Value of dual-modal ultrasound imaging nomogram in differentiating benign and malignant peripheral pulmonary focal lesions

doi:10.3877/cma.j.issn.1672-6448.2025.01.009

Abstract

Abstract:

Objective

To develop a nomogram based on dual-modal ultrasound features and radiomics, and to evaluate its value in differentiating benign and malignant peripheral pulmonary focal lesions.

Methods

A total of 306 patients with peripheral pulmonary focal lesions confirmed by ultrasoundguided biopsy in the Second Hospital of Shanxi Medical University from October 2017 to October 2023 were retrospectively collected, including 143 patients with benign lesions and 163 patients with malignant lesions.All patients underwent two-dimensional ultrasound and contrast-enhanced ultrasound.At a ratio of 7:3, the patients were randomly divided into a training set (214 cases) and a validation set (92 cases),and extraction of radiomics feature from dual-modal ultrasound images was performed.The least absolute shrinkage and selection operator (LASSO) regression was used to screen the optimal features and construct the radiomics score (Rad-score).Univariate and multivariate Logistic regression analyses were performed to screen independent risk factors for differential diagnosis, and a clinical model and a nomogram model were developed.The nomogram model included both Rad-score and independent clinical risk factors identified by multivariate analysis, while the clinical model only included independent clinical risk factors.Receiver operating characteristic curve, calibration curve, and clinical decision curve analyses were used to evaluate the efficiency of each model.

Results

A total of 14 radiomics features were obtained by feature dimension reduction and screening.Multivariate Logistic regression analysis showed that age, lesion morphology,lesion-lung tissue enhancement time difference, enhancement mode, and Rad-score were independent risk factors for judging the benign and malignant nature of peripheral pulmonary focal lesions.The area under the curve of the nomogram based on the above factors in the training set and validation set was 0.894 and 0.917, respectively, which was higher than that of the clinical model and Rad-score alone.The calibration curve showed a good consistency between the predicted probability of the nomogram and the pathological results.The clinical decision curve showed that the nomogram model provided higher clinical value in the differential diagnosis of benign and malignant peripheral pulmonary focal lesions in a larger threshold range.

Conclusion

The combination of two-dimensional ultrasound, contrast-enhanced ultrasound features, and radiomics can better identify the benign and malignant peripheral pulmonary focal lesions and provide a basis for clinical diagnosis.

Key words: Ultrasonography, Radiomics, Contrast agent, Peripheral pulmonary lesions, Nomogram

Jie Zhao, Lijing Zhu, Lei Hao, Zezheng Chen, Bojuan Wang, Jingzhu Xu, Kai Zhang, Jizheng Tu, Xinghua Wang. Value of dual-modal ultrasound imaging nomogram in differentiating benign and malignant peripheral pulmonary focal lesions[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(01): 62-69.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://chaosheng.cma-cmc.com.cn/EN/10.3877/cma.j.issn.1672-6448.2025.01.009

https://chaosheng.cma-cmc.com.cn/EN/Y2025/V22/I01/62

Figures/Tables 9

因素	训练集		统计值	P 值	验证集		统计值	P 值
因素	良性组（n=100）	恶性组（n=114）	统计值	P 值	良性组（n=43）	恶性组（n=49）	统计值	P 值
年龄（岁， $\overset{ˉ}{x}$ ±s）	57.9±15.0	67.3±10.7	t=-5.191	＜ 0.001	59.5±13.8	66.8±12.1	t=-2.701	0.008
男/ 女（例）	59/41	87/27	χ2=7.368	0.007	33/10	39/10	χ ²=0.109	0.741
病灶大小（cm， $\overset{ˉ}{x}$ ±s）	5.16±2.62	5.78±2.76	t=-1.677	0.095	5.50±2.94	5.88±2.84	t=-0.630	0.530
病灶形态（例）			χ2=8.180	0.004			χ2=5.935	0.015
楔形/ 三角形	42	27			20	11
球形/ 团块状	58	87			23	38
回声（例）			χ ²=0.517	0.472			χ ²=0.143	0.706
均	47	48			22	27
不均	53	66			21	22
边界（例）			χ ²=0.133	0.716			χ ²=2.140	0.144
清	75	83			34	32
不清	25	31			9	17
空气支气管气相（例）			χ ²=2.960	0.085			χ ²=1.933	0.164
有	21	14			10	6
无	79	100			33	43
AT（s， $\overset{ˉ}{x}$ ±s）	10.67±3.80	12.31±4.75	t=-2.757	0.006	10.23±3.45	11.67±3.49	t=-1.987	0.050
未增强区（例）			χ ²=0.694	0.405			χ ²=0.056	0.813
有	46	46			20	24
无	54	68			23	25
ΔAT（例）			χ ²=19.859	＜ 0.001			χ ²=8.642	0.003
＜ 2.5 s	74	50			29	18
≥ 2.5 s	26	64			14	31
增强模式（例）			χ ²=14.161	＜ 0.001			χ ²=4.896	0.027
迅速基底树枝	59	38			20	12
其他	41	76			23	37

