Magnetic resonance imaging has evolved as a key component for prostate cancer (PCa) detection, substantially increasing the radiologist workload. Artificial intelligence (AI) systems can support radiological assessment by segmenting and classifying lesions in clinically significant (csPCa) and non-clinically significant (ncsPCa). Commonly, AI systems for PCa detection involve an automatic prostate segmentation followed by the lesion detection using the extracted prostate. However, evaluation reports are typically presented in terms of detection under the assumption of the availability of a highly accurate segmentation and an idealistic scenario, omitting the propagation of errors between modules. For that purpose, we evaluate the effect of two different segmentation networks (s1 and s2) with heterogeneous performances in the detection stage and compare it with an idealistic setting (s1:89.90+-2.23 vs 88.97+-3.06 ncsPCa, P<.001, 89.30+-4.07 and 88.12+-2.71 csPCa, P<.001). Our results depict the relevance of a holistic evaluation, accounting for all the sub-modules involved in the system.

翻译：磁共振成像已成为前列腺癌（PCa）检测的关键组成部分，显著增加了放射科医生的工作负担。人工智能（AI）系统可通过分割病灶并将其分类为临床显著性（csPCa）和非临床显著性（ncsPCa）来支持放射学评估。通常，用于PCa检测的AI系统涉及自动前列腺分割，随后利用提取的前列腺进行病灶检测。然而，评估报告通常仅基于理想化场景假设高精度分割的可用性，忽视了模块间的误差传播。为此，我们评估了两种性能异质的分割网络（s1和s2）对检测阶段的影响，并与理想化设置进行比较（s1:89.90±2.23 vs 88.97±3.06 ncsPCa, P<0.001; 89.30±4.07 vs 88.12±2.71 csPCa, P<0.001）。研究结果揭示了系统综合评估的重要性，需考虑系统中所有子模块的相互作用。