Background and Objective: To evaluate the effectiveness of radiofrequency ablation (RFA) using the moving-shot technique for benign soft tissue neoplasm. Materials and Methods: This retrospective study reviewed eight patients with benign soft tissue neoplasm presenting with cosmetic concerns and/or symptomatic issues who refused surgery. Six patients had vascular malformation, including four with venous malformation and two with congenital hemangioma. The other two patients had neurofibroma. All patients underwent RFA using the moving-shot technique. Imaging and clinical follow-up were performed in all patients. Follow-up image modalities included ultrasound (US), computed tomography (CT), and magnetic resonance (MR) imaging. The volume reduction ratio (VRR), cosmetic scale (CS), and complications were evaluated. Results: Among the seven patients having received single-stage RFA, there were significant volume reductions between baseline (33.3 ± 21.2 cm3), midterm follow-up (5.1 ± 3.8 cm3, p = 0.020), and final follow-up (3.6 ± 1.4 cm3, p = 0.022) volumes. The VRR was 84.5 ± 9.2% at final follow-up. There were also significant improvements in the CS (from 3.71 to 1.57, p = 0.017). The remaining patient, in the process of a scheduled two-stage RFA, had a 33.8% VRR after the first RFA. The overall VRR among the eight patients was 77.5%. No complications or re-growth of the targeted lesions were noted during the follow-up period. Of the eight patients, two received RFA under local anesthesia, while the other six patients were under general anesthesia. Conclusions: RFA using the moving-shot technique is an effective, safe, and minimally invasive treatment for benign soft tissue neoplasms, achieving mass volume reduction within 6 months and significant esthetic improvement, either with local anesthesia or with general anesthesia under certain conditions.

Objective We aimed to develop a deep learning artificial intelligence (AI) algorithm to detect impacted animal bones on lateral neck radiographs and to assess its effectiveness for improving the interpretation of lateral neck radiographs. Methods Lateral neck radiographs were retrospectively collected for patients with animal bone impaction between January 2010 and March 2020. Radiographs were then separated into training, validation, and testing sets. A total of 1733 lateral neck radiographs were used to develop the deep learning algorithm. The testing set was assessed for the stand-alone deep learning AI algorithm and for human readers (radiologists, radiology residents, emergency physicians, ENT physicians) with and without the aid of the AI algorithm. Another radiograph cohort, collected from April 1, 2020, to June 30, 2020, was analyzed to simulate clinical application by comparing the deep learning AI algorithm with radiologists’ reports. Results In the testing set, the sensitivity, specificity, and accuracy of the AI model were 96%, 90%, and 93% respectively. Among the human readers, all physicians of different subspecialties achieved a higher accuracy with AI-assisted reading than without. In the simulation set, among the 20 cases positive for animal bones, the AI model accurately identified 3 more cases than the radiologists’ reports. Conclusion Our deep learning AI model demonstrated a higher sensitivity for detection of animal bone impaction on lateral neck radiographs without an increased false positive rate. The application of this model in a clinical setting may effectively reduce time to diagnosis, accelerate workflow, and decrease the use of CT.