The PI-CAI Challenge: Public Training and Development Dataset

This dataset represents the <strong>PI-CAI: Public Training and Development Dataset</strong>. It contains 1500 anonymized prostate biparametric MRI scans from 1476 patients, acquired between 2012-2021, at three centers (Radboud University Medical Center, University Medical Center Groningen, Ziekenhuis Groep Twente) based in The Netherlands. The PI-CAI challenge is an all-new grand challenge that aims to validate the diagnostic performance of artificial intelligence and radiologists at clinically significant prostate cancer (csPCa) detection/diagnosis in MRI, with histopathology and follow-up (≥ 3 years) as the reference standard, in a retrospective setting. The study hypothesizes that state-of-the-art AI algorithms, trained using thousands of patient exams, are non-inferior to radiologists reading bpMRI. Key aspects of the PI-CAI study design have been established in conjunction with an international scientific advisory board of 16 experts in prostate AI, radiology and urology —to unify and standardize present-day guidelines, and to ensure meaningful validation of prostate AI towards clinical translation (<strong>Reinke et al., 2021</strong>).本数据集为**PI-CAI：公开训练与开发数据集**。其包含来自1476名患者的1500份经匿名化处理的前列腺双参数磁共振成像（biparametric MRI，后文简称bpMRI）扫描数据，采集时间跨度为2012年至2021年，采集机构为荷兰境内的三家医学中心：拉德堡德大学医学中心、格罗宁根大学医学中心以及特温特医院集团（Ziekenhuis Groep Twente）。PI-CAI挑战赛是一项全新的大型挑战赛，旨在以组织病理学检查与≥3年的随访结果作为参考金标准，在回顾性研究场景下，验证人工智能与放射科医师在磁共振成像中检出临床显著性前列腺癌（clinically significant prostate cancer，后文简称csPCa）的诊断性能。本研究提出假设：依托数千份患者检查数据训练的当前最优人工智能算法，在读取bpMRI影像时的诊断表现不劣于放射科医师。PI-CAI研究的核心设计方案由16位前列腺人工智能、放射学与泌尿学领域专家组成的国际科学顾问委员会联合制定，旨在统一并规范现行相关指南，确保前列腺人工智能技术向临床转化过程中的有效验证（Reinke等人，2021）。