前列腺病变检测算法的评估

背景

与系统活检相比，多参数 MRI (mpMRI) 改善了前列腺癌 (PCa) 的检测，但其解释容易出现读者间差异，从而导致性能不一致。人工智能 (AI) 模型可以协助 mpMRI 解释，但需要大量训练数据集和广泛的模型测试。

目的

评估用于前列腺内病变检测和分割的双参数 MRI AI 算法，并将其性能与放射科医生读数和活检结果进行比较。

材料和方法

这项前瞻性登记的二次分析包括 2019 年 4 月至 2022 年 9 月期间连续接受 mpMRI、US 引导的系统活检或组合系统和 MRI/US 融合引导活检的疑似或已知 PCa 患者。所有病变均使用前列腺进行前瞻性评估成像报告和数据系统版本 2.1。使用灵敏度、阳性预测值 (PPV) 和 Dice 相似系数 (DSC) 将先前开发的级联深度学习算法的病变和参与者级别的性能与组织病理学结果和放射科医生读数进行比较。

结果

总共包括 658 名男性参与者（中位年龄 67 岁 [IQR，61-71 岁]），有 1029 个 MRI 可见病变。在组织病理学分析中，45%（658 名参与者中的 294 名）患有国际泌尿病理学会 (ISUP) 分级组 (GG) 2 级或更高级别的病变。该算法识别出 96%（294 人中的 282 人；95% CI：94%、98%）的所有参与者患有临床显着的 PCa，而放射科医生识别出 98%（294 人中的 287 人；95% CI：96%、99%；P = .23）。该算法识别出 84%（122 人中的 103 人）、96%（159 人中的 152 人）、96%（49 人中的 47 人）、95%（40 人中的 38 人）和 98%（46 人中的 45 人）具有 ISUP GG 1，分别为 2、3、4 和 5 个病变。在使用放射科医生真实数据进行的病变级别分析中，检测灵敏度为 55%（1029 中的 569；95% CI：52%、58%），PPV 为 57%（934 中的 535；95% CI：54%） ，61%）。每个参与者的假阳性病变平均数为 0.61（范围，0-3）。病灶分割DSC为0.29。

结论

AI 算法在双参数 MRI 扫描中检测到可疑癌症病变，其性能可与经验丰富的放射科医生相媲美。此外，该算法可靠地预测了组织病理学检查中的临床显着病变。

ClinicalTrials.gov 标识符：NCT03354416

© 北美放射学会，2024

本文提供了补充材料。