因素	训练集		统计值	P 值	验证集		统计值	P 值
因素	良性组（n=100）	恶性组（n=114）	统计值	P 值	良性组（n=43）	恶性组（n=49）	统计值	P 值
年龄（岁， $\overset{ˉ}{x}$ ±s）	57.9±15.0	67.3±10.7	t=-5.191	＜ 0.001	59.5±13.8	66.8±12.1	t=-2.701	0.008
男/ 女（例）	59/41	87/27	χ2=7.368	0.007	33/10	39/10	χ ²=0.109	0.741
病灶大小（cm， $\overset{ˉ}{x}$ ±s）	5.16±2.62	5.78±2.76	t=-1.677	0.095	5.50±2.94	5.88±2.84	t=-0.630	0.530
病灶形态（例）			χ2=8.180	0.004			χ2=5.935	0.015
楔形/ 三角形	42	27			20	11
球形/ 团块状	58	87			23	38
回声（例）			χ ²=0.517	0.472			χ ²=0.143	0.706
均	47	48			22	27
不均	53	66			21	22
边界（例）			χ ²=0.133	0.716			χ ²=2.140	0.144
清	75	83			34	32
不清	25	31			9	17
空气支气管气相（例）			χ ²=2.960	0.085			χ ²=1.933	0.164
有	21	14			10	6
无	79	100			33	43
AT（s， $\overset{ˉ}{x}$ ±s）	10.67±3.80	12.31±4.75	t=-2.757	0.006	10.23±3.45	11.67±3.49	t=-1.987	0.050
未增强区（例）			χ ²=0.694	0.405			χ ²=0.056	0.813
有	46	46			20	24
无	54	68			23	25
ΔAT（例）			χ ²=19.859	＜ 0.001			χ ²=8.642	0.003
＜ 2.5 s	74	50			29	18
≥ 2.5 s	26	64			14	31
增强模式（例）			χ ²=14.161	＜ 0.001			χ ²=4.896	0.027
迅速基底树枝	59	38			20	12
其他	41	76			23	37

模型	AUC（95%CI）	准确性（%）	敏感度（%）	特异度（%）
临床模型
训练集	0.782（0.720 ～ 0.844）	74.3	65.0	82.5
验证集	0.771（0.676 ～ 0.867）	73.9	74.4	73.5
Rad-score
训练集	0.821（0.767 ～ 0.876）	75.7	74.0	77.2
验证集	0.856（0.783 ～ 0.930）	76.1	90.7	63.3
联合列线图
训练集	0.894（0.852 ～ 0.936）	81.8	91.0	73.7
验证集	0.917（0.863 ～ 0.972）	84.8	88.4	81.6

