Suri Abhinav, Mukherjee Pritam, Rabbee Nusrat, Pickhardt Perry J, Summers Ronald M
David Geffen School of Medicine at UCLA, Los Angeles, California (A.S.); Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D MSC 1182, Bethesda, MD 20892-1182 (A.S., P.M., R.M.S.).
Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D MSC 1182, Bethesda, MD 20892-1182 (A.S., P.M., R.M.S.).
Acad Radiol. 2025 Jul;32(7):4013-4021. doi: 10.1016/j.acra.2025.02.047. Epub 2025 Mar 22.
Pancreatic imaging biomarkers on CT imaging are known to be associated with diabetes. However, no studies have examined if these imaging biomarkers are resilient to changes in segmentation quality and contrast status. Here, we assess if imaging biomarkers are robust to variations in pancreatic segmentation quality and contrast status, and how these factors affect their ability to predict diabetes.
This retrospective study selected patients with CT scans and corresponding HbA1c tests from two institutions. Patients were classified into two categories: having diabetes at the time or < 4 years after the scan (diabetic/incident) vs not having diabetes within 4 years after the scan (nondiabetic). Pancreatic imaging biomarkers, including average attenuation, intrapancreatic fat fraction, fractal dimension of the pancreatic boundary and volume, were measured using three pancreatic segmentation algorithms (TotalSegmentator, nnU-Net, and DM-UNet). Pairwise comparisons were made between algorithms when computing pancreatic imaging biomarker values for all patient scans. Predictive ability of imaging biomarkers (derived from each algorithm) was assessed for agreement between algorithms using a generalized additive model.
A total of 9772 patients (age, 56.1 years ± 9.1 [SD]; 5407 females) were included in this study. Imaging biomarkers based on attenuation measurements showed high algorithm agreement (ICC ≥0.93), with lower agreement on measures not reliant on attenuation. Models trained on imaging biomarkers derived from these algorithms exhibited good predictive agreement (AUC for diabetes overall, 0.84-0.91; contrast scans, 0.73-0.80; noncontrast scans, 0.62-0.80). Algorithms achieved a positive predictive value of 0.79-0.84, and negative predictive value of 0.89-0.94.
Attenuation-based imaging biomarkers demonstrated robustness to segmentation algorithm quality and consistent predictive ability across different clinical scenarios. These findings suggest that CT-derived biomarkers could be a reliable tool for diabetes screening across multiple institutions.
已知CT成像上的胰腺成像生物标志物与糖尿病有关。然而，尚无研究探讨这些成像生物标志物是否对分割质量和对比度状态的变化具有弹性。在此，我们评估成像生物标志物对胰腺分割质量和对比度状态变化的稳健性，以及这些因素如何影响其预测糖尿病的能力。
这项回顾性研究从两个机构中选取了进行CT扫描并进行了相应糖化血红蛋白（HbA1c）检测的患者。患者分为两类：扫描时或扫描后<4年患有糖尿病（糖尿病/新发）与扫描后4年内未患糖尿病（非糖尿病）。使用三种胰腺分割算法（TotalSegmentator、nnU-Net和DM-UNet）测量胰腺成像生物标志物，包括平均衰减、胰腺内脂肪分数、胰腺边界的分形维数和体积。在为所有患者扫描计算胰腺成像生物标志物值时，对算法之间进行成对比较。使用广义相加模型评估成像生物标志物（源自每种算法）的预测能力，以评估算法之间的一致性。
本研究共纳入9772例患者（年龄，56.1岁±9.1[标准差]；5407例女性）。基于衰减测量的成像生物标志物显示出较高的算法一致性（组内相关系数[ICC]≥0.93），而对不依赖于衰减的测量一致性较低。基于这些算法得出的成像生物标志物训练的模型表现出良好的预测一致性（总体糖尿病的曲线下面积[AUC]为0.84 - 0.91；增强扫描为0.73 - 0.80；平扫为0.62 - 0.80）。算法的阳性预测值为0.79 - 0.84，阴性预测值为0.89 - 0.94。
基于衰减的成像生物标志物对分割算法质量具有稳健性，并且在不同临床场景中具有一致的预测能力。这些发现表明，CT衍生的生物标志物可能是跨多个机构进行糖尿病筛查的可靠工具。
