常规影像和CT影像组学特征鉴别腮腺腺淋巴瘤与恶性肿瘤的价值

doi:10.3969/j.issn.1006-5725.2025.21.021

Abstract

Abstract:

Objective To investigate the value of conventional radiological features and CT radiomics features to differentiate parotid adenolymphoma from malignant tumor. Methods Radiological data from 128 patients with adenolymphoma and 39 patients with parotid malignancy were collected between December 2018 and October 2023. Radiomics features were extracted to obtain Rad?score and construct a radiomics model. Conventional radiological features were analyzed to obtain independent predictors， and a conventional radiological model was constructed. Model performance was compared by the DeLong test， and the Rad?score was combined with radiological features to establish a comprehensive model and plot a nomogram. Results Based on CT venous phase images， 9 optimal radiomic features were selected. Conventional radiological features were analyzed by univariate and multivariate logistic regression analysis and found that shape and degree of enhancement were independent predictors of adenolymphoma and malignant parotid tumors. The CT radiomics model is superior to the conventional radiological model（P < 0.05）. The area under the curve （AUC） of the radiomics model was 0.938 （95% CI： 0.887 ~ 0.988）， and the specificity and sensitivity were 0.856 and 0.923， respectively. Conventional radiological features and Rad?score were analyzed by univariate and multivariate logistic regression analysis and found that Rad?score and degree of enhancement were independent predictors of adenolymphoma and malignant parotid tumors. The difference between the diagnostic efficacy of the comprehensive model created by the Rad?score combined with the degree of enhancement and the diagnostic efficacy of the radiomics model was not statistically significant （P > 0.05）. Conclusion The CT radiomics model performed better than the conventional radiological model in discriminating parotid gland adenolymphoma from malignant tumors. The diagnostic performance of the comprehensive model has improved， aiding in clinical decision?making.

Key words: parotid gland, adenolymphoma, malignant tumor, radiomics

CLC Number:

R445.3

Guoliang WEN,Hang FANG,Wei. ZHANG. Value of conventional radiological features and ct radiomics features in differentiating parotid adenolymphoma from malignant tumors[J]. The Journal of Practical Medicine, 2025, 41(21): 3442-3448.

