Background:Low-grade myofibroblastic sarcoma (LGMS) originating from breast is rare. Existing literature comprises clinical and pathological reports, with limited information on imaging characteristics. This study reports a case of LGMS of the breast and presents its imaging characteristics, with an emphasis on those observed using contrast-enhanced magnetic resonance imaging (MRI). Case Description:A 50-year-old patient presented with a left breast mass for 1 year. One year before the presentation, the patient had palpated a mass of approximately 1.5 cm in size in the upper part of the left breast without any obvious cause. The mass was perceived to be growing slowly. There was no relevant family history of breast conditions. Physical examination revealed a hard, ill-defined, irregularly shaped, non-tender mass of approximately 3.5 cm × 3 cm in size, with poor mobility and a close connection to the deep skin. The mammography showed a high-density mass without microcalcifications and boundary wrapping. Ultrasonography showed an oval, ill-defined hypoechoic mass. The combination of mammography and ultrasound examination results ruled out the possibility of ductal carcinoma and benign fibroepithelial tumor. On contrast-enhanced MRI, the mass exhibited heterogeneous enhancement, high signal intensity on T2-weighted imaging (T2WI), high signal intensity on diffusion-weighted imaging (DWI), and a type I time-intensity curve (TIC). A core needle biopsy (CNB) suggested a spindle cell tumor. To confirm the diagnosis, the patient underwent surgical excision, and postoperative pathology confirmed LGMS of the breast. The patient subsequently received adjuvant radiotherapy. Seven months postoperatively, bone scintigraphy suggested possible metastases. Conclusions:LGMS of the breast exhibited a degree of malignancy on ultrasonography, mammography, and MRI, with the contrast-enhanced MRI showing a persistent enhancement pattern (type I TIC). A preoperative biopsy indicated a spindle cell tumor. Surgical excision remains the best diagnostic method. A thorough understanding of the imaging characteristics and biopsy results of this tumor type provides comprehensive information for formulating corresponding treatment plans.

Background: Low nuclear grade ductal carcinoma in situ (DCIS) patients can adopt proactive management strategies to avoid unnecessary surgical resection. Different personalized treatment modalities may be selected based on the expression status of molecular markers, which is also predictive of different outcomes and risks of recurrence. DCIS ultrasound findings are mostly non mass lesions, making it difficult to determine boundaries. Currently, studies have shown that models based on deep learning radiomics (DLR) have advantages in automatic recognition of tumor contours. Machine learning models based on clinical imaging features can explain the importance of imaging features. Methods: The available ultrasound data of 349 patients with pure DCIS confirmed by surgical pathology [54 low nuclear grade, 175 positive estrogen receptor (ER+), 163 positive progesterone receptor (PR+), and 81 positive human epidermal growth factor receptor 2 (HER2+)] were collected. Radiologists extracted ultrasonographic features of DCIS lesions based on the 5th Edition of Breast Imaging Reporting and Data System (BI-RADS). Patient age and BI-RADS characteristics were used to construct clinical machine learning (CML) models. The RadImageNet pretrained network was used for extracting radiomics features and as an input for DLR modeling. For training and validation datasets, 80% and 20% of the data, respectively, were used. Logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms were performed and compared for the final classification modeling. Each task used the area under the receiver operating characteristic curve (AUC) to evaluate the effectiveness of DLR and CML models. Results: In the training dataset, low nuclear grade, ER+, PR+, and HER2+ DCIS lesions accounted for 19.20%, 65.12%, 61.21%, and 30.19%, respectively; the validation set, they consisted of 19.30%, 62.50%, 57.14%, and 30.91%, respectively. In the DLR models we developed, the best AUC values for identifying features were 0.633 for identifying low nuclear grade, completed by the XGBoost Classifier of ResNet50; 0.618 for identifying ER, completed by the RF Classifier of InceptionV3; 0.755 for identifying PR, completed by the XGBoost Classifier of InceptionV3; and 0.713 for identifying HER2, completed by the LR Classifier of ResNet50. The CML models had better performance than DLR in predicting low nuclear grade, ER+, PR+, and HER2+ DCIS lesions. The best AUC values by classification were as follows: for low nuclear grade by RF classification, AUC: 0.719; for ER+ by XGBoost classification, AUC: 0.761; for PR+ by XGBoost classification, AUC: 0.780; and for HER2+ by RF classification, AUC: 0.723. Conclusions: Based on small-scale datasets, our study showed that the DLR models developed using RadImageNet pretrained network and CML models may help predict low nuclear grade, ER+, PR+, and HER2+ DCIS lesions so that patients benefit from hierarchical and personalized treatment

