The peripheral nerve is demonstrated as a reticular pattern in a transverse section at high-resolution ultrasonography (US). Its echogenicity is between that of tendon and muscle. High-resolution US applied to lesions of peripheral nerves yields impressive results in that the nerve is highly differentiated from surrounding soft tissue. In cases of trauma, high-resolution US can easily differentiate between a rupture of the nerve bundle and fibroblast infiltration that results in traumatic neuroma. In cases of inflammation or compressive syndrome, high-resolution US can easily demonstrate lesion location and cause. In the evaluation of abnormal masses, high-resolution US cannot clearly differentiate neurofibromas from schwannomas but it can clarify the relationship between tumor and neural trunk and help the clinician plan treatment strategies. The authors discuss the success that can be achieved with the application of high-resolution US in the evaluation of peripheral nerve lesions. © RSNA, 2003

This study was performed to evaluate the usefulness of high-resolution grayscale and color Doppler ultrasound to distinguish benign from malignant soft-tissue masses on the basis of ultrasonographic patterns. We enrolled 398 female and 420 male patients aged 1-104 years (mean, 49.8 years). All presented with a palpable nodule or mass located superficially in the body. Each lesion was examined by grayscale and color Doppler ultrasonography to assess its echogenicity, margin, shape, composition, acoustic transmission, size and other patterns. Spectral Doppler was applied in lesions with positive color flow signals. The nature of all masses was confirmed by aspiration cytology, biopsy, surgical pathology or long-term clinical follow-up. There were a total of 693 benign and 125 malignant masses. Five malignant and 14 benign histologies (including 6 types with inflammation-related, hematoma or pseudoaneurysm) occurred that had more than 10 subjects with each histology. Eight benign histopathologies included cysts, neoplasms, vascular and miscellaneous. Five malignant histologies included metastases, osteogenic sarcomas, lymphomas, malignant fibrous histiocytomas and liposarcomas. There were significant differences (p < 0.05) between the benign and malignant soft-tissue tumors in terms of parameters including tumor margin, shape and size. Benign lesions did not have infiltrated margins or a scalloped shape and malignant tumors tended to be large. However, there was no significant difference (p > 0.05) between the benign and malignant soft-tissue tumors in terms of echogenicity, composition and color Doppler features. Ultrasonography with color Doppler imaging is a good modality for characterizing most soft-tissue masses, and tumor size > 5 cm and having infiltrated margin highly suggests malignancy.

Objective The purpose of this study was to verify whether high‐resolution and color Doppler ultrasonography could distinguish schwannomas from neurofibromas. Methods Seventy‐six tumors in 71 patients were included in this study. There were 46 patients (50 tumors) with schwannomas and 25 patients (26 tumors) with nondiffuse neurofibromas in the extremities or superficial parts of the body. Ultrasonographic examinations were performed in all patients. The tumor size, shape, location, internal echogenicity, posterior acoustic phenomenon (eg, shadowing or enhancement), capsule, relationship with the adjacent nerve, and presence of cystic components were documented. Color Doppler studies (75 lesions) and spectral Doppler studies (44 lesions) were performed. All data were analyzed with statistical software to check the significance. Results Both tumors presented as well‐defined hypoechoic nodules on ultrasonography. They were oval or lobulated, showed posterior acoustic enhancement, and were hypervascular on color Doppler ultrasonography. There was no significant difference with respect to ultrasonographic morphologic characteristics. The rates of centric, eccentric, and undetermined associations with nerves were 40%, 20%, and 40% in the schwannomas and 46.2%, 0%, and 53.8% in the neurofibromas, respectively, showing a significant difference (P = .032). There was no significant difference in the chance of cystic changes between the schwannomas (30%) and neurofibromas (23%). Conclusions No ultrasonographic finding (gray scale, color Doppler, or spectral analysis) allows differentiation between neurofibromas and schwannomas of the extremities. A nerve eccentrically entering a mass was seen only in schwannomas, and that may allow differentiation between neurofibromas and schwannomas.

Objectives The purpose of this study was to evaluate the appearance of primary peripheral soft tissue lymphoma on high‐resolution ultrasonography. Methods We retrospectively studied the sonograms of 12 patients (5 female and 7 male; age range, 12–90 years; mean, 55 years) with soft tissue lymphoma. All lesions were palpable and in the salivary glands, trunk, upper limb, or lower limb, and the diagnosis was proved by biopsy or open surgery. For each lesion, sonograms were obtained by gray scale and color Doppler ultrasonography. Results The gray scale imaging showed relatively homogeneous hypoechogenicity in 11 patients and homogeneous hyperechogenicity in 1 patient. The tumors appeared as big masses in 5 patients, nodal or confluent nodes in 3, small disseminated nodules in 2, a myositis type in 1, and a panniculitis type (homogeneous echogenic infiltrate in a subcutaneous fat layer) in 1. Conclusions In patients with a soft‐tissue mass, routine plain radiography and high‐resolution ultrasonography including color Doppler ultrasonography are recommended before further evaluation with ultrasonographically guided biopsy.

The purpose of this study was to compare the diagnostic performance and the interpretation time of breast ultrasound examination between reading without and with the artificial intelligence (AI) system as a concurrent reading aid. A fully crossed multi-reader and multi-case (MRMC) reader study was conducted. Sixteen participating physicians were recruited and retrospectively interpreted 172 breast ultrasound cases in two reading scenarios, once without and once with the AI system (BU-CAD™, TaiHao Medical Inc.) assistance for concurrent reading. Interpretations of any given case set with and without the AI system were separated by at least 5 weeks. These reading results were compared to the reference standard and the area under the LROC curve (AUCLROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for performance evaluations. The interpretation time was also compared between the unaided and aided scenarios. With the help of the AI system, the readers had higher diagnostic performance with an increase in the average AUCLROC from 0.7582 to 0.8294 with statistically significant. The sensitivity, specificity, PPV, and NPV were also improved from 95.77%, 24.07%, 44.18%, and 93.50%–98.17%, 30.67%, 46.91%, and 96.10%, respectively. Of these, the improvement in specificity reached statistical significance. The average interpretation time was significantly reduced by approximately 40% when the readers were assisted by the AI system. The concurrent-read AI system improves the diagnostic performance in detecting and diagnosing breast lesions on breast ultrasound images. In addition, the interpretation time is effectively reduced for the interpreting physicians.