Medical Extended Reality for Radiology Education and Training.

Medical Extended Reality (MXR), encompassing augmented reality (AR), virtual reality (VR), and mixed reality (MR), presents a novel paradigm in radiology training by offering immersive, interactive, and realistic learning experiences in healthcare. While traditional educational tools in the field of radiology are essential, it is necessary to capitalize on the innovative and emerging educational applications of XR technologies. At the most basic level of learning anatomy, XR has been extensively utilized with an emphasis on its superiority over conventional learning methods, especially in spatial understanding and recall. For imaging interpretation, XR has fostered the concepts of virtual reading rooms by enabling collaborative learning environments and enhancing image analysis and understanding. Moreover, image-guided interventions in interventional radiology have witnessed an uptick in XR utilization, illustrating its effectiveness in procedural training and skill acquisition for medical students and residents in a safe and risk-free environment. However, there remain several challenges and limitations for XR in radiology education, including technological, economic, ergonomic, and integration into existing curricula. This review explores the transformative potential of MXR in radiology education and training along with insights on the future of XR in radiology education, forecasting advancements in immersive simulations, AI integration for personalized learning, and the potential of cloud-based XR platforms for remote and collaborative training. In summation, MXR's burgeoning role in reshaping radiology education offers a safer, scalable, and more efficient training model that aligns with the dynamic healthcare landscape.

CASCADE: Context-Aware Data-Driven AI for Streamlined Multidisciplinary Tumor Board Recommendations in Oncology.

This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.

Transient, Image-Guided Gel-Dissection for Percutaneous Thermal Ablation.

Image-guided tumor ablative therapies are mainstay cancer treatment options but often require intra-procedural protective tissue displacement to reduce the risk of collateral damage to neighboring organs. Standard of care strategies, such as hydrodissection (fluidic injection), are limited by rapid diffusion of fluid and poor retention time, risking injury to adjacent organs, increasing cancer recurrence rates from incomplete tumor ablations, and limiting patient qualification. Herein, a "gel-dissection" technique is developed, leveraging injectable hydrogels for longer-lasting, shapeable, and transient tissue separation to empower clinicans with improved ablation operation windows and greater control. A rheological model is designed to understand and tune gel-dissection parameters. In swine models, gel-dissection achieves 24 times longer-lasting tissue separation dynamics compared to saline, with 40% less injected volume. Gel-dissection achieves anti-dependent dissection between free-floating organs in the peritoneal cavity and clinically significant thermal protection, with the potential to expand minimally invasive therapeutic techniques, especially across locoregional therapies including radiation, cryoablation, endoscopy, and surgery.

A Novel Design-Thinking, Hospital Innovation Core Certificate Curriculum for Radiologists and Trainees: Creation, Implementation, and Multiyear Results.

RATIONALE AND OBJECTIVES: Innovation is a crucial skill for physicians and researchers, yet traditional medical education does not provide instruction or experience to cultivate an innovative mindset. This study evaluates the effectiveness of a novel course implemented in an academic radiology department training program over a 5-year period designed to educate future radiologists on the fundamentals of medical innovation. MATERIALS AND METHODS: A pre- and post-course survey and examination were administered to residents who participated in the innovation course (MESH Core) from 2018 to 2022. Respondents were first evaluated on their subjective comfort level, understanding, and beliefs on innovation-related topics using a 5-point Likert-scale survey. Respondents were also administered a 21-question multiple-choice exam to test their objective knowledge of innovation-related topics. RESULTS: Thirty-eight residents participated in the survey (response rate 95%). Resident understanding, comfort and belief regarding innovation-related topics improved significantly (P < .0001) on all nine Likert-scale questions after the course. After the course, a significant majority of residents either agreed or strongly agreed that technological innovation should be a core competency for the residency curriculum, and that a workshop to prototype their ideas would be beneficial. Performance on the course exam showed significant improvement (48% vs 86%, P < .0001). The overall course experience was rated 5 out of 5 by all participants. CONCLUSION: MESH Core demonstrates long-term success in educating future radiologists on the basic concepts of medical technological innovation. Years later, residents used the knowledge and experience gained from MESH Core to successfully pursue their own inventions and innovative projects. This innovation model may serve as an approach for other institutions to implement training in this domain.

