人工智能辅助超声造影技术在微小肝癌诊断中的应用

肝脏 ›› 2026, Vol. 31 ›› Issue (8): 1112-1114.

人工智能辅助超声造影技术在微小肝癌诊断中的应用

吴思思, 杨阳

225500 泰州泰州市第二人民医院超声科(吴思思),消化内科(杨阳)

收稿日期:2026-01-21 出版日期:2026-08-31 发布日期:2026-09-28
通讯作者: 杨阳,Email:904438338@qq.com

The application of artificial intelligence-assisted contrast-enhanced ultrasound technology in the diagnosis of tiny liver cancer

Wu Sisi¹, Yang Yang²

1. Department of Ultrasound, Taizhou Second People′s Hospital, Taizhou 225500, China;
2. Department of Gastroenterology, Taizhou Second People′s Hospital, Taizhou 225500, China

Received:2026-01-21 Online:2026-08-31 Published:2026-09-28
Contact: Yang Yang,Email:904438338@qq.com

摘要/Abstract

摘要： 目的分析人工智能(AI)辅助超声造影(CEUS)技术在微小肝癌(SHCC)诊断中的应用价值。方法回顾性分析2023年1月至2025年1月泰州市第二人民医院进行检查的80例疑似SHCC的慢性肝病患者的临床资料,患者均进行CEUS及病理检查,将所有病灶的CEUS动态影像数据输入AI-CEUS系统,获得AI诊断结论。以病理或最终临床诊断为金标准,分析CEUS单独及在AI辅助下诊断SHCC的一致性。结果 80例患者中,共检出90个病灶,经病理确诊恶性病灶(SHCC)58个(64.44%),良性病灶32个(35.56%),其中血管瘤12个(37.50%),局灶性结节增生8个(25.00%)、不典型增生结节7个(21.88%)及炎性假瘤5个(15.62%)。一致性分析证实,CEUS技术诊断SHCC的准确率86.67%、灵敏度82.76%、特异度93.75%、阳性预测值96.00%、阴性预测值75.00%、Kappa值=0.724。AI辅助CEUS技术诊断SHCC的准确率92.22%、灵敏度91.38%、特异度93.75%、阳性预测值96.36%、阴性预测值85.71%、Kappa值=0.834。结论 AI辅助CEUS技术能显著提升SHCC的诊断准确率与特异性,具有优越且稳定的诊断性能,临床应用价值较高。

关键词: 人工智能, 超声造影技术, 微小肝癌

Abstract: Objective To analysis the application value of Contrast-Enhanced Ultrasound (CEUS) technology assisted by Artificial Intelligence (AI) in the diagnosis of small hepatocellular carcinoma (SHCC). Methods The clinical data of 80 patients with 90 lesions suspected to be SHCC who underwent examinations in Taizhou Second People′s Hospital from January 2023 to January 2025 were retrospectively analyzed. All patients underwent CEUS and pathological examinations. The dynamic imaging data of all lesions were input into the AI-CEUS system for analysis, and the AI diagnosis conclusions were obtained. Taking the pathological or final clinical diagnosis as the gold standard, the consistency of CEUS alone and in combination with AI for diagnosing SHCC was analyzed. Results More than 90 lesions were detected in 80 patients, within them. 58 cases (64.44%) were pathologically diagnosed as SHCC, 32 cases (35.56%) were of benign lesions,, which included 12 cases (37.50%) of hemangioma and 8 cases (25.00%) of focal nodular hyperplasia. 7 cases (21.88%), were of atypical hyperplasia nodules, and 5 cases (15.62%) were of inflammatory pseudotumor. Consistency analysis confirmed that the accuracy, sensitivity, and specificity of CEUS technique in the diagnosis of SHCC were 86.67%, 82.76% and 93.75%, respectively, with a positive predictive value of 96.00%, a negative predictive value of 75.00%, and a Kappa value of 0.724. The sensitivity, accuracy specificity, positive predictive value, negative predictive value, and Kappa value of AI auxiliary CEUS technique in diagnosing SHCC were 92.22%, 91.38%, 93.75%, 96.36%, 85.71%,and 0.834, respectively. Conclusion AI auxiliary CEUS technique can significantly improve the accuracy, specificity for diagnosing SHCC, with superior and stable performance, thus has high clinical value.

Key words: Artificial intelligence, Contrast-enhanced ultrasound technology, Small liver cancer

吴思思, 杨阳. 人工智能辅助超声造影技术在微小肝癌诊断中的应用[J]. 肝脏, 2026, 31(8): 1112-1114.