Figures/Tables 9

Tab.1

Tab.2

Tab.3

Tab.4

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

References 25

[1]	LIU S， YU B， ZHENG X， et al. Construction and Application of a Nomogram for Predicting Benign and Malignant Parotid Tumors［J］. J Comput Assist Tomogr，2024，48（1）：143-149. doi:10.1097/rct.0000000000001522 doi: 10.1097/rct.0000000000001522
[2]	QUER M， HERNANDEZ-PRERA J C， SILVER C E， et al. Current Trends and Controversies in the Management of Warthin Tumor of the Parotid Gland［J］. Diagnostics （Basel），2021，11（8）：1467. doi:10.3390/diagnostics11081467 doi: 10.3390/diagnostics11081467
[3]	陈飞，王利伟，布静秋. 腮腺沃辛瘤555例临床分析［J］. 北京口腔医学，2022，30（4）：284-286.
[4]	DI SANTO D， DERETTI A， VANDER POORTEN V. Current surgical management of malignant parotid tumors［J］. Curr Opin Otolaryngol Head Neck Surg，2025，33（2）：79-84. doi:10.1097/moo.0000000000001039 doi: 10.1097/moo.0000000000001039
[5]	GEIGER J L， ISMAILA N， BEADLE B， et al. Management of Salivary Gland Malignancy： ASCO Guideline［J］. J Clin Oncol，2021，39（17）：1909-1941. doi:10.1200/jco.21.00449 doi: 10.1200/jco.21.00449
[6]	ESPINOZA S， FELTER A， MALINVAUD D， et al. Warthin's tumor of parotid gland： Surgery or follow-up？ Diagnostic value of a decisional algorithm with functional MRI［J］. Diagn Interv Imaging，2016，97（1）：37-43. doi:10.1016/j.diii.2014.11.024 doi: 10.1016/j.diii.2014.11.024
[7]	CENGIZ A B， TANSUKER H D， GUL R， et al. Comparison of preoperative diagnostic accuracy of fine needle aspiration and core needle biopsy in parotid gland neoplasms［J］. Eur Arch Otorhinolaryngol，2021，278（10）：4067-4074. doi:10.1007/s00405-021-07022-x doi: 10.1007/s00405-021-07022-x
[8]	LAMBIN P， RIOS-VELAZQUEZ E， LEIJENAAR R， et al. Radiomics： Extracting more information from medical images using advanced feature analysis［J］. Eur J Cancer，2012，48（4）：441-446. doi:10.1016/j.ejca.2011.11.036 doi: 10.1016/j.ejca.2011.11.036
[9]	何尚鹏，黄炜贤，江燕辉，等. 超声特征与超声影像组学对Bethesda Ⅲ类甲状腺结节良恶性再评价的价值［J］. 实用医学杂志，2025，41（12）：1892-1898.
[10]	YE J， CHEN Y， PAN J， et al. US-based Radiomics Analysis of Different Machine Learning Models for Differentiating Benign and Malignant BI-RADS 4A Breast Lesions［J］. Acad Radiol，2025，32（1）：67-78. doi:10.1016/j.acra.2024.08.024 doi: 10.1016/j.acra.2024.08.024
[11]	黄忠江，姜增誉，李健丁，等. 基于增强CT影像组学联合机器学习鉴别均质性肾透明细胞癌与肾乏脂肪血管平滑肌脂肪瘤［J］. 实用医学杂志，2021，37（17）：2266-2270. doi:10.3969/j.issn.1006-5725.2021.17.020 doi: 10.3969/j.issn.1006-5725.2021.17.020
[12]	CHEN F， GE Y， LI S， et al. Enhanced CT-based texture analysis and radiomics score for differentiation of pleomorphic adenoma， basal cell adenoma， and Warthin tumor of the parotid gland［J］. Dentomaxillofac Radiol，2023，52（2）：20220009. doi:10.1259/dmfr.20220009 doi: 10.1259/dmfr.20220009
[13]	HU Z， GUO J， FENG J， et al. Value of T2-weighted-based radiomics model in distinguishing Warthin tumor from pleomorphic adenoma of the parotid［J］. Eur Radiol，2023，33（6）：4453-4463. doi:10.1007/s00330-022-09295-0 doi: 10.1007/s00330-022-09295-0
[14]	FISHER R， RONEN O. Cytologic diagnosis of parotid gland Warthin tumor： Systematic review and meta-analysis［J］. Head Neck，2022，44（10）：2277-2287. doi:10.1002/hed.27099 doi: 10.1002/hed.27099
[15]	王张嵩，谢舒乐，张汉卿，等. 2456例唾液腺肿瘤临床病理分析［J］. 口腔疾病防治，2020，28（5）：298-302.
[16]	LEE D H， JUNG E K， LEE J K， et al. Comparative analysis of benign and malignant parotid gland tumors： A retrospective study of 992 patients［J］. Am J Otolaryngol，2023，44（2）：103690. doi:10.1016/j.amjoto.2022.103690 doi: 10.1016/j.amjoto.2022.103690
[17]	张亮，张莉，刘华，等. 312例腮腺区肿瘤临床回顾性分析［J］. 临床口腔医学杂志，2022，38（9）：534-537.
[18]	YU H， CALDWELL C， MAH K， et al. Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images［J］. Int J Radiat Oncol Biol Phys，2009，75（2）：618-625. doi:10.1016/j.ijrobp.2009.04.043 doi: 10.1016/j.ijrobp.2009.04.043
[19]	LIU Y， ZHENG J， LU X， et al. Radiomics-based comparison of MRI and CT for differentiating pleomorphic adenomas and Warthin tumors of the parotid gland： A retrospective study［J］. Oral Surg Oral Med Oral Pathol Oral Radiol，2021，131（5）：591-599. doi:10.1016/j.oooo.2021.01.014 doi: 10.1016/j.oooo.2021.01.014
[20]	ZHENG Y， ZHOU D， LIU H， et al. CT-based radiomics analysis of different machine learning models for differentiating benign and malignant parotid tumors［J］. Eur Radiol，2022，32（10）：6953-6964. doi:10.1007/s00330-022-08830-3 doi: 10.1007/s00330-022-08830-3
[21]	LI Q， JIANG T， ZHANG C， et al. A nomogram based on clinical information， conventional ultrasound and radiomics improves prediction of malignant parotid gland lesions［J］. Cancer Lett，2022，527：107-114. doi:10.1016/j.canlet.2021.12.015 doi: 10.1016/j.canlet.2021.12.015
[22]	MUNTEAN D D， DUDEA S M， BĂCIUȚ M， et al. The Role of an MRI-Based Radiomic Signature in Predicting Malignancy of Parotid Gland Tumors［J］. Cancers （Basel），2023，15（13）：3319. doi:10.3390/cancers15133319 doi: 10.3390/cancers15133319
[23]	ZHAO F， HUANG X， HE J， et al. A nomogram for distinguishing benign and malignant parotid gland tumors using clinical data and preoperative blood markers： Development and validation［J］. J Cancer Res Clin Oncol，2023，149（13）：11719-11733. doi:10.1007/s00432-023-05032-2 doi: 10.1007/s00432-023-05032-2
[24]	陈函，陈贤明，王茂鑫，等. 外周血中性粒细胞/淋巴细胞比值在腮腺恶性肿瘤诊断中的价值［J］. 中国耳鼻咽喉头颈外科，2021，28（7）：419-422.
[25]	秦硕，李冉，李春梅，等. 术前外周血炎症指标在腮腺恶性肿瘤中的诊断及预后价值分析［J］. 口腔颌面外科杂志，2022，32（6）：362-367.