Virtual reading room for diagnostic radiology.

RATIONALE AND OBJECTIVE: To assess the perceptions of radiology staff regarding the role of virtual reality technology in diagnostic radiology after using a virtual reality (VR) headset METHODS: Participants completed a pre-study questionnaire assessing their familiarity with VR technology and its potential role in radiology. Using a VR headset, participants entered a simulated reading room (SieVRt, Luxsonic Technologies) with three large virtual monitors. They were able to view plain radiographs, ultrasound, CT, and MRI images and pull up and compare multiple images simultaneously. They then completed a post-study questionnaire to re-assess their perception about the role of VR technology for diagnostic radiology. RESULTS: Fifteen participants were enrolled, with 33.3 % attendings, 40 % fellows, and 26.7 % residents. Pre-study, 60 % reported they were "not familiar" with VR technology and 66.7 % had never used it. On a 1 to 5 scale, the median perceived likelihood of VR having a role in radiology significantly increased from 3 (IQR 2-3) pre-study to 4 (IQR 4-4) post-study; p = 0.014. Image contrast and resolution were adequate according to most participants, with 53.3 % strongly agreeing and 33.3 % agreeing. The headset was comfortable for 73.3 % and did not induce nausea in any participant. Confidence in VR technology improved after using the headset for 80 %. According to 80 %, future VR technology could replace a PACS workstation. DISCUSSION: Radiologists' perception regarding the role of virtual reality in diagnostic interpretation improves after a hands-on trial of the technology, and VR has the potential to replace a traditional workstation in certain situations.

Retrieval of a Greenfield Inferior Vena Cava Filter Indwelling for 29 Years.

Inferior vena cava (IVC) filters are used to prevent fatal and nonfatal pulmonary embolism in patients who otherwise cannot receive anticoagulation for venous thrombosis. While generally safe and effective, complications can arise, especially after prolonged implantation. Timely retrieval is essential once the indication for insertion has resolved. However, encountering patients with long-standing embedded filters is not uncommon. This case report discusses the successful retrieval of a permanent Greenfield IVC filter after 29 years.

Percutaneous treatment of renal tumours.

Image-guided ablation is an accepted treatment option in the management of renal cell carcinoma. Percutaneous renal ablation offers the possibility of minimally invasive treatment while attempting to preserve renal function. Over the past several years there have been advances in tools and techniques that have improved procedure safety and patient outcomes. This article provides an updated comprehensive review of percutaneous ablation in the management of renal cell carcinoma.

Machine Learning-Based Radiomic Features on Pre-Ablation MRI as Predictors of Pathologic Response in Patients with Hepatocellular Carcinoma Who Underwent Hepatic Transplant.

BACKGROUND: The aim was to investigate the role of pre-ablation tumor radiomics in predicting pathologic treatment response in patients with early-stage hepatocellular carcinoma (HCC) who underwent liver transplant. METHODS: Using data collected from 2005-2015, we included adult patients who (1) had a contrast-enhanced MRI within 3 months prior to ablation therapy and (2) underwent liver transplantation. Demographics were obtained for each patient. The treated hepatic tumor volume was manually segmented on the arterial phase T1 MRI images. A vector with 112 radiomic features (shape, first-order, and texture) was extracted from each tumor. Feature selection was employed through minimum redundancy and maximum relevance using a training set. A random forest model was developed based on top radiomic and demographic features. Model performance was evaluated by ROC analysis. SHAP plots were constructed in order to visualize feature importance in model predictions. RESULTS: Ninety-seven patients (117 tumors, 31 (32%) microwave ablation, 66 (68%) radiofrequency ablation) were included. The mean model for end-stage liver disease (MELD) score was 10.5 ± 3. The mean follow-up time was 336.2 ± 179 days. Complete response on pathology review was achieved in 62% of patients at the time of transplant. Incomplete pathologic response was associated with four features: two first-order and two GLRM features using univariate logistic regression analysis (p < 0.05). The random forest model included two radiomic features (diagnostics maximum and first-order maximum) and four clinical features (pre-procedure creatinine, pre-procedure albumin, age, and gender) achieving an AUC of 0.83, a sensitivity of 82%, a specificity of 67%, a PPV of 69%, and an NPV of 80%. CONCLUSIONS: Pre-ablation MRI radiomics could act as a valuable imaging biomarker for the prediction of tumor pathologic response in patients with HCC.

