Pearls and Pitfalls for Soft-Tissue and Bone Biopsies: A Cross-Institutional Review.

Management of soft-tissue and bone neoplasms depends on a definitive histologic diagnosis. Percutaneous image-guided biopsy of bone and soft-tissue tumors is a cost-effective and accurate method to obtain a histopathologic diagnosis. Biopsy requests must be approached thoughtfully to avoid numerous potential pitfalls. Hasty biopsy planning places the patient at increased risk for misdiagnosis, delayed therapy, repeated invasive procedures, and substantial morbidity. Biopsy planning begins with a thorough review of the relevant clinical history and pertinent imaging. The biopsy route must be planned in concert with the referring orthopedic oncologist to preserve limb-sparing options. Carefully selecting the most appropriate imaging modality to guide the biopsy increases the chances of reaching a definitive diagnosis. It is also critical to identify and target with expertise the part of the lesion that is most likely to yield an accurate diagnosis. Percutaneous biopsy is a safe procedure, and familiarity with preprocedural laboratory testing parameters, anticoagulation guidelines, and commonly used sedation medications minimizes the risk of complications while ensuring patient comfort. Nondiagnostic biopsy results are not infrequent and may still have value in guiding patient treatment. Awareness of the imaging manifestations of tumor recurrence is also important. The aim of this article is to provide a comprehensive review of pertinent preprocedural, periprocedural, and postprocedural considerations for bone and soft-tissue musculoskeletal biopsies.The online slide presentation from the RSNA Annual Meeting is available for this article.©RSNA, 2020.

Machine Learning for the Interventional Radiologist.

OBJECTIVE. The purpose of this article is to describe key potential areas of application of machine learning in interventional radiology. CONCLUSION. Machine learning, although in the early stages of development within the field of interventional radiology, has great potential to influence key areas such as image analysis, clinical predictive modeling, and trainee education. A proactive approach from current interventional radiologists and trainees is needed to shape future directions for machine learning and artificial intelligence.