Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies?

Diagnostic Value of Artificial Intelligence in Minimal Breast Lesions Based on Real-Time Dynamic Ultrasound Imaging

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.

Improving ultrasound diagnostic Precision for breast cancer and adenosis with modality-specific enhancement (MSE) - Breast Net

Adenosis is a benign breast condition whose lesions can mimic breast carcinoma and is evaluated for malignancy with the Breast Imaging-Reporting and Data System (BI-RADS). We construct and validate the performance of modality-specific enhancement (MSE)-Breast Net based on multimodal ultrasound images and compare it to the BI-RADS in differentiating adenosis from breast cancer. A total of 179 patients with breast carcinoma and 229 patients with adenosis were included in this retrospective, two-institution study, then divided into a training cohort (institution I, n = 292) and a validation cohort (institution II, n = 116). In the training cohort, the final model had a significantly greater AUC (0.82; P < 0.05) than B-mode-based model (0.69, 95% CI [0.49-0.90]). In the validation cohort, the AUC of the final model was 0.81, greater than that of the BI-RADS (0.75, P < 0.05). The multimodal model outperformed the individual and bimodal models, reaching a significantly greater AUC of 0.87 (95% CI = 0.69-1.0) (P < 0.05). MSE-Breast Net, based on multimodal ultrasound images, exhibited better diagnostic performance than the BI-RADS in differentiating adenosis from breast cancer and may contribute to clinical diagnosis and treatment.