Artificial Intelligence, Augmented Reality, and Virtual Reality Advances and Applications in Interventional Radiology.

Artificial intelligence (AI) uses computer algorithms to process and interpret data as well as perform tasks, while continuously redefining itself. Machine learning, a subset of AI, is based on reverse training in which evaluation and extraction of data occur from exposure to labeled examples. AI is capable of using neural networks to extract more complex, high-level data, even from unlabeled data sets, and better emulate, or even exceed, the human brain. Advances in AI have and will continue to revolutionize medicine, especially the field of radiology. Compared to the field of interventional radiology, AI innovations in the field of diagnostic radiology are more widely understood and used, although still with significant potential and growth on the horizon. Additionally, AI is closely related and often incorporated into the technology and programming of augmented reality, virtual reality, and radiogenomic innovations which have the potential to enhance the efficiency and accuracy of radiological diagnoses and treatment planning. There are many barriers that limit the applications of artificial intelligence applications into the clinical practice and dynamic procedures of interventional radiology. Despite these barriers to implementation, artificial intelligence in IR continues to advance and the continued development of machine learning and deep learning places interventional radiology in a unique position for exponential growth. This review describes the current and possible future applications of artificial intelligence, radiogenomics, and augmented and virtual reality in interventional radiology while also describing the challenges and limitations that must be addressed before these applications can be fully implemented into common clinical practice.

Nationwide Trends in Catheter-Directed Therapy Utilization for the Treatment of Lower Extremity Deep Vein Thrombosis in Medicare Beneficiaries.

PURPOSE: To determine overall and provider specialty trends in the use of catheter-directed therapy for lower extremity deep vein thrombosis (DVT) treatment in the Medicare population. MATERIALS AND METHODS: Using data obtained from 2007-2017 Centers for Medicare & Medicaid Services 5% research identifiable files, all claims associated with acute and chronic lower extremity DVT were identified. The annual volume of 2 services-venous percutaneous transluminal thrombectomy (current procedural terminology [CPT] code 37187) and venous infusion for thrombolysis (CPT code 37201 from 2007 to 2012 and CPT code 37212 from 2013 to 2017)-was examined for trends in DVT intervention. Utilization rates based on region and the place of service were calculated. The results were further categorized based on primary operator type (radiology, cardiology, surgery, and other). RESULTS: The total number of DVT interventions increased over time, with 4.27 service counts per 100,000 beneficiaries in 2007 increasing to 13.4 by 2017, a growth rate of 12.09%. Radiologists performed the majority of interventions each year, except in 2013, in which they performed 46.6% of interventions, whereas surgeons and cardiologists combined performed the other 53.4%. In 2017, radiologists performed 7.56 services per 100,000 beneficiaries, which was 56.8% of the total count, more than those performed by surgeons, cardiologists, and unspecified providers combined. CONCLUSIONS: Catheter-directed therapy is increasingly being used for the treatment of DVT, with its use undergoing a nearly 12-fold increase from 2007 to 2017 in the Medicare population. Radiologists remained the dominant provider of these services throughout the majority of study period, with a relative reduction in market share from 72% in 2007 to 57% in 2017.

Nationwide Trends in Tube-Related Genitourinary Interventions for Medicare Beneficiaries.

PURPOSE: To evaluate national trends in tube-related genitourinary interventions, with specific attention to primary operator specialty. METHODS: Using a 5% national sample of Medicare claims data from 2005 to 2015, all claims associated with nephrostomy tube, nephro-ureteral tube, and ureteral stent placement and exchange were identified. The annual volume of the nine billable procedures were analyzed to evaluate trends in the number of procedures performed and primary operator specialty over time. The Charleston Comorbidity Index (CCI) was used to evaluate patient comorbidities and to determine differences in patient populations treated by interventional radiologists and urologists. RESULTS: The total volume of tube-related genitourinary interventions has increased over the course of the study period, representing 455.0 services per 100,000 Medicare Fee-for-Service beneficiaries in 2005 to 607.2 services in 2015, an increase of 33.4%. Interventional radiologists performed the majority of all procedures in all procedure types and for each year (>90%) with the exception of nephro-ureteral catheter placement or ureteral stent placement, for which urologists performed the overwhelming majority of procedures each year (>85%). Interventional radiologists performed 63% of their total number of procedures on patients with a CCI = 3 or higher, and urologists performed 42% of their total number of procedures on patients with a CCI = 3 or higher (P < .01). CONCLUSION: Tube-related genitourinary interventions have demonstrated persistent growth over the 2005 to 2015 decade. Interventional radiologists are the dominant providers for the majority of these interventions compared with urologists while delivering care to a patient population with a higher number of comorbidities.

Single-Center Longitudinal Implementation of Lecture Series Based on the American College of Radiology Appropriateness Criteria for Emergency Medicine Provider Education.

RATIONALE AND OBJECTIVES: The purpose of our study was to improve awareness and knowledge of the American College of Radiology Appropriateness Criteria (ACR-AC) among Emergency Medicine (EM) residents and to assess the long-term effectiveness of this ACR-AC lecture-based series. MATERIALS AND METHODS: Ten lectures-based on the ACR-AC were given to EM residents at an academic medical center. Four of these lectures were subsequently repeated in the subsequent academic year. A prelecture quiz was given to all participants prior to each lecture and the same quiz was given after each lecture. Participants were instructed to select the most appropriate imaging study for each question. Results were analyzed with a 2-tailed paired sample t-test for the means. RESULTS: A total of 28 residents from three EM resident classes participated in the lecture-based series over the course of this 2-year study. In phase I of the study, there was statistically significant improvement in mean postlecture quiz scores compared to prelecture quiz scores (55.7% vs 80.5%, P < 0.01) for each topic, as well as within each training level, (P < 0.05). In phase II, the resident class of 2018 had the only statistically significant difference between prelecture and postlecture quiz scores (59% vs 94%, P < 0.05). EM residents further demonstrated an enduring effect at 1 year with statistically significant improvement in prelecture quiz scores during phase II compared with phase I (88% vs 50%, P < 0.05). CONCLUSIONS: This work revealed that lecture-based education on the ACR-AC, relevant to EM residents, significantly increased the participant knowledge for ordering appropriate imaging. In addition, it was evident participants retained the knowledge they acquired from these lectures during phase II 1 year later.

Primary Pulmonary Anaplastic Large Cell Lymphoma: A Rare Malignancy and Rare Cause of the Luftsichel Sign.

Primary pulmonary lymphomas are rare with primary pulmonary non-Hodgkin lymphoma accounting for only 0.3% of primary lung neoplasms. Of these, the large majority are made up of marginal zone B-cell lymphoma and diffuse large B-cell lymphoma. We present a case of a very rare primary pulmonary anaplastic large cell lymphoma presenting as the luftsichel sign on chest radiograph. Pertinent imaging and pathology findings are discussed.