The double-balloon technique: a safe and effective adjunctive technique in patients undergoing arterial therapy for hepatic malignancies with vascular supply not amenable to selective administration.

PURPOSE: During catheter directed intraarterial therapy for liver lesions, challenging hepatic vascular anatomy can sometimes prevent selective administration of treatment delivery to liver tumors leading to increased toxicity to normal liver parenchyma. The objective of this study is to describe a variation of the double balloon technique that isolates the feeding artery to liver tumors proximally and distally to provide treatment delivery in lesions that cannot be otherwise selected. MATERIALS AND METHODS: An IRB-approved retrospective review of 7 patients who had undergone either radioembolization, chemoembolization, or bland embolization and the double balloon technique was employed. The devices used for flow augmentation were two 2.1 French balloon microcatheters (Sniper™, Embolx). One balloon was inflated distal to target vessel and the second was inflated proximal to protect from reflux. RESULTS: DEB-TACE was performed in 3 cases, 90Y was performed in 4, and bland embolization was performed in the last patient. There were no adverse effects from the procedure or clinically evident effects from non-target embolization. Mean follow up time was 286.4 +/- 200.1 days. Six of the 7 patients are alive. One patient passed away on post-procedure day 121 from septic shock unrelated to the procedure. One patient was bridged to transplant with an additional TACE of a separate lesion. CONCLUSION: Double-balloon technique for patients undergoing 90Y or chemoembolization is a safe adjunctive technique for super selective treatment of hepatic lesions where direct selection via catheter is not feasible. This may increase the range of lesions that can be both safely and effectively treated by catheter directed therapies.

Let the EHR Talk Loudly: An EHR-Connected Verbal Surgical Safety Checklist for Medical Procedures in the Intensive Care Unit.

OBJECTIVES: The purpose of this study was to test the accuracy and user acceptance of an electronic health records (EHR)-connected verbal surgical safety checklist in the intensive care unit (ICU). METHODS: An EHR-connected verbal checklist software was deployed in our ICU between January 2019 and June 2019. The software, loaded on a mobile tablet, loudly verbalized clinical information from the EHR in the form of a time-out checklist. The accuracy of the information delivered was compared with up-to-date clinical data in the EHR in 300 patients. User acceptance was assessed using survey instruments. RESULTS: The software accurately verbalized patient demographics in 100% (300/300) of tested cases. Concordance rates with real-time values in the EHR for the following variables were calculated: allergies 98.6% (296/300), international normalized ratio 97.6% (293/300), and platelets 91.6% (275/300). Surveys showed that 41.2% (7/17) of users preferred current standard EHR time-outs, 17.6% (3/17) preferred verbalization software, 35.3% (6/17) preferred neither, and 5.9% (1/17) wanted both. When asked if EHR-connected verbalization software should officially replace the current standard EHR checklists, 76.5% (13/17) supported the idea. CONCLUSIONS: An EHR-connected verbal surgical safety checklist software can leverage information in the EHR to help with workflow and patient safety. This study shows that the software can verbally deliver clinical information with great accuracy and that most ICU staff would support replacing current time-out processes.

Microwave Ablation as Bridging Therapy for Patients with Hepatocellular Carcinoma Awaiting Liver Transplant: A Single Center Experience.

