Search

Objectives: To evaluate the preoperative diagnostic value of contrast-enhanced lymphatic ultrasound (CEUS) for the sentinel lymph node (SLN) status in early breast cancer., Materials and Methods: We prospectively recruited 102 consecutive patients with clinically node-negative early breast cancer from July 2021 to October 2021. All patients underwent conventional US and percutaneous CEUS examinations. The CEUS of SLNs were classified into four enhancement patterns: homogeneous (I), featured inhomogeneous (II), focal defect (III), and no enhancement (IV). The diagnostic performance of conventional US and CEUS for SLN metastasis was assessed by receiver operating characteristic (ROC) curves and decision curves., Results: A total of 78 women were enrolled in this study, including 55, 18, and 5 patients with negative axilla, 1-2, and ≥ 3 metastastic SLNs pathologically, respectively. The identification rate of SLNs by CEUS was 100%. Patterns I and II can select 91.7% (44/48) of patients with disease-free axilla, while patterns III and IV had higher percentages of metastasis (65.2%, p < 0.001 and 57.1%, p < 0.002, respectively). For the SLN metastatic burden, 100% (48/48) of patients with pattern I/II had ≤ 2 metastatic SLNs. Compared with conventional US, the CEUS enhancement patterns showed significant improvement in diagnosing metastatic SLNs (0.813 vs 0.601, p < 0.001). CEUS had greater clinical benefits and correctly reclassified 48% of metastatic SLNs (p < 0.001) without sacrificing the classification accuracy of negative SLNs (p = 0.25), and could improve prediction accuracy by 0.42 (p < 0.001)., Conclusions: CEUS demonstrated better diagnostic performance and greater clinical benefits than conventional US for the preoperative diagnosis of SLNs, showing its potential to select candidates for precluding axillary surgery in early breast cancer., Key Points: • The homogeneous and featured inhomogeneous enhancement of SLNs are highly suggestive of negative LNs, while focal defect (p < 0.001) and no enhancement (p < 0.002) patterns had higher percentages of metastasis. • The proportion of SLNs with highly suspicious signs on conventional US increases as the type of enhancement pattern increases (no suspicious signs in pattern I/II, 34.8% in pattern III, and 85.7% in pattern IV). • Compared with conventional US, CEUS improved the area under the receiver operating characteristic curve (0.813 vs. 0.601, p < 0.001) and had greater clinical benefits (IDI = 0.42, p < 0.001) for the diagnosis of axillary metastasis., (© 2022. The Author(s), under exclusive licence to European Society of Radiology.)

To develop a deep-learning system for the automatic identification of triple-negative breast cancer (TNBC) solely from ultrasound images. A total of 145 patients and 831 images were retrospectively enrolled at Peking Union College Hospital from April 2018 to March 2019. Ultrasound images and clinical information were collected accordingly. Molecular subtypes were determined from immunohistochemical (IHC) results. A CNN with VGG-based architecture was then used to predict TNBC. The model's performance was evaluated using randomized k-fold stratified cross-validation. A t-SNE analysis and saliency maps were used for model visualization. TNBC was identified in 16 of 145 (11.03%) patients. One hundred fifteen (80%) patients, 15 (10%) patients, and 15 (10%) patients formed the train, validation, and test set respectively. The deep learning system exhibits good efficacy, with an AUC of 0.86 (95% CI: 0.64, 0.95), an accuracy of 85%, a sensitivity of 86%, a specificity of 86%, and an F1-score of 0.74. In addition, the internal representation features learned by the model showed clear differentiation across molecular subtype groups. Such a deep learning system can automatically predict triple-negative breast cancer preoperatively and accurately. It may help to get to more precise and comprehensive management., (© 2022. The Author(s).)

Objectives: To establish a prediction model for evaluating the axillary lymph node (ALN) status of patients with T1/T2 invasive breast cancer based on radiomics analysis of US images of primary breast lesions., Methods: Between August 2016 and November 2018, a total of 343 patients with histologically proven malignant breast tumors were included in this study and randomly assigned to the training and validation groups at a ratio of 7:3. ALN tumor burden was defined as low (< 3 metastatic ALNs) or high (≥ 3 metastatic ALNs). Radiomics features were obtained using the PyRadiomics package, and the radiomics score was established by least absolute shrinkage and selection operator regression. A nomogram combining the breast cancer US radiomics score with patient age and lesion size was generated based on the multivariate logistic regression results., Results: In the training and validation cohorts, 29.1% (69/237) and 32.08% (34/106) of patients were pathologically diagnosed with more than 2 metastatic ALNs, respectively. The radiomics score consisted of 16 US features, and patient age and lesion diameter identified by US were included to construct the model. The AUC of the model was 0.846 (95% CI, 0.790-0.902) for the training cohort and 0.733 (95% CI, 0.613-0.852) for the validation cohort. The calibration curves showed good agreement between the predictions and observations., Conclusions: Our novel nomogram demonstrates high accuracy in predicting ALN tumor burden in breast cancer patients. We also suggest further development of PyRadiomics to improve US radiomics., Key Points: • A nomogram based on US was developed to predict ALN tumor burden (low, < 3 metastatic ALNs; high, ≥ 3 metastatic ALNs). • The nomogram could assist clinicians in evaluating treatment strategies for T1/T2 invasive breast cancer.