Comparison of CT Perfusion Software Packages for Thrombectomy Eligibility.

INTRODUCTION: Computed tomography perfusion (CTP) has played an important role in patient selection for mechanical thrombectomy (MT) in acute ischemic stroke. We aimed to investigate the agreement between perfusion parametric maps of 3 software packages - RAPID (RapidAI-IschemaView), Viz CTP(Viz.ai), and e-CTP(Brainomix) - in estimating baseline ischemic core volumes of near completely/completely reperfused patients. METHODS: We retrospectively reviewed a prospectively maintained MT database to identify patients with anterior circulation large vessel occlusion strokes (LVOS) involving the internal carotid artery or middle cerebral artery M1-segment and interpretable CTP maps treated during September 2018 to November 2019. A subset of patients with near-complete/complete reperfusion (expanded thrombolysis in cerebral infarction [eTICI] 2c-3) was used to compare the pre-procedural prediction of final infarct volumes. RESULTS: In this analysis of 242 patients with LVOS, RAPID and Viz CTP relative cerebral blood flow (rCBF) < 30% values had substantial agreement (ρ = 0.767 [95% confidence interval [CI] = 0.71-0.81]) as well as for RAPID and e-CTP (ρ = 0.668 [95% CI = 0.61-0.71]). Excellent agreement was seen for time to maximum of the residue function (Tmax ) > 6 seconds between RAPID and Viz CTP (ρ = 0.811 [95% CI = 0.76-0.84]) and substantial for RAPID and e-CTP (ρ = 0.749 [95% CI = 0.69-0.79]). Final infarct volume (FIV) prediction (n = 136) was substantial in all 3 packages (RAPID ρ = 0.744; Viz CTP ρ = 0.711; and e-CTP ρ = 0.600). CONCLUSION: Perfusion parametric maps of the RAPID, Viz CTP, and e-CTP software have substantial agreement in predicting final infarct volume in near-completely/completely reperfused patients. ANN NEUROL 2023;94:848-855.

Intellectual property: A primer for radiologists.

Typically the creative product of the mind, intellectual property often forms the basis of a new product, service line, or company. Intellectual property law is complicated and nuanced, and poorly understood by many physicians, innovators, and entrepreneurs. Successfully navigating the process of intellectual property protection is critical in facilitating the translation of innovation into clinical practice. We define intellectual property and common terms used in intellectual property law and offer justification for the importance of intellectual property protections. We additionally highlight resources to assist radiologists with intellectual property protection and outline basic guidelines to successfully initiate discussions around intellectual property with third party vendors and consultants. SUMMARY: Proactive intellectual property protection is critically important for radiologist innovators seeking to bring new ideas to the marketplace.

Development and Implementation of an Integrated Imaging Informatics Track for Radiology Residents: Our 3-Year Experience.

RATIONALE AND OBJECTIVES: Imaging Informatics is an emerging and fast-evolving field that encompasses the management of information during all steps of the imaging value chain. With many information technology tools being essential to the radiologists' day-to-day work, there is an increasing need for qualified professionals with clinical background, technology expertise, and leadership skills. To answer this, we describe our experience in the development and implementation of an Integrated Imaging Informatics Track (I3T) for radiology residents at our institution. MATERIALS AND METHODS: The I3T was created by a resident-driven initiative funded by an intradepartmental resident grant. Its curriculum is delivered through a combination of monthly small group discussions, operational meetings, recommended readings, lectures, and early exposure to the National Imaging Informatics Course. The track is steered and managed by the I3T Committee, including trainees and faculty advisors. Up to two first-year residents are selected annually based on their curriculum vitae and an interest application. Successful completion of the program requires submission of a capstone project and at least one academic deliverable (national meeting presentation, poster, exhibit, manuscript and/or grant). RESULTS: In our three-year experience, the seven I3T radiology residents have reported a total of 58 scholarly activities related to Imaging Informatics. I3T residents have assumed leadership roles within our organization and nationally. All residents have successfully carried out their clinical responsibilities. CONCLUSION: We have developed and implemented an I3T for radiology residents at our institution. These residents have been successful in their clinical, scholarship and leadership pursuits.