PURPOSE: To determine the pathologic response of computed tomography-guided percutaneous microwave ablation as bridging therapy for patients with hepatocellular carcinoma awaiting liver transplant, and its subsequent effect on survival. MATERIALS AND METHODS: A single-center retrospective analysis was conducted on 62 patients (M:F = 50:12) with mean age of 59.6 years ± 7.2 months (SD). Sixty-four total MWA procedures were performed for hepatocellular carcinomas within Milan criteria as bridging therapy to subsequent orthotopic liver transplant between August 2014 and September 2018. The pathology reports of the explanted livers were reviewed to assess for residual disease. Residual disease was categorized as complete or incomplete necrosis. Patient demographics, tumor/procedural characteristics, and laboratory values were evaluated. Survival from time of ablation and time of transplantation were recorded and compared between cohorts using log rank tests. RESULTS: The mean tumor size was 2.4 cm ± 0.7 cm (SD), (range = 1-4.6 cm). 32 (50%) cases required hydrodissection. Histopathologic necrosis was seen in 66% of cases at time of liver transplantation. Median time to liver transplant post-MWA was 12.6 months. [IQR = 8.6-14.8 months]. The median survival from ablation was 60.8 months [IQR = 45.5-73.7 months], and the median survival from transplant was 49.3 months [IQR = 33.7-60.1 months]. There was no significant difference in survival for patients with complete versus incomplete necrosis from ablation or liver transplant (p = 0.49, p = 0.46, respectively). CONCLUSIONS: Computed tomography-guided percutaneous microwave ablation is an effective bridge to orthotopic liver transplantation for patients with hepatocellular carcinoma. CEBM LEVEL OF EVIDENCE: Level 3, non-randomized controlled cohort study/follow-up study.

Role of Machine Learning and Artificial Intelligence in Interventional Oncology.

PURPOSE OF REVIEW: The purpose of this review is to highlight the current role of machine learning and artificial intelligence and in the field of interventional oncology. RECENT FINDINGS: With advancements in technology, there is a significant amount of research regarding the application of artificial intelligence and machine learning in medicine. Interventional oncology is a field that can benefit greatly from this research through enhanced image analysis and intraprocedural guidance. These software developments can increase detection of cancers through routine screening and improve diagnostic accuracy in classifying tumors. They may also aid in selecting the most effective treatment for the patient by predicting outcomes based on a combination of both clinical and radiologic factors. Furthermore, machine learning and artificial intelligence can advance intraprocedural guidance for the interventional oncologist through more accurate needle tracking and image fusion technology. This minimizes damage to nearby healthy tissue and maximizes treatment of the tumor. While there are several exciting developments, this review also discusses limitations before incorporating machine learning and artificial intelligence in the field of interventional oncology. These include data capture and processing, lack of transparency among developers, validating models, integrating workflow, and ethical challenged. In summary, machine learning and artificial intelligence have the potential to positively impact interventional oncologists and how they provide cancer care treatments.

Infection Control in Interventional Radiology During the COVID-19 Era.

The COVID-19 pandemic has challenged the capacity of interventional radiology departments worldwide to effectively treat COVID-19 and non-COVID-19 patients while preventing disease transmission among patients and healthcare workers. In this review, we describe the various data driven infection control measures implemented by the interventional radiology department of a large tertiary care center in the United States including the use and novel re-use of personal protective equipment, COVID-19 testing strategies, modifications in procedural workflows and the leveraging of telehealth visits. Herein, we provide effective triage, procedural, and management algorithms that may guide other interventional radiology departments during the ongoing COVID-19 pandemic and in future infectious disease outbreaks.

Thermal Ablation, Embolization, and Selective Internal Radiation Therapy Combined with Checkpoint Inhibitor Cancer Immunotherapy: Safety Analysis.