References 20

1	Eldridge L, Wagner EM.Angiogenesis in the lung [J].J Physiol, 2019,597(4): 1023-1032.
2	Eldridge L, Moldobaeva A, Zhong Q, et al.Bronchial artery angiogenesis drives lung tumor growth [J].Cancer Res, 2016, 76(20):5962-5969.
3	Fu Y, Zhang YY, Cui LG, et al.Ultrasound-guided biopsy of pleuralbased pulmonary lesions by injection of contrast-enhancing drugs [J].Front Pharmacol, 2019, 10: 960-967.
4	Fu Y, Lei Y, Cui L, et al.Can ultrasound and contrast-enhanced ultrasound help differentiate between subpleural focal organizing pneumonia and primary lung malignancy? [J].Diagnostics (Basel),2022, 12(9): 2074-2084.
5	朱丽静, 王兴华.超声造影定量参数对肺部良恶性病变鉴别诊断的研究 [J].中国临床医学影像杂志, 2020, 31(1): 34-37.
6	郭西源, 郝磊, 朱丽静, 等.超声造影鉴别诊断周围型肺局灶性病变的临床价值 [J].临床超声医学杂志, 2020, 22(11): 866-868.
7	Findeisen H, Trenker C, Figiel J, et al.Vascularization of primary,peripheral lung carcinoma in CEUS - a retrospective study (n = 89 patients) [J].Ultraschall Med, 2019, 40(5): 603-608.
8	Calamai I, Greco M, Finazzi S, et al.Thoracic Ultrasonography reporting:the TUONO study [J].J Clin Med, 2022, 11(23): 7126-7135.
9	宋奕薇, 李曼熙, 李阳, 等.基于临床及超声特征列线图模型诊断淋巴瘤 [J].中国介入影像与治疗学, 2024, 21(3): 170-174.
10	Guo SY, Zhou P, Zhang Y, et al.Exploring the value of radiomics features based on B-mode and contrast-enhanced ultrasound in discriminating the nature of thyroid nodules [J].Front Oncol, 2021,11: 738909-73917.
11	Bade BC, Dela Cruz CS.Lung cancer 2020: epidemiology, etiology,and prevention [J].Clin Chest Med, 2020, 41(1): 1-24.
12	Bi K, Xia DM, Fan L, et al.Development and prospective validation of an ultrasound prediction model for the differential diagnosis of benign and malignant subpleural pulmonary lesions: a large ambispective cohort study [J].Front Oncol, 2021, 11: 656060-656072.
13	Boccatonda A, Guagnano MT, D’Ardes D, et al.The role of contrastenhanced ultrasound in the differential diagnosis of malignant and benign subpleural lung lesions [J].J Clin Med, 2024, 13(8): 2302-2330.
14	郭西源, 朱丽静, 土继政, 等.超声造影与增强CT 对周围型肺局灶性病变诊断价值的对比研究 [J].中国临床医学影像杂志, 2021,32(11): 799-802.
15	魏伟, 冯慧俊, 韦天军, 等.基于超声影像组学鉴别腮腺良性与恶性肿瘤临床应用价值 [J].中国超声医学杂志, 2023, 39(6): 613-617.
16	张旭, 黄品同.基于灰阶超声影像组学的颈部淋巴瘤预测模型研究 [J].中华超声影像学杂志, 2021, 30(6): 506-512.
17	Chen M, Copley SJ, Viola P, et al.Radiomics and artificial intelligence for precision medicine in lung cancer treatment [J].Semin Cancer Biol, 2023,93: 97-113.
18	Du D, Gu J, Chen X, et al.Integration of PET/CT radiomics and semantic features for differentiation between active pulmonary tuberculosis and lung cancer [J].Mol Imaging Biol, 2021, 23(2): 287-298.
19	Gong JW, Zhang Z, Luo TY, et al.Combined model of radiomics,clinical, and imaging features for differentiating focal pneumonialike lung cancer from pulmonary inflammatory lesions: an exploratory study [J].BMC Med Imaging, 2022, 22(1): 98-107.
20	Wei M, Du Y, Wu X, et al.A benign and malignant breast tumor classification method via efficiently combining texture and morphological features on ultrasound images [J].Comput Math Methods Med, 2020, 2020: 5894010-5894021.