因素	AL（n = 128）	MPGT（n = 39）	t//U/ χ²值	P值
轴位最大直径［M（P₂₅， P₇₅）］/cm	2.52（2.07，2.97）	2.68（2.18，3.39）	-1.653	0.098
形状			19.828	< 0.001
规则	105（82.0）	18（46.2）
不规则	23（18.0）	21（53.8）
边界			15.601	< 0.001
清楚	122（95.3）	28（71.8）
不清楚	6（4.7）	11（28.2）
囊变			4.177	0.041
有	95（74.2）	35（89.7）
无	33（25.8）	4（10.3）
强化程度			9.907	0.002
明显	69（53.9）	32（80.8）
不明显	59（46.1）	7（19.2）
			-10.894	< 0.001
Rad-score （x ± s）	-1.78 ± 0.71	-0.36 ± 0.73

因素	训练集（n = 116）	验证集（n = 51）	t//U/χ²值	P值
轴位最大直径［M（P₂₅， P₇₅）］/cm	2.68（2.11，3.25）	2.49（2.01，2.84）	-1.713	0.087
形状			1.847	0.174
规则	89（76.7）	34（66.7）
不规则	27（23.3）	17（33.3）
边界			1.010	0.315
清楚	106（91.4）	44（71.8）
不清楚	10（8.6）	7（28.2）
囊变			5.319	0.021
有	96（82.8）	34（66.7）
无	20（17.2）	17（33.3）
强化程度			1.176	0.278
明显	67（53.9）	34（66.7）
不明显	49（46.1）	17（33.3）
			-0.247	0.809
Rad-score（x ± s）	-1.46 ± 0.96	-1.42 ± 0.89

因素	单因素OR（95%CI）	P值	多因素OR（95%CI）	P值
轴位最大直径	1.865（1.246 ~ 2.790）	0.002	1.103（0.562 ~ 2.165）	0.776
形状	5.326（2.455 ~ 11.556）	< 0.001	2.621（0.737 ~ 9.320）	0.137
边界	7.988（2.723 ~ 23.433）	< 0.001	1.075（0.135 ~ 8.589）	0.945
囊变	3.039（1.004 ~ 9.202）	0.049	1.067（0.228 ~ 4.992）	0.934
强化程度	3.909（1.607 ~ 9.505）	0.003	4.912（1.197 ~ 20.161）	0.027
Rad-score	14.188（5.990 ~ 33.606）	< 0.001	13.188（4.938 ~ 35.219）	< 0.001