PURPOSE: To describe interventional oncology therapies combined with immune checkpoint inhibitor (ICI) therapy targeting the programmed death 1 pathway in patients with different neoplasms. MATERIALS AND METHODS: This was a retrospective cohort study of patients who underwent tumor-directed thermal ablation, embolization, or selective internal radiation therapy (SIRT) between January 1, 2011, and May 1, 2019, and received anti-programmed death 1/PD-L1 agents ≤ 90 days before or ≤ 30 days after the interventional procedure. Immune-related adverse events (irAEs) and procedural complications ≤ 90 days after the procedure were graded according to the Common Terminology Criteria for Adverse Events version 5.0. The study included 65 eligible patients (49% female; age 63 years ± 11.1). The most common tumors were metastatic melanoma (n = 28) and non-small cell lung cancer (NSCLC) (n = 12). Patients underwent 78 procedures (12 patients underwent > 1 procedure), most frequently SIRT (35.9%) and cryoablation (28.2%). The most common target organs were liver (46.2%), bone (24.4%), and lung (9.0%). Most patients received ICI monotherapy with pembrolizumab (n = 30), nivolumab (n = 22), and atezolizumab (n = 6); 7 patients received ipilimumab and nivolumab. RESULTS: Seven (10.8%) patients experienced an irAE (71.4% grade 1-2), mostly affecting the skin. Median time to irAE was 33 days (interquartile range, 19-38 days). Five irAEs occurred in patients with melanoma, and no irAEs occurred in patients with NSCLC. Management required corticosteroids (n = 3) and immunotherapy discontinuation (n = 1); all irAEs resolved to grade ≤ 1. There were 4 intraprocedural and 32 postprocedural complications (77.8% grade < 3). No grade 5 irAEs and/or procedural complications occurred. CONCLUSIONS: No unmanageable or unanticipated toxicities occurred within 90 days after interventional oncology therapies combined with ICIs.

Infrastructure Design: A Critical Element in the Care of the Patient With Obesity.

ABSTRACT: The worldwide rate of obesity continues to rise, causing healthcare systems to morph to meet the demands posed by the concomitant increase in comorbidities associated with this condition. Increasing patient weight imposes its own constraints on the safety of patients and providers; therefore, a sound healthcare facility infrastructure is required to properly address the medical needs of patients with obesity. Currently, most healthcare systems-in their attitudes, equipment, and facility design-are ill equipped to meet the needs of this epidemic. In this article, we discuss the facilities and equipment design considerations in providing medical care to patients with obesity. Extending beyond the physical plant, we also touch on organizational elements that enable the healthcare provider to safely care for this challenging patient population. The rising prevalence and disease burden of excess adiposity highlight the obligation to recognize that the design needs common to all of our patients must include the particular needs of the patient with obesity.

Impact of Body Mass Index on Perioperative Complications and Oncologic Outcomes in Patients Undergoing Thermal Ablation for Renal Cell Carcinoma.

PURPOSE: To determine effect of body mass index (BMI) on safety and cancer-related outcomes of thermal ablation for renal cell carcinoma (RRC). MATERIALS AND METHODS: This retrospective study evaluated 427 patients (287 men and 140 women; mean [SD] age, 72 [12] y) who were treated with thermal ablation for RCC between October 2006 and December 2017. Patients were stratified by BMI into 3 categories: normal weight (18.5-24.9 kg/m2), overweight (25-29.9 kg/m2), and obese (≥ 30 kg/m2). Of 427 patients, 71 (16%) were normal weight, 157 (37%) were overweight, and 199 (47%) were obese. Complication rates, local recurrence, and residual disease were compared in the 3 cohorts. RESULTS: No differences in technical success between normal-weight, overweight, and obese patients were identified (P = .72). Primary technique efficacy rates for normal-weight, overweight, and obese patients were 91%, 94%, and 93% (P = .71). There was no significant difference in RCC specific-free survival, disease-free survival, and metastasis-free survival between obese, overweight, and normal-weight groups (P = .72, P = .43, P = .99). Complication rates between the 3 cohorts were similar (normal weight 4%, overweight 2%, obese 3%; P = .71). CONCLUSIONS: CT-guided renal ablation is safe, feasible, and effective regardless of BMI.

Thermal Ablation of Renal Cell Carcinoma in Patients With Morbid Obesity: Assessment of Technique, Safety, and Oncologic Outcomes.