Wu Sisi, Yang Yang. The application of artificial intelligence-assisted contrast-enhanced ultrasound technology in the diagnosis of tiny liver cancer[J]. Chinese Hepatolgy, 2026, 31(8): 1112-1114.

/ 推荐

参考文献

[1] 陈丽,陆圣威,向田丹,等.肝硬化背景下小肝癌的诊断和鉴别诊断[J].中华肝脏病杂志, 2025, 33(4):323-328.
[2] 伍秋艳,刘娟,杨崇双,等.影像学检查在诊断小肝癌中的应用价值[J].中华消化外科杂志, 2022,21(4):543-550.
[3] 张岚,黎雅琳,韩鼎盛,等.微小肝细胞癌(≤1 cm)的Gd-EOB-DTPA增强MRI表现[J].中国医学计算机成像杂志, 2023, 29(1):39-43.
[4] 付小兵,袁建军,杨龙,等.超声造影对小肝癌微血管侵犯的预测价值[J].广东医学, 2023, 44(3):320-324.
[5] Jin X,Vincent W,Terry C .Is AI-based hepatocellular carcinoma prediction ready for prime time?[J].Liver Int, 2025, 45(4):e16165.
[6] 徐琛,黄品同,陈继繁,等.ACR CEUS LI-RADS和WFUMB-EFSUMB标准对高危人群肝细胞癌诊断价值的对比研究[J/OL].中华医学超声杂志(电子版), 2022,19(9):968-975.chaosheng.cma-cmc.com.cn/CN/10.3877/cma.j.issn.1672-6448.2022.09.017.
[7] 中华人民共和国国家卫生健康委员会医政医管局.原发性肝癌诊疗指南(2022年版)[J].中华肝脏病杂志,2022,30(4):367-388.
[8] 夏桂辉,贾昌俊,徐锋,等.吲哚菁绿荧光成像技术在肝癌切除术中识别微小癌灶的价值[J].中国医科大学学报, 2020,49(10):899-906.
[9] Saborido B, Darnell A, Forner A,et al.Diagnostic performance of contrast-enhanced US in small liver nodules not conclusively characterized after MRI in cirrhotic patients[J].Eur Radiol, 2025, 35(9):5771-5780.
[10] Brooks J A, Kallenbach M, Radu I P,et al.Artificial intelligence for contrast-enhanced ultrasound of the liver: a systematic review[J].Digestion, 2025, 106(3): 227-244.
[11] Tu H, Chen L, Lin J,et al.Liver cancer confirmation by contrast-enhanced ultrasound coupled with magnetic resonance imaging: case report of liver inflammation misdiagnosed as atypical liver cancer[J].J Ultrasound Med, 2020, 39(7):1453-1457.
[12] Oezsoy A, Brooks J A, Van Treeck M,et al.Weakly supervised deep learning can analyze focal liver lesions in contrast-enhanced ultrasound[J].Digestion, 2025, 106(6):502-514.
[13] Vetter M, Waldner M J, Zundler S,et al.Artificial intelligence for the classification of focal liver lesions in ultrasound-a systematic review[J].Ultraschall Med, 2023, 44(4):395-407.
[14] Liu D, Liu F, Xie X,et al.Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound[J].Eur Radiol, 2020, 30(4):2365-2376.
[15] Oezsoy A, Brooks J, Radu P,et al.SAT-469 artificial intelligence for classifying liver lesions in contrast-enhanced ultrasound[J].J Hepatol, 2024, 80(1):392-393.
[16] Li T, Wu C, Wang G, et al.Clinical value of artificial intelligence-based computer-aided diagnosis system versus contrast-enhanced ultrasound for differentiation of benign from malignant thyroid nodules in different backgrounds[J].J Ultrasound Med, 2023, 42(8):1757-1766.
[17] Wu S, Chen X, Ji Y,et al.Leveraging artificial intelligence to validate traditional biomarkers and drug targets in liver cancer recovery: a mini review[J].Front Pharmacol, 2025,17(16):1697608.
[18] Liu L, Wang L, Xu D,et al.CT image segmentation method of liver tumor based on artificial intelligence enabled medical imaging[J].Math Probl Eng, 2021, 2021,1(1):1-8.
[19] Bakrania A K, Joshi N, Zhao X,et al. Artificial intelligence in liver cancers: decoding the impact of machine learning models in clinical diagnosis of primary liver cancers and liver cancer metastases.[J].Pharmacol Res, 2023,189(5):106706.
[20] Rai H M, Yoo J, Moqurrab S A,et al.Advancements in traditional machine learning techniques for detection and diagnosis of fatal cancer types: comprehensive review of biomedical imaging datasets[J].Measurement, 2024,225(12):1-49.