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