CT影像组学对肾上腺乏脂腺瘤与结节样增生的诊断价值

doi:10.6040/j.issn.1671-7554.0.2021.1619

摘要/Abstract

摘要： 目的探讨基于CT平扫图像建立的影像组学诺模图对鉴别肾上腺乏脂腺瘤和肾上腺结节样增生的诊断价值。方法回顾性分析经病理学检查证实的44例肾上腺乏脂腺瘤与55例肾上腺结节样增生患者。从CT平扫图像提取并筛选出有诊断价值的影像组学参数,计算影像组学评分构建影像组学模型,分析筛选临床因素构建临床模型并联合临床因素和影像组学模型构建诺模图。分析比较上述3种模型的诊断效能。结果 13项影像组学参数被筛选用于建立影像组学诊断模型。影像组学模型验证集曲线下面积为0.91,敏感度和特异度分别为84.6%和81.3%。单因素及多因素二分类Logistic回归分析结果显示,肾素和最大径为鉴别二者的独立影响因子,临床模型验证集曲线下面积为0.57, 敏感度和特异度分别为53.9%和68.8%。诺模图验证集AUC为0.94,敏感度和特异度分别为84.6%和93.8%。影像组学模型及诺模图的诊断效能均大于临床模型(z=3.188,P<0.001;z=3.409,P<0.001)。结论基于CT平扫图像的影像组学诺模图对鉴别肾上腺乏脂腺瘤和肾上腺结节样增生有较高的诊断效能,具有较高的临床价值。

关键词: 肾上腺乏脂腺瘤, 肾上腺增生, 体层摄影技术, 影像组学, 诺模图

Abstract: Objective To investigate the value of radiomics nomogram based on non-contrast CT in the differential diagnosis of adrenal lipid-poor adenoma and adrenal nodular hyperplasia. Methods Clinical data of 44 patients with adrenal lipid-poor adenoma and 55 with nodular hyperplasia confirmed by pathology were retrospectively analyzed. Radiomics features extracted from non-contrast CT and radiomics score(Radscore)were calculated to construct a radiomics model. Clinical factors were selected to construct a clinical model. Radiomics nomogram was constructed combining clinical factors and Radscore. The diagnostic values of the three models were compared. Results A total of 13 features were selected to establish the radiomics model. The area under the receiver operator characteristic curve(AUC), sensitivity and specificity of the radiomics model were 0.91, 84.6% and 81.3%, respectively. Both univariate and multivariate Logistic regression showed that renin and maximum diameter were the independent influencing factors in the differential diagnosis of adrenal lipid-poor adenoma and adrenal nodular hyperplasia. The AUC, sensitivity and specificity of the clinical model were 0.57, 53.9% and 68.8%. respectively. The AUC, sensitivity and specificity of the radiomics nomogram were 0.94, 84.6% and 93.8%, respectively. The diagnostic efficiency of the radiomics model and nomogram was significantly higher than that of the clinical model(z=3.188, P<0.001; z=3.409, P<0.001). Conclusion The radiomics nomogram based on non-contrast CT has a high efficiency in the differential diagnosis of adrenal lipid-poor adenoma and nodular hyperplasia.

Key words: Adrenal lipid-poor adenoma, Adrenal nodular hyperplasia, CT, Radiomics, Nomogram

中图分类号:

R574

袁宏涛,纪淙山,康冰,秦松楠,于鑫鑫,高琳,王锡明. CT影像组学对肾上腺乏脂腺瘤与结节样增生的诊断价值[J]. 山东大学学报 (医学版), 2022, 60(4): 68-75.

YUAN Hongtao, JI Congshan, KANG Bing, QIN Songnan, YU Xinxin, GAO Lin, WANG Ximing. Diagnostic value of CT radiomics nomogram for adrenal lipid-poor adenoma and nodular hyperplasia[J]. Journal of Shandong University (Health Sciences), 2022, 60(4): 68-75.