BACKGROUND. Obesity is a worldwide problem that impacts patient health as well as the morbidity associated with surgical procedures. Thus, patients with morbid obesity may not be suitable candidates for curative surgery. For this patient population, thermal ablation may be an effective alternative to nephrectomy. OBJECTIVE. The purpose of this study was to determine the feasibility, oncologic outcomes, and survival of patients with morbid obesity and renal cell carcinoma treated with thermal ablation. MATERIALS AND METHODS. A retrospective analysis was performed of 107 patients treated with CT-guided renal ablation for clinical T1 renal cell carcinoma between February 2005 and December 2017. Patients were stratified into two cohorts on body mass index of ≥ 40 kg/m2 (morbidly obese) and body mass index (weight in kilograms divided by the square of height in meters) of ≥ 40 (morbidly obese) and 18.5-24.9 (normal weight). Anesthetic and radiation dosages, procedure time, residual disease, and local recurrence, and adverse events were analyzed between the two groups. Kaplan-Meier statistics were used to evaluate cancer-related outcomes for each group. RESULTS. Thirty-four patients were morbidly obese, and 73 patients had normal weight. Morbid obesity was associated with longer procedural duration (p = .001), sedative doses (p = .002) and radiation exposure (p = .001) than normal weight. Hematomas were more prevalent in patients with morbid obesity than in those of normal weight (p = .01), but treatment efficacy and local recurrences were comparable with those for normal-weight individuals (p = .81 and p = .12, respectively). Cancer-related outcomes were equivalent between the two groups based on 5 years of imaging observation data. CONCLUSION. CT-guided thermal ablation remains technically feasible, well-tolerated, and effective in patients with morbid obesity and renal cell carcinoma, with the caveat of increased risk of perinephric hematoma, anesthesia dose, and radiation exposure. CLINICAL IMPACT. CT-guided thermal ablation can be considered a safe and effective treatment for renal cell carcinoma in patients with morbid obesity.

Transjugular Intrahepatic Portosystemic Shunt Placement for Portal Hypertension: Meta-Analysis of Safety and Efficacy of 8 mm vs. 10 mm Stents.

INTRODUCTION: Hepatic encephalopathy (HE) following transjugular intrahepatic portosystemic shunt (TIPS) placement remains a leading adverse event. Controversy remains regarding the optimal stent diameter given that smaller stents may decrease the amount of shunted blood and decrease the risk of HE, but stent patency and/or clinical adequacy of portal decompression may also be affected. We aim to provide meta-analysis-based evidence regarding the safety and efficacy of 8 mm vs. 10 mm stents during TIPS placement. METHODS: PubMed, Embase, Cochrane Library, and Web of Science were searched for studies comparing 8 mm and 10 mm stents during TIPS placement for portal hypertension decompression in cirrhotic patients. Randomized controlled trials and cohort studies were prioritized for inclusion. Overall evaluation of quality and bias for each study was performed. The outcomes assessed were the prevalence of HE, rebleeding or failure to control refractory ascites, and overall survival. Subgroup analysis based on TIPS indication was conducted. RESULTS: Five studies with a total number of 489 cirrhotic patients were identified. The pooled hazard ratio (HR) of post-TIPS HE was significantly lower in patients in the 8 mm stent group than in the 10 mm stent group (HR: 0.68, 95% CI: 0.51~0.92, p value < 0.0001). The combined HR of post-TIPS rebleeding/the need for paracentesis was significantly higher in patients in the 8 mm stent group than in the 10 mm stent group (HR: 1.76, 95% CI: 1.22~2.55, p value < 0.0001). There was no statistically significant difference in the overall survival between the 8 mm and 10 mm stent groups. The combined risk of HE in the variceal bleeding subgroup was statistically lower (HR: 0.52, CI: 0.34-0.80) with an 8 mm stent compared with a 10 mm stent. The combined risk of both rebleeding/paracentesis and survival was not statistically significant between 8 mm and 10 mm stent use in subgroup analysis. CONCLUSION: 8 mm stents during TIPS placement are associated with a significant lower risk of HE compared to 10 mm stents (32% decreased risk), as well as a 76% increased risk of rebleeding/paracentesis. Meta-analysis results suggest that there is not one superior stent choice for all clinical scenarios and that the TIPS indication of variceal bleeding or refractory ascites might have different appropriate selection of the shunt diameter.