Korn Ronald Lee, Burkett Andre, Geschwind Jeff, Zygadlo Dominic, Brodie Taylor, Cridebring Derek, Von Hoff Daniel D, Demeure Michael J
Imaging Endpoints Research Laboratory, 7150 E Camelback Road Suite 120, Scottsdale, AZ 85251, USA.
Hoag Family Cancer Institute, 1 Hoag Drive, Newport Beach, CA 92663, USA.
Diagnostics (Basel). 2023 Mar 1;13(5):941. doi: 10.3390/diagnostics13050941.
Despite a growing number of effective therapeutic options for patients with pancreatic adenocarcinoma, the prognosis remains dismal mostly due to the late-stage presentation and spread of the cancer to other organs. Because a genomic analysis of pancreas tissue revealed that it may take years, if not decades, for pancreatic cancer to develop, we performed radiomics and fat fraction analysis on contrast-enhanced CT (CECT) scans of patients with historical scans showing no evidence of cancer but who subsequently went on to develop pancreas cancer years later, in an attempt to identify specific imaging features of the normal pancreas that may portend the subsequent development of the cancer. In this IRB-exempt, retrospective, single institution study, CECT chest, abdomen, and pelvis (CAP) scans of 22 patients who had evaluable historical imaging data were analyzed. The images from the "healthy" pancreas were obtained between 3.8 and 13.9 years before the diagnosis of pancreas cancer was established. Afterwards, the images were used to divide and draw seven regions of interest (ROIs) around the pancreas (uncinate, head, neck-genu, body (proximal, middle, and distal) and tail). Radiomic analysis on these pancreatic ROIs consisted of first order quantitative texture analysis features such as kurtosis, skewness, and fat quantification. Of all the variables tested, fat fraction in the pancreas tail ( = 0.029) and asymmetry of the histogram frequency curve (skewness) of pancreas tissue ( = 0.038) were identified as the most important imaging signatures for subsequent cancer development. Changes in the texture of the pancreas as measured on the CECT of patients who developed pancreas cancer years later could be identified, confirming the utility of radiomics-based imaging as a potential predictor of oncologic outcomes. Such findings may be potentially useful in the future to screen patients for pancreatic cancer, thereby helping detect pancreas cancer at an early stage and improving survival.
尽管针对胰腺腺癌患者有越来越多有效的治疗选择，但由于癌症晚期表现以及扩散至其他器官，其预后仍然很差。因为对胰腺组织的基因组分析显示，胰腺癌的发展可能需要数年甚至数十年时间，所以我们对有历史扫描记录且当时无癌症迹象但数年后患上胰腺癌的患者进行了增强CT（CECT）扫描的影像组学和脂肪分数分析，试图确定正常胰腺可能预示后续癌症发展的特定影像特征。在这项豁免机构审查委员会批准的回顾性单机构研究中，分析了22例有可评估历史影像数据患者的胸部、腹部和骨盆CECT扫描。“健康”胰腺的图像是在胰腺癌确诊前3.8至13.9年期间获取的。之后，利用这些图像在胰腺周围划分并绘制了七个感兴趣区域（ROI）（钩突、头部、颈体部、体部（近端、中部和远端）以及尾部）。对这些胰腺ROI的影像组学分析包括一阶定量纹理分析特征，如峰度、偏度和脂肪定量。在所有测试变量中，胰腺尾部的脂肪分数（=0.029）和胰腺组织直方图频率曲线的不对称性（偏度）（=0.038）被确定为后续癌症发展的最重要影像特征。数年后患上胰腺癌的患者在CECT上测量的胰腺纹理变化能够被识别出来，证实了基于影像组学的成像作为肿瘤学结果潜在预测指标的实用性。这些发现未来可能对胰腺癌筛查患者有潜在帮助，从而有助于早期发现胰腺癌并提高生存率。