参考文献

[1] Song JH, Chaudhry FS, Mayo-Smith WW. The incidental adrenal mass on CT: prevalence of adrenal disease in 1,049 consecutive adrenal masses in patients with no known malignancy [J]. AJR Am J Roentgenol, 2008, 190(5): 1163-8.
[2] 项林爱, 胡红杰, 王健, 等. 无脂性肾上腺腺瘤和无囊变嗜铬细胞瘤的CT鉴别诊断[J]. 临床放射学杂志, 2019, 38(3): 484-488. XIANG Linai, HU Hongjie, WANG Jian, et al. Differentiation the lipid-none adrenal adenoma from non-necrosis pheochromocytoma with CT [J]. Journal of Practical Radiology, 2019, 38(3): 484-488.
[3] 刘刚, 王坤利, 田野, 等. 原发性醛固酮增多症手术治疗的研究进展[J]. 中华泌尿外科杂志, 2022, 43(1): 75-78. LIU Gang, WANG Kunli, TIAN Ye, et al. The research progress in surgical treatment of primary hyperaldosteronism [J]. Chin J Urol, 2022, 43(1): 75-78.
[4] 刘欣, 郑伊能, 钟毅, 等. CT纹理分析对醛固酮腺瘤与皮质醇腺瘤的鉴别诊断价值[J]. 中国中西医结合影像学杂志, 2021, 19(1): 60-64. LIU Xin, ZHENG Yineng, ZHONG Yi, et al. Differential diagnostic value of aldosterone-producing adenoma and cortisol-producing adenoma by CT texture analysis [J]. Chinese Imaging Journal of Integrated Traditional and Western Medicine, 2021, 19(1): 60-64.
[5] 何竑超, 祝宇, 何威, 等. 腹腔镜下肾上腺部分切除术治疗库欣综合征肾上腺腺瘤:单中心121例临床分析[J]. 中华泌尿外科杂志, 2017, 38(4): 244-247. HE Hongchao, ZHU Yu, HE Wei, et al. Clinical investigation on minimal invasive surgery for Cushing syndrome caused by adrenocortical adenoma: experience of 121 cases in a single center [J]. Chinese Journal of Urology, 2017, 38(4): 244-247.
[6] 宋颖, 罗婷, 肖明, 等. 单侧肾上腺增生性原发性醛固酮增多症的临诊应对[J]. 中华内分泌代谢杂志, 2018, 34(12): 1037-1041. SONG Ying, LUO Ting, XIAO Ming, et al. Approach to a patient with primary aldosteronism caused by unilateral adrenal hyperplasia [J]. Chinese Journal of Endocrinology and Metabolism, 2018, 34(12): 1037-1041.
[7] Panda A, Das CJ, Dhamija E, et al. Adrenal imaging(Part 1): Imaging techniques and primary cortical lesions [J]. Indian J Endocrinol Metab, 2015, 19(1): 8-15.
[8] Shrout P, Fleiss J. Intraclass correlations: uses in assessing rater reliability [J]. Psychological Bulletin, 1979, 86(2): 420-428.
[9] Torresan F, Crimì F, Ceccato F, et al. Radiomics: a new tool to differentiate adrenocortical adenoma from carcinoma [J]. BJS Open, 2021, 5(1): zraa061.
[10] 郭凯, 任帅, 刘绍伟, 等. CT动态增强鉴别肾上腺乏脂肪腺瘤与肾上腺结节样增生的价值[J]. 医学影像学杂志, 2020, 30(4): 632-636. GUO Kai, REN Shuai, LIU Shaowei, et al. The value of CT dynamic contrast-enhanced scanning in distinguishing lipid-poor adrenal adenoma and adrenal nodular hyperplasia [J]. Journal of Medical Imaging, 2020, 30(4): 632-636.
[11] Park SY, Park BK, Park JJ, et al. Differentiation of adrenal hyperplasia from adenoma by use of CT densitometry and percentage washout [J]. AJR Am J Roentgenol, 2016, 206(1): 106-112.
[12] 蔡明珠. 能谱CT多物质参数在肾上腺结节性增生与乏脂性腺瘤中的诊断价值[D]. 郑州:郑州大学, 2019.
[13] 张振红, 解丙坤, 洒盼盼, 等. CT增强扫描碘对比剂不良反应的临床表现分析[J]. 医学影像学杂志, 2020, 30(9): 1718-1720. ZHANG Zhenhong,XIE Bingkun,SA Panpan, et al. Analysis of clinical manifestations of adverse reactions of iodine contrast medium in enhanced CT scan [J]. Journal of Medical Imaging, 2020, 30(9): 1718-1720.
[14] Young WF, Stanson AW, Thompson GB, et al. Role for adrenal venous sampling in primary aldosteronism [J]. Surgery, 2004, 136(6): 1227-1235.
[15] 杨蕾, 张在先, 国建林, 等. 基于增强CT影像组学模型预测肺腺癌ALK突变[J]. 中国医学影像学杂志, 2021, 29(5): 454-458. YANG Lei, ZHANG Zaixian, GUO Jianlin, et al. Radiomics models based on enhanced CT for predicting ALK mutation in lung adenocarcinoma [J]. Chinese Journal of Medical Imaging, 2021, 29(5): 454-458.
[16] He K, Zhang ZT, Wang ZH, et al. A clinical-radiomic nomogram based on unenhanced computed tomography for predicting the risk of aldosterone-producing adenoma [J]. Frontiers in Oncology, 2021, 11: 634879. doi:10.3389/fonc.2021.634879
[17] Davnall F, Yip CSP, Ljungqvist G, et al. Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? [J]. Insights into Imaging, 2012, 3(6): 573-589.
[18] Yi X, Guan X, Zhang Y, et al. Radiomics improves efficiency for differentiating subclinical pheochromocytoma from lipid-poor adenoma: a predictive, preventive and personalized medical approach in adrenal incidentalomas [J]. EPMA J, 2018, 9(4): 421-429.
[19] Kong J, Zheng J, Wu J, et al. Development of a radiomics model to diagnose pheochromocytoma preoperatively: a multicenter study with prospective validation[J]. J Transl Med, 2022, 20(1): 31.
[20] Yu H, Parakh A, Blake M, et al. Texture analysis as a radiomic marker for differentiating benign from malignant adrenal tumors [J]. J Comput Assist Tomogr, 2020, 44(5): 766-771.
[21] Akai H, Yasaka K, Kunimatsu A, et al. Application of CT texture analysis to assess the localization of primary aldosteronism[J]. Sci Rep, 2020, 10(1): 472.
[22] Daye D, Staziaki P, Furtado V, et al. CT Texture analysis and machine learning improve post-ablation prognostication in patients with adrenal metastases: a proof of concept [J]. Cardiovasc Inter Rad, 2019, 42(12): 1771-1776.
[23] Karahaliou A, Vassiou K, Arikidis N, et al. Assessing heterogeneity of lesion enhancement kinetics in dynamic contrast-enhanced MRI for breast cancer diagnosis [J]. Brit J Radiol, 2010, 83(988): 296-309.
[24] 常富江, 张雪培, 王声政, 等. 醛固酮腺瘤患者血浆醛固酮、肾素水平分析[J]. 检验医学, 2019, 34(8): 722-725. CHANG Fujiang, ZHANG Xuepei, WANG Shengzheng, et al. Plasma aldosterone and renin levels in patients with aldosterone adenoma[J]. Laboratory Medicine, 2019, 34(8): 722-725.
[25] 李蓉. 肾上腺软组织密度肿块的影像学诊断相关研究[D]. 天津:天津医科大学, 2019.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed