Chen Qu,1,* Fei Xia,2,* Ling Chen,1 Hong-Jian Li,2 Wei-Min Li1 

1Department of Ultrasonography, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, People’s Republic of China; 2Department of Ultrasonography, Huai’an Cancer Hospital, Huai’an, Jiangsu, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Hong-Jian Li, Department of Ultrasonography, Huai’an Cancer Hospital, Huai’an, Jiangsu, 223232, People’s Republic of China, Tel +8613511507565, Email 492938595@qq.com Wei-Min Li, Department of Ultrasonography, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, 214000, People’s Republic of China, Tel +8613912362309, Email 1005342597@qq.com

Purpose: : To explore the diagnostic value of artificial intelligence (AI)-based on real-time dynamic ultrasound imaging system for minimal breast lesions.
Patients and Methods: Minimal breast lesions with a maximum diameter of ≤ 10mm were selected in this prospective study. The ultrasound equipment and AI system were activated Simultaneously. The ultrasound imaging video is connected to the server of AI system to achieve simultaneous output of AI and ultrasound scanning. Dynamic observation of breast lesions was conducted via ultrasound. And these lesions were evaluated and graded according to the Breast Imaging Reporting and Data System (BI-RADS) classification system through deep learning (DL) algorithms in AI. Surgical pathology was taken as the gold standard, and ROC curves were drawn to determine the area under the curve (AUC) and the optimal threshold values of BI-RADS. The diagnostic efficacy was compared with the use of a BI-RADS category > 3 as the threshold for clinically intervening in diagnosing minimal breast cancers.
Results: 291 minimal breast lesions were enrolled in the study, of which 228 were benign (78.35%) and 63 were malignant (21.65%). The AUC of the ROC curve was 0.833, with the best threshold value > 4A. When using >BI-RADS 3 and >BI-RADS 4A as threshold values, the sensitivity and negative predictive value for minimal breast cancers were higher for >BI-RADS 3 than >BI-RADS 4A (100% vs 65.08%, 100% vs 89.91%, P values < 0.001). However, the corresponding specificity, positive predictive value, and accuracy were lower than those for >BI-RADS 4A (42.11% vs 85.96%, 32.31% vs 56.16%, and 54.64% vs 81.44%, P values < 0.001).
Conclusion: The AI-based real-time dynamic ultrasound imaging system shows good capacity in diagnosing minimal breast lesions, which is helpful for early diagnosis and treatment of breast cancer, and improves the prognosis of patients. However, it still results in some missed diagnoses and misdiagnoses of minimal breast cancers.

Keywords: Breast cancer, ultrasound, artificial intelligence, diagnostic