Increasing Utilization of Emergency Department Neuroimaging From 2007 Through 2017.

BACKGROUND. The volume of emergency department (ED) visits and the number of neuroimaging examinations have increased since the start of the century. Little is known about this growth in the commercially insured and Medicare Advantage populations. OBJECTIVE. The purpose of our study was to evaluate changing ED utilization of neuroimaging from 2007 through 2017 in both commercially insured and Medicare Advantage enrollees. METHODS. Using patient-level claims from Optum's deidentified Clinformatics Data Mart database, which annually includes approximately 12-14 million commercial and Medicare Advantage health plan enrollees, annual ED utilization rates of head CT, head MRI, head CTA, neck CTA, head MRA, neck MRA, and carotid duplex ultrasound (US) were assessed from 2007 through 2017. To account for an aging sample population, utilization rates were adjusted using annual relative proportions of age groups and stratified by patient demographics, payer type, and provider state. RESULTS. Between 2007 and 2017, age-adjusted ED neuroimaging utilization rates per 1000 ED visits increased 72% overall (compound annual growth rate [CAGR], 5%). This overall increase corresponded to an increase of 69% for head CT (CAGR, 5%), 67% for head MRI (CAGR, 5%), 1100% for head CTA (CAGR, 25%), 1300% for neck CTA (CAGR, 27%), 36% for head MRA (CAGR, 3%), and 52% for neck MRA (CAGR, 4%) and to a decrease of 8% for carotid duplex US (CAGR, -1%). The utilization of head CT and CTA of the head and neck per 1000 ED visits increased in enrollees 65 years old or older by 48% (CAGR, 4%) and 1011% (CAGR, 24%). CONCLUSION. Neuroimaging utilization in the ED grew considerably between 2007 and 2017, with growth of head and neck CTA far outpacing the growth of other modalities. Unenhanced head CT remains by far the dominant ED neuroimaging examination. CLINICAL IMPACT. The rapid growth of head and neck CTA observed in the fee-for-service Medicare population is also observed in the commercially insured and Medicare Advantage populations. The appropriateness of this growth should be monitored as the indications for CTA expand.

Diagnostic Performance of Computed Tomography Angiography and Computed Tomography Perfusion Tissue Time-to-Maximum in Vasospasm Following Aneurysmal Subarachnoid Hemorrhage.

Background Vasospasm is a treatable cause of deterioration following aneurysmal subarachnoid hemorrhage. Cerebral computed tomography perfusion mean transit times have been proposed as a predictor of vasospasm but suffer from well-known technical limitations. We evaluated fully automated, thresholded time-to-maxima of the tissue residue function (Tmax) for determination of vasospasm following aneurysmal subarachnoid hemorrhage. Methods and Results Retrospective analysis of 540 arterial segments from 36 encounters in 31 consecutive patients with aneurysmal subarachnoid hemorrhage undergoing computed tomography angiography (CTA), computed tomography perfusion, and digital subtraction angiography (DSA) within 24 hours. Tmax at 4, 6, 8, and 10 s was generated using RAPID (iSchemaView Inc., Menlo Park, CA). Dual-reader CTA and computed tomography perfusion interpretations were compared for patients with and without vasospasm on DSA (DSA+ and DSA-). Logistic regression models were developed using CTA and Tmax as input predictors and DSA vasospasm as outcome in adjusted and unadjusted models. Imaging studies from all 31 subjects (mean age 47.3±11.1, 77% female, 65% with single aneurysm with mean size of 6.0±2.9 mm) were included. Vasospasm was identified in 42 segments on DSA and 59 segments on CTA, with significant associations across individual vessel segments (P<0.001). In adjusted analyses, DSA vasospasm was associated with CTA (odds ratio [OR], 2.43; 95% CI, 0.94-6.32; P=0.068) as well as territory-specific Tmax>6 seconds delays (OR, 3.57; 95% CI, 1.36-9.35; P=0.009). Sensitivity/specificity for DSA vasospasm was 31%/91% for CTA, 26%/89% for Tmax>6 seconds, and 12%/99% for CTA+Tmax>6 seconds. Conclusions CTA and Tmax offer high specificity for presence of vasospasm; their utility, even in combination, as screening tests is, however, limited by poor sensitivity.

