目的 探讨CT影像组学模型在肾上腺富血供腺瘤(HAA)及嗜铬细胞瘤(AP)鉴别诊断中的价值。方法 回顾性纳入2022-01至2024-07在解放军总医院第三医学中心放射诊断科行CT四期扫描并经病理证实的79例患者(HAA 53例,AP 26例),收集患者的临床指标、影像特征,并通过科研平台分期像提取影像组学特征,采用F_Test方法对影像组学特征降维和筛选,其中差异有统计学意义的因素纳入二元logistic回归分析及后续建模,最后绘制预测模型的ROC曲线及决策曲线以评估其预测效能和临床应用价值。结果 平扫CT值(OR=1.166,P＜0.01)和肿瘤长径(OR=2.226,P＜0.01)是鉴别两组的独立危险因素。基于CTpre、动脉期(CTa)、动脉晚期(CTla)、静脉期(CTv)、四期联合、影像特征及临床指标模型验证集的AUC分别为0.93、0.92、0.88、0.86、0.87、0.88、0.72,基于CTpre影像组学效能最优,其准确度、敏感度、特异度分别为0.86、0.89、0.85。结论 基于CT影像组学模型在鉴别HAA和AP中具有较高的预测性能和应用价值。
Abstract
Objective To explore the value of the CT radiomics model in the differential diagnosis of hypervascular adrenal adenoma (HAA) and pheochromocytoma (AP). Methods A total of 79 patients (53 HAA and 26 AP) who underwent phase 4 CT scan and were pathologically confirmed in the Department of Radiology of the Third Medical Center of PLA General Hospital from January 2022 to July 2024 were retrospectively included. Clinical indicators and radiomics features extracted from CT images through scientific research platform were analyzed. Using the F_Test to reduce dimensionality and screen radiomics features, factors with statistically significant differences were included in binary logistic regression analysis and subsequent modeling. Finally, ROC curve and decision curve of the predictive model were plotted to evaluate its predictive performance and clinical application value. Results The value of plain CT scan (OR=1.166, P<0.01) and the long diameter of tumor (OR=2.226, P<0.01) were independent risk factors for the discrimination of the two groups. The AUC based on CTpre, arterial phase (CTa), late arterial phase (CTla), venous phase (CTv), four-phase combination, imaging features, and clinical indicator model validation set were 0.93, 0.92, 0.88, 0.86, 0.87, 0.88 and 0.72, respectively. The CTpre-based radiomics model was characterized by the best performance, with accuracy, sensitivity, and specificity of 0.86, 0.89, and 0.85, respectively. Conclusions The model based om CT radiomics has good predictive performance and application value in the discrimination of HAA from AP.
关键词
CT /
影像组学 /
肾上腺富血供腺瘤 /
嗜铬细胞瘤 /
鉴别
Key words
CT /
radiomics /
hypervascular adrenal adenoma /
adrenal pheochromocytoma /
discrimination
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Fassnacht M, Tsagarakis S, Terzolo M, et al. European society of endocrinology clinical practice guidelines on the management of adrenal incidentalomas, in collaboration with the european network for the study of adrenal tumors[J]. Eur J Endocrinol, 2023,189(1):G1-G42.
[2] Aggarwal S, Prete A, Chortis V, et al. Pheochromocytomas most commonly present as adrenal incidentalomas: a large tertiary center experience[J]. J Clin Endocrinol Metab, 2023,109(1):e389-e396.
[3] Bancos I, Prete A. Approach to the patient with adrenal incidentaloma[J]. The J of Clini End & Met, 2021,106(11):3331-3353.
[4] Mete O, Asa S L, Gill A J, et al. Overview of the 2022 WHO Classification of Paragangliomas and Pheochromocytomas[J]. Endocr Pathol, 2022,33(1):90-114.
[5] Amin M B, Greene F L, Edge S B, et al. The eighth edition AJCC cancer staging manual: continuing to build a bridge from a population‐based to a more “personalized” approach to cancer staging[J]. CA: A Cancer Journal for Clinicians, 2017,67(2):93-99.
[6] 张 磊, 石浪勇, 谢宝君. CT与MRI鉴别诊断肾上腺皮质腺瘤与嗜铬细胞瘤的价值研究[J]. 现代医用影像学, 2023,32(10):1924-1927.
[7] 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.
[8] 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(03):484-488.
[9] Aerts H J, Velazquez E R, Leijenaar R T, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach[J]. Nat Commun, 2014,5:4006.
[10] 周 怡, 张 贝, 黄科峰, 等. 高分辨CT联合Ki-67表达预测低分化浸润性非黏液肺腺癌的临床应用[J]. 武警医学, 2024,35(09):777-780.
[11] 吴春梅, 殷小平. 肾上腺腺瘤的影像组学研究进展[J]. 医学研究与教育, 2022,39(3):29-34.
[12] Reiazi R, Abbas E, Famiyeh P, et al. The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review[J]. Computers in Bio Med, 2021,133:104400.
[13] Fassnacht M, Arlt W, Bancos I, et al. Management of adrenal incidentalomas: european society of endocrinology clinical practice guideline in collaboration with the european network for the study of adrenal tumors[J]. Eur J Endocrinol, 2016,175(2):G1-G34.
[14] Lam A K. Update on Adrenal Tumours in 2017 world health organization (WHO) of endocrine tumours[J]. Endocr Pathol, 2017,28(3):213-227.
[15] 史 展, 张亚斌, 张丹卉. 能谱CT成像在鉴别肾上腺意外瘤的价值研究[J]. 中国CT和MRI杂志, 2024,22(05):123-125.
[16] 刘 芳, 王明亮, 许晓杰, 等. 肾上腺嗜铬细胞瘤的MRI表现:常见特征及少见特征[J]. 临床放射学杂志, 2024,43(04):615-620.
[17] Gerson R, Tu W, Abreu-Gomez J, et al. Evaluation of the T2-weighted (T2W) adrenal MRI calculator to differentiate adrenal pheochromocytoma from lipid-poor adrenal adenoma[J]. Eur Radiol, 2022,32(12):8247-8255.
[18] Niu Z, Wang J, Yang Y, et al. Risk prediction model establishment with tri-phasic CT image features for differential diagnosis of adrenal pheochromocytomas and lipid-poor adenomas: Grouping method[J]. Front Endocrinol (Lausanne), 2022,13:925577.
[19] 陈 威, 陶宇峰, 王 伟. 基于CT影像特征构建鉴别肾上腺嗜铬细胞瘤和乏脂性腺瘤的预测模型[J]. 浙江医学, 2022,44(16):1714-1719.
[20] An Y Y, Yang G Z, Lin B, et al. Differentiation of lipid-poor adenoma from pheochromocytoma on biphasic contrast-enhanced CT[J]. Abdom Radiol (NY), 2021,46(9):4353-4361.
[21] Yi X, Guan X, Chen C, et al. Adrenal incidentaloma: machine learning-based quantitative texture analysis of unenhanced CT can effectively differentiate sPHEO from lipid-poor adrenal adenoma[J]. J Cancer, 2018,9(19):3577-3582.
PDF(2465 KB)
