Background: The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is entirely based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS category. We analysed the morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and the ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.
Methods: A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the morphological and texture features of the lesions, such as circularity, depth-to-width ratio, number of spicules, edge roughness, edge fuzziness, margin lobules, energy, entropy, mean grey level, grey level variance, grey level similarity, internal calcification and angle between the long axis of the lesion and skin(ALS) of the ROI, were calculated using grey level gradient co-occurrence matrix analysis. The differences between benign and malignant lesions of BI-RADS 4A were analysed.
Results: There were significant differences between the benign group and malignant group in margin lobules, entropy, internal calcification and ALS (P=0.013, 0.045, 0.045, 0.002, respectively). The malignant group had more margin lobules and lower entropy than the benign group, and the benign group had more internal calcification and a larger ALS than the malignant group. There were no significant differences in circularity, depth-to-width ratio, number of spicules, edge roughness, edge fuzziness, energy, mean of grey level, grey level variance, and grey level similarity between benign and malignant lesions.
Conclusion: For benign and malignant lesions of BI-RADS 4A, margin lobules and internal echo uniformity are the critical points of differentiation. Some of the characteristics of atypical benign and malignant lesions are blurry or even inverted, which may lead to a deviation of the characteristics of benign and malignant lesions.