Harmon Stephanie A, Tetreault Jesse, Esengur Omer Tarik, Qin Ming, Yilmaz Enis C, Chang Victor, Yang Dong, Xu Ziyue, Cohen Gregg, Plum Jeff, Sherif Testi, Levin Ron, Schmidt-Richberg Alexander, Thompson Scott, Coons Samuel, Chen Te, Choyke Peter L, Xu Daguang, Gurram Sandeep, Wood Bradford J, Pinto Peter A, Turkbey Baris
National Institutes of Health, Bethesda, USA.
Nvidia (United States), Santa Clara, USA.
Abdom Radiol (NY). 2025 May 26. doi: 10.1007/s00261-025-05014-7.
A critical limitation to deployment and utilization of Artificial Intelligence (AI) algorithms in radiology practice is the actual integration of algorithms directly into the clinical Picture Archiving and Communications Systems (PACS). Here, we sought to integrate an AI-based pipeline for prostate organ and intraprostatic lesion segmentation within a clinical PACS environment to enable point-of-care utilization under a prospective clinical trial scenario.
A previously trained, publicly available AI model for segmentation of intra-prostatic findings on multiparametric Magnetic Resonance Imaging (mpMRI) was converted into a containerized environment compatible with MONAI Deploy Express. An inference server and dedicated clinical PACS workflow were established within our institution for evaluation of real-time use of the AI algorithm. PACS-based deployment was prospectively evaluated in two phases: first, a consecutive cohort of patients undergoing diagnostic imaging at our institution and second, a consecutive cohort of patients undergoing biopsy based on mpMRI findings. The AI pipeline was executed from within the PACS environment by the radiologist. AI findings were imported into clinical biopsy planning software for target definition. Metrics analyzing deployment success, timing, and detection performance were recorded and summarized.
In phase one, clinical PACS deployment was successfully executed in 57/58 cases and were obtained within one minute of activation (median 33 s [range 21-50 s]). Comparison with expert radiologist annotation demonstrated stable model performance compared to independent validation studies. In phase 2, 40/40 cases were successfully executed via PACS deployment and results were imported for biopsy targeting. Cancer detection rates for prostate cancer were 82.1% for ROI targets detected by both AI and radiologist, 47.8% in targets proposed by AI and accepted by radiologist, and 33.3% in targets identified by the radiologist alone.
Integration of novel AI algorithms requiring multi-parametric input into clinical PACS environment is feasible and model outputs can be used for downstream clinical tasks.
人工智能（AI）算法在放射学实践中的部署和应用存在一个关键限制，即如何将算法直接集成到临床图像存档与通信系统（PACS）中。在此，我们试图在临床PACS环境中集成一个基于AI的前列腺器官和前列腺内病变分割流程，以便在前瞻性临床试验场景下实现床边即时应用。
一个先前训练好的、公开可用的用于在多参数磁共振成像（mpMRI）上分割前列腺内病变的AI模型被转换到与MONAI Deploy Express兼容的容器化环境中。在我们机构内建立了一个推理服务器和专门的临床PACS工作流程，用于评估AI算法的实时使用情况。基于PACS的部署在前瞻性的两个阶段进行评估：第一阶段，对在我们机构接受诊断性成像的连续队列患者进行评估；第二阶段，对基于mpMRI结果接受活检的连续队列患者进行评估。AI流程由放射科医生在PACS环境中执行。AI结果被导入临床活检计划软件以进行靶点定义。记录并总结了分析部署成功率、时间安排和检测性能的指标。
在第一阶段，57/58例病例成功完成了临床PACS部署，且在激活后一分钟内获得结果（中位数33秒[范围21 - 50秒]）。与专家放射科医生的标注结果相比，该模型性能与独立验证研究结果相比表现稳定。在第二阶段，40/40例病例通过PACS部署成功执行，并将结果导入用于活检靶点定位。对于前列腺癌，AI和放射科医生均检测到的ROI靶点的癌症检出率为82.1%，AI提出并被放射科医生接受的靶点的癌症检出率为47.8%，仅由放射科医生识别的靶点的癌症检出率为33.3%。
将需要多参数输入的新型AI算法集成到临床PACS环境中是可行的，并且模型输出可用于下游临床任务。
