BackgroundTo develop and validate a model based on conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) features to preoperatively predict microinvasion in breast ductal carcinoma in situ (DCIS). Patients and MethodsData from 163 patients with DCIS who underwent CUS and CEUS from the internal hospital was retrospectively collected and randomly apportioned into training and internal validation sets in a ratio of 7:3. External validation set included 56 patients with DCIS from the external hospital. Univariate and multivariate logistic regression analysis were performed to determine the independent risk factors associated with microinvasion. These factors were used to develop predictive models. The performance was evaluated through calibration, discrimination, and clinical utility. ResultsMultivariate analysis indicated that centripetal enhancement direction (odds ratio [OR], 13.268; 95% confidence interval [CI], 3.687, 47.746) and enhancement range enlarged on CEUS (OR, 4.876; 95% CI, 1.470, 16.181), lesion size of ≥20 mm (OR, 3.265; 95% CI, 1.230, 8.669) and calcification detected on CUS (OR, 5.174; 95% CI, 1.903, 14.066) were independent risk factors associated with microinvasion. The nomogram incorporated the CUS and CEUS features achieved favorable discrimination (AUCs of 0.850, 0.848, and 0.879 for the training, internal and external validation datasets), with good calibration. The nomogram outperformed the CUS model and CEUS model (all p < 0.05). Decision curve analysis confirmed that the predictive nomogram was clinically useful. ConclusionThe nomogram based on CUS and CEUS features showed promising predictive value for the preoperative identification of microinvasion in patients with DCIS. Micro AbstractPreoperative identification of microinvasion in DCIS is crucial for personalized clinical decision support. Four factors, including the enhancement direction and enhancement range features of CEUS, and the lesion size and calcification features of CUS, were selected to develop a nomogram for predicting microinvasion in DCIS. The nomogram achieved favorable discrimination, calibration and clinical potential, helping to stratify patients with DCIS for personalized care and minimize potential treatment-related harms.