Extramammary masses are infrequently encountered in breast examinations. They may occur in the chest wall and axilla as neighbors of the breast. It is important to determine the nature of the lesion. However, some benign tumors, such as granular cell tumors (GCTs), also show malignant characteristics, which leads to misdiagnosis. To the best of our knowledge, multimodal ultrasound features of GCT have not been elucidated. We report two cases of women with GCTs encountered upon breast cancer screening; the tumor was not located in breast tissue. The first patient was a 37-year-old woman who presented with a slow-growing mass in the right breast and the GCT was located in the pectoralis major muscle. The second patient was a 52-year-old woman who presented with a palpable left axillary mass and the GCT was located in the axilla. Mammography failed to detect the masses in the two patients upon breast cancer screening. However, two-dimensional ultrasonography revealed a solid heterogeneous hypoechoic mass. Shear wave elastography showed that the masses had an increased hardness compared with the surrounding tissue. Further contrast-enhanced ultrasonography showed that the contrast patterns of the two masses were different. In case one, contrast-enhanced ultrasonography showed an inhomogeneous annular high enhancement, and the dynamic curve showed rapid enhancement and regression. In case two, contrast enhanced ultrasound showed slight enhancement around the lesion but no enhancement inside. Postoperative pathology confirmed that the GCT was benign in both cases. The patients showed no signs of recurrence at the 2-year follow-up. Here, we report two cases and present the multimodal ultrasonography findings of this tumor for the first time. Radiologists and surgeons should be aware of these imaging manifestations and include them in their differential diagnoses.

Background: The treatment and prognosis of breast ductal carcinoma in situ (DCIS) with and without microinvasion (MIC) are different. Ultrasound imaging shows that DCIS is a heterogeneous breast tumor with diverse manifestations. DCIS means that the cancer cells are confined in the duct without penetrating the basement membrane, MIC means that the cancer cells penetrate the basement membrane and the maximum diameter of any largest invasive lesion is less than or equal to 1 mm. This study was designed to evaluate how deep learning can be used to identify DCIS with MIC on ultrasound images. Methods: The clinical and ultrasound data of 467 consecutive inpatients diagnosed with DCIS (213 with MIC) in West China Hospital of Sichuan University were collected from January 2013 to April 2019 and randomly apportioned to training and internal validation sets. An external validation set comprised data from Sichuan Provincial People's Hospital with 101 patients (33 with MIC) collected between January 2017 and December 2019. There were 2,492 original images; 66% of these were used to establish a model, and the remaining 34% were used to evaluate the model. Three experienced breast ultrasound clinicians analyzed the ultrasound images to establish a logistic regression model. Finally, the logistic regression model and five deep learning models (ResNet-50, ResNet-101, DenseNet-161, DenseNet-169, and Inception-v3) were compared and evaluated to assess their diagnostic efficiency when identifying MIC based on ultrasound image data. Results: The characteristics of high nuclear grade (P<0.001), necrosis (P=0.006), estrogen receptor negative (ER−; P=0.003), progesterone receptor negative (PR−; P=0.001), human epidermal growth factor receptor 2 positive (HER2+; P=0.034), lymphatic metastasis (P=0.008), and calcification (P<0.001) all showed significant correlations with MIC. The Inception-v3 model achieved the best performance (P<0.05) in MIC identification. The area under the receiver operating curve (AUC) of the Inception-v3 model was 0.803 [95% confidence interval (CI): 0.709 to 0.878], with a classification accuracy of 0.766, a sensitivity of 0.767, and a specificity of 0.765. Conclusions: Deep learning can be used to identify MIC of breast DCIS from ultrasound images. Models based on Inception-v3 can provide automated detection of DCIS with MIC from ultrasound images.