诊断方法		AUC（95%CI）	特异度	灵敏度
影像组学模型	训练集	0.938（0.887 ~ 0.988）	0.856	0.923
	验证集	0.858（0.742 ~ 0.975）	0.711	0.923
常规影像模型	训练集	0.785（0.697 ~ 0.873）	0.856	0.538
	验证集	0.692（0.540 ~ 0.845）	0.737	0.538
综合模型	训练集	0.944（0.899 ~ 0.990）	0.844	0.923
	验证集	0.879（0.777 ~ 0.980）	0.737	0.923

Value of conventional radiological features and ct radiomics features in differentiating parotid adenolymphoma from malignant tumors

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 25

Related Articles 11

Recommended Articles

Metrics

Comments

[1]	Danhui LAI,Yanhui JIANG,Siting YE,Shulian ZHUANG,Shuang YANG,Wen XUE,Jianxing ZHANG. Analysis of prediction of carotid in-stent restenosis based on ultrasonographic carotid plaque radiomics [J]. The Journal of Practical Medicine, 2025, 41(5): 742-750.
[2]	Yangchun DU,Hongyu ZHENG,Haining CHEN,Wenwen GUO,Jinxiu YAO,Tongliu LAN,Yanju XIAO. Ultrasound⁃based deep learning radiomics nomogram to differentiate type Ⅰ and type Ⅱ epithelial ovarian cancer [J]. The Journal of Practical Medicine, 2025, 41(18): 2920-2927.
[3]	Zhaoyang WANG,Nan. ZHANG. Constructing a Nomogram prediction model for early recurrence of hepatocellular carcinoma radical hepatectomy based on CT imaging omics and traditional Chinese medicine tongue image features [J]. The Journal of Practical Medicine, 2025, 41(16): 2590-2596.
[4]	Huiliang CAI,Qianying ZHANG,Ying HUANG,Weisheng PENG,Chengli WANG,Cuiting YANG,Na DENG,Sizhu ZHANG,Nina XU,Xiaobing HAN. Assessments of ki⁃67 expression in hepatocellular carcinoma using enhanced MRI intratumoral and peritumoral radiomics and clinical imaging features [J]. The Journal of Practical Medicine, 2025, 41(15): 2311-2319.
[5]	Shangpeng HE,Weixian HUANG,Yanhui JIANG,Xiongqiang PENG,Lingcui MENG,Jianxing ZHANG. Value of ultrasound radiomics in re⁃evaluating the benign or malignant of Bethesda Ⅲ nodules [J]. The Journal of Practical Medicine, 2025, 41(12): 1892-1898.
[6]	Minghong SHI,Zhanwei LIU,Yang ZHU,Lili XIA,Gang CHENG,Youguo LU. Influence of oxycodone-acetaminophen combined with local radiotherapy on serum cytokines in elderly patients with malignant tumor bone metastasis complicated with cancer pain [J]. The Journal of Practical Medicine, 2025, 41(11): 1718-1723.
[7]	ZHOU Huien, CHEN Wanming, WANG Mengdie, LUO Sijia, CHEN Jialin, HE Kun, GUO Xinmin. . The Value of Nomogram Model Based on Clinical and Ultrasound Radiomics for Predicting Preterm Birth [J]. The Journal of Practical Medicine, 2023, 39(14): 1835-1841.
[8]	LIAO Shuting, YU Xiangrong. . Application of spectral CT and artificial intelligence in the diagnosis of thyroid cancer [J]. The Journal of Practical Medicine, 2022, 38(2): 129-1133.
[9]	TIAN Tian, JING Hui, FU Jia.. Nomogram prediction model of delirium risk in patients with malignant tumors [J]. The Journal of Practical Medicine, 2021, 37(20): 2641-2646.
[10]	HUANG Zhongjiang, JIANG Zengyu, LI Jianding, ZHANG Zhixing, CHEN Wenqing. Application of enhanced CT radiomics in differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma [J]. The Journal of Practical Medicine, 2021, 37(17): 2266-2270.
[11]	LI Ling, HU Datao, XIA Chunhua, LI Hongxia.. Prediction of lymph node metastasis of head and neck malignant tumor based on CT radiomics nomogram [J]. The Journal of Practical Medicine, 2021, 37(14): 1872-1878.