人工智能生成的ADC图对前列腺癌计算机辅助诊断的影响：一项可行性研究。

Impact of AI-Generated ADC Maps on Computer-Aided Diagnosis of Prostate Cancer: A Feasibility Study.

作者信息

Ozyoruk Kutsev B, Harmon Stephanie A, Yilmaz Enis C, Gelikman David G, Bagci Ulas, Simon Benjamin D, Merino Maria J, Lis Rosina, Gurram Sandeep, Wood Bradford J, Pinto Peter A, Choyke Peter L, Turkbey Baris

机构信息

Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, Bethesda, Maryland (K.B.O., S.A.H., D.G.G., B.D.S., R.L., P.L.C., B.T.); Molecular Imaging Branch, National Cancer Institute, Bethesda, Maryland (K.B.O., S.A.H., D.G.G., B.D.S., R.L., P.L.C., B.T.).

Transitional Program, Sinai-Grace Hospital, Detroit Medical Center, Detroit, Michigan (E.C.Y.).

出版信息

Acad Radiol. 2025 Aug;32(8):4621-4630. doi: 10.1016/j.acra.2025.05.041. Epub 2025 Jun 4.

DOI:10.1016/j.acra.2025.05.041

PMID:40473563

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12279456/

Abstract

RATIONALE AND OBJECTIVES

To evaluate the impact of AI-generated apparent diffusion coefficient (ADC) maps on diagnostic performance of a 3D U-Net AI model for prostate cancer (PCa) detection and segmentation at biparametric MRI (bpMRI).

MATERIAL AND METHODS

The study population was retrospectively collected and consisted of 178 patients, including 119 cases and 59 controls. Cases had a mean age of 62.1 years (SD=7.4) and a median prostate-specific antigen (PSA) level of 7.27ng/mL (IQR=5.43-10.55), while controls had a mean age of 63.4 years (SD=7.5) and a median PSA of 6.66ng/mL (IQR=4.29-11.30). All participants underwent 3.0 T T2-weighted turbo spin-echo MRI and high b-value echo-planar diffusion-weighted imaging (bpMRI), followed by either prostate biopsy or radical prostatectomy between January 2013 and December 2022. We compared the lesion detection and segmentation performance of a pretrained 3D U-Net AI model using conventional ADC maps versus AI-generated ADC maps. The Wilcoxon signed-rank test was used for statistical comparison, with 95% confidence intervals (CI) estimated via bootstrapping. A p-value <0.05 was considered significant.

RESULTS

AI-ADC maps increased the accuracy of the lesion detection AI model, from 0.70 to 0.78 (p<0.01). Specificity increased from 0.22 to 0.47 (p<0.001), while maintaining high sensitivity, which was 0.94 with conventional ADC maps and 0.93 with AI-ADC maps (p>0.05). Mean dice similarity coefficients (DSC) for conventional ADC maps was 0.276, while AI-ADC maps showed a mean DSC of 0.225 (p<0.05). In the subset of patients with ISUP≥2, standard ADC maps demonstrated a mean DSC of 0.282 compared to 0.230 for AI-ADC maps (p<0.05).

CONCLUSION

AI-generated ADC maps can improve performance of computer-aided diagnosis of prostate cancer.

摘要

原理与目的

评估人工智能生成的表观扩散系数（ADC）图对基于双参数磁共振成像（bpMRI）的三维U-Net人工智能模型检测和分割前列腺癌（PCa）的诊断性能的影响。

材料与方法

回顾性收集研究人群，包括178例患者，其中119例为病例组，59例为对照组。病例组患者平均年龄62.1岁（标准差=7.4），前列腺特异性抗原（PSA）水平中位数为7.27ng/mL（四分位间距=5.43-10.55）；对照组患者平均年龄63.4岁（标准差=7.5），PSA中位数为6.66ng/mL（四分位间距=4.29-11.30）。所有参与者均接受了3.0T T2加权快速自旋回波磁共振成像和高b值回波平面扩散加权成像（bpMRI），随后在2013年1月至2022年12月期间接受了前列腺活检或根治性前列腺切除术。我们比较了使用传统ADC图与人工智能生成的ADC图的预训练三维U-Net人工智能模型的病变检测和分割性能。采用Wilcoxon符号秩检验进行统计学比较，通过自抽样估计95%置信区间（CI）。p值<0.05被认为具有统计学意义。

结果

人工智能生成的ADC图将病变检测人工智能模型的准确率从0.70提高到了0.78（p<0.01）。特异性从0.22提高到0.47（p<0.001），同时保持了较高的敏感性，传统ADC图的敏感性为0.94，人工智能生成的ADC图的敏感性为0.93（p>0.05）。传统ADC图的平均骰子相似系数（DSC）为0.276，而人工智能生成的ADC图的平均DSC为0.225（p<0.05）。在国际泌尿病理学会（ISUP）≥2的患者亚组中，标准ADC图的平均DSC为0.282，而人工智能生成的ADC图为0.230（p<0.05）。