Ultrasound imaging characteristics, including multiple occurrences, shape, intrinsic cystic change, and the grade and distribution of tumor vessels, can be used to differentiate pleomorphic adenomas from Warthin's tumors.

Although rare and accounting for less than 1% of all breast cancers, the incidence of breast cancer in men has increased by 26% over the past few decades. Very little has been reported on the sonographic appearance of benign and malignant male breast conditions. The aim of this study was to describe the ultrasonographic features of male breast disease and the value of ultrasound in the evaluation of male breast disease. Between December 2006 and October 2014, ultrasound examinations were performed in 560 male patients presenting with enlargement of, pain in, and/or a lump in the breast. One hundred and thirty-six patients (24.3%) underwent surgical excision, and 424 patients (75.7%) were diagnosed by ultrasound. Their ultrasonographic features were retrospectively evaluated. The final diagnoses were gynecomastia (n = 537), primary breast cancer (n = 9), lipoma (n = 7), chronic mastitis (n = 6), and fibroadenoma (n = 1). Of the 560 lesions, 356 (63.6%) were classified as Breast Imaging Reporting and Data System (BI-RADS) category 2, 191 (34.1%) were classified as BI-RADS category 3, and 13 (2.3%) were classified as BI-RADS 4 or 5. The sensitivity, specificity, PPV, NPV, and accuracy of the detection of malignant breast masses according to ultrasound were 100%, 99.3%, 69.2%, 100%, and 97.7% respectively. The sonographic patterns of gynecomastia were nodular (n = 131, 24.4%), dendritic (n = 50, 9.3%), and diffuse glandular (n = 356, 66.3%). Color Doppler flow imaging revealed hypervascularity in five of these malignant masses, moderate vascularity in two of the masses, and mild vascularity in the remaining two masses. Other diseases included in the study are also described. Ultrasonography (US) is useful in the diagnosis of male breast diseases, especially in differentiating cancer from benign lesions.

Background: Significant differences exist in classification outcomes for radiologists using ultrasonography-based breast imaging-reporting and data systems for diagnosing category 3–5 (BI-RADS-US 3–5) breast nodules, due to a lack of clear and distinguishing image features. As such, this study investigates the use of a transformer-based computer-aided diagnosis (CAD) model for improved BI-RADS-US 3–5 classification consistency.Methods: Five radiologists independently performed BI-RADS-US annotations on a breast ultrasonography image set collected from 20 hospitals in China. The data were divided into training, validation, testing, and sampling sets. The trained transformer-based CAD model was then used to classify test images, for which sensitivity, specificity, and accuracy were calculated. Variations in these metrics among the 5 radiologists were analyzed by referencing BI-RADS-US classification results for the sampling test set, provided by CAD, to determine whether classification consistency (the kappa value)，sensitivity, specificity, and accuracy had improved.Results: Classification accuracy for the CAD model applied to the test set was 95.7% for category 3 nodules, 97.6% for category 4A nodules, 95.60% for category 4B nodules, 94.2% for category 4C nodules, and 97.5% for category 5 nodules. Adjustments were made to 1,583 nodules, as 905 were classified to a higher category and 678 to a lower category in the sampling test set. As a result, the accuracy, sensitivity, and specificity of classification by each radiologist improved, with the consistency (kappa values) for all radiologists increasing to >0.60.Conclusions: The proposed transformer-based CAD model improved BI-RADS-US 3–5 nodule classification by individual radiologists and increased diagnostic consistency.