[1]	Shuhan Sun, Yajing Chen, Qingqing Zong, Cuiying Li, Shumei Miao, Bin Yang, Feihong Yu. Ultrasound-based deep learning nomogram for predicting axillary lymph node status after neoadjuvant chemotherapy for breast cancer [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(02): 97-105.
[2]	Tingting Shen, Bowen Zhao, Mei Pan, Xiaohui Peng, Ran Chen, Yuanshi Tian, Mingxuan Zhang. Evaluation of cardiac morphology and function in fetuses with simple complete transposition of the great arteries using fetal heart quantification：a preliminary study [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(02): 120-130.
[3]	Xinyue Wang, Ya Yuan, Hua Shu, Kunpeng Cao, Xinhua Ye, Lu Li. Development of a dose prediction model for ultrasound-guided thrombin treatment of pseudoaneurysms using the LightGBM algorithm [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(02): 153-161.
[4]	Xuewei He, Hua Lian, Ning Wang, Xiaohong Fang. Clinical application of real-time dynamic three-dimensional painless tubal contrast-enhanced ultrasonography [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(01): 39-45.
[5]	Caixia Zhu, Zhixing Liu, Fangqun Chen, Jingling Wang, Jin Yao, Xingqi Peng, Yi Mao, Li Chen. Value of ultrasound viscoelastic imaging technology in differential diagnosis of benign and malignant breast masses≤3 cm [J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2024, 21(12): 1095-1102.
[6]	Xia Xu, Jiamin Hu, Liping Huang, Long Cheng, Shuliu Zhang, Weiwei Zhao, Panpan Gu, Cheng Cao. Current status of early enteral nutrition feeding intolerance in elderly critically ill patients and the construction and validation of a risk prediction nomogram [J]. Chinese Journal of Critical Care Medicine(Electronic Edition), 2025, 18(01): 11-17.
[7]	Xia Pan, Lin Li, Lei Zhu, Chao Dai, Le Pang. Association analysis of oral frailty risk in elderly people in Hanzhong community and construction of a nomogram model [J]. Chinese Journal of Stomatological Research(Electronic Edition), 2025, 19(01): 25-32.
[8]	Qiang Yuan, Huayu Zhang, Zhangzhe Yan, Hanfang Zhu, Guang Chen, Liang Sun, Yuan Lv, Gang Chen, Suo Zhao. Preoperative prediction model for central lymph node metastasis in cN0 lateral isthmic papillary thyroid carcinoma [J]. Chinese Journal of Operative Procedures of General Surgery(Electronic Edition), 2025, 19(03): 333-336.
[9]	Danfeng Shen, Peng Chang, Yingchao Lu, Hongxing Xu, Qiang Gu. Early prediction value of PCT and CRP on severity of acute cholangitis and construction of nomogram model [J]. Chinese Journal of Operative Procedures of General Surgery(Electronic Edition), 2025, 19(02): 192-195.
[10]	Zheng Li, Jinfeng Ma. Construction of a nomogram model for predicting prognosis of esophagogastric junction adenocarcinoma patients after radical surgery based on inflammatory response scoring system [J]. Chinese Journal of Operative Procedures of General Surgery(Electronic Edition), 2025, 19(02): 170-175.
[11]	Song Zhou, Xiangyong Jiang, Hai Kang, Ke Yang, An Wei, Zhenhua Tang, Tieqiu Li. The value of contrast enhanced ultrasonography in the diagnosis of prostate cancer: a meta-analysis [J]. Chinese Journal of Endourology(Electronic Edition), 2025, 19(02): 159-166.
[12]	Feng Qiu, Tianchi Yang, Wei Han. Safety and efficacy of laparoscopic ultrasound-guided radiofrequency ablation for malignant liver tumors [J]. Chinese Journal of Hepatic Surgery(Electronic Edition), 2025, 14(01): 102-106.
[13]	Lei Tan, Dengdi Wang, Hao Zhang, Zhuoma Danzeng, Yi Long, Zeqian Wu. Application of contrast-enhanced ultrasound in diagnosis of liver rupture: reflection on one case of liver rupture from Xizang [J]. Chinese Journal of Hepatic Surgery(Electronic Edition), 2025, 14(01): 113-117.
[14]	Zexin Yin, Jilin Yang, Youyao Li, Meilong Wu, Liping Liu. Research progress in preoperative prediction of microvascular invasion in liver cancer [J]. Chinese Journal of Hepatic Surgery(Electronic Edition), 2025, 14(01): 128-134.
[15]	Gaofang Zhao, Jing Chen, Chunmei Wang, Juan Wu. Ultrasound omics study of axillary lymph node metastatic burden in breast cancer [J]. Chinese Journal of Interventional Radiology(Electronic Edition), 2025, 13(01): 54-61.

Please choose a citation manager

Content to export