Ghost infarct core following endovascular reperfusion: A risk for computed tomography perfusion misguided selection in stroke.

BACKGROUND: Computed tomography perfusion (CTP) has been increasingly used for patient selection in mechanical thrombectomy for stroke. However, previous studies suggested that CTP might overestimate the infarct size. The term ghost infarct core (GIC) has been used to describe an overestimation of the final infarct volumes by pre-treatment CTP of >10 ml. AIM: We sought to study the frequency and predictors of GIC. METHODS: A prospectively collected mechanical thrombectomy database at a comprehensive stroke center between September 2010 and August 2020 was reviewed. Patients were included if they had a successful reperfusion (mTICI2b-3), a pre-procedure CTP, and final infarct volume measured on follow-up magnetic resonance imaging. Uni- and multivariable analyses were performed to identify predictors of GIC. RESULTS: Among 923 eligible patients (median [IQR] age, 64 [55-75] years; NIHSS, 16 [11-21]; onset to reperfusion time, 436.5 [286-744.5] min), GIC was identified in 77 (8.3%) of the overall patients and in 14% (47/335) of those reperfused within 6 h of symptom onset. The median overestimation volume was 23.2 [16.4-38.3] mL. GIC was associated with higher NIHSS score, larger areas of infarct core and tissue at risk on CTP, unfavorable collateral scores, and shorter times from onset to image acquisition and to reperfusion as compared to non-GIC. Patients with GIC had smaller median final infarct volumes (10.7 vs. 27.1 ml, p < 0.001), higher chances of functional independence (76.2% vs. 55.5%, adjusted odds ratio (aOR) 3.829, 95% CI [1.505-9.737], p = 0.005), lower disability (one-point-mRS improvement, aOR 1.761, 95% CI [1.044-2.981], p = 0.03), and lower mortality (6.3% vs. 15%, aOR 0.119, 95% CI [0.014-0.984], p = 0.048) at 90 days. On multivariable analysis, time from onset to reperfusion ≤6 h (OR 3.184, 95% CI [1.743-5.815], p < 0.001), poor collaterals (OR 2.688, 95% CI [1.466-4.931], p = 0.001), and higher NIHSS score (OR 1.060, 95% CI [1.010-1.113], p = 0.018) were independent predictors of GIC. CONCLUSION: GIC is a relatively common entity, particularly in patients with poor collateral status, higher baseline NIHSS score, and early presentation, and is associated with more favorable outcomes. Patients should not be excluded from reperfusion therapies on the sole basis of CTP findings, especially in the early window.

Data Sharing of Imaging in an Evolving Health Care World: Report of the ACR Data Sharing Workgroup, Part 2: Annotation, Curation, and Contracting.

A core principle of ethical data sharing is maintaining the security and anonymity of the data, and care must be taken to ensure medical records and images cannot be reidentified to be traced back to patients or misconstrued as a breach in the trust between health care providers and patients. Once those principles have been observed, those seeking to share data must take the appropriate steps to curate the data in a way that organizes the clinically relevant information so as to be useful to the data sharing party, assesses the ensuing value of the data set and its annotations, and informs the data sharing contracts that will govern use of the data. Embarking on a data sharing partnership engenders a host of ethical, practical, technical, legal, and commercial challenges that require a thoughtful, considered approach. In 2019 the ACR convened a Data Sharing Workgroup to develop philosophies around best practices in the sharing of health information. This is Part 2 of a Report on the workgroup's efforts in exploring these issues.

Data Sharing of Imaging in an Evolving Health Care World: Report of the ACR Data Sharing Workgroup, Part 1: Data Ethics of Privacy, Consent, and Anonymization.

Radiology is at the forefront of the artificial intelligence transformation of health care across multiple areas, from patient selection to study acquisition to image interpretation. Needing large data sets to develop and train these algorithms, developers enter contractual data sharing agreements involving data derived from health records, usually with postacquisition curation and annotation. In 2019 the ACR convened a Data Sharing Workgroup to develop philosophies around best practices in the sharing of health information. The workgroup identified five broad domains of activity important to collaboration using patient data: privacy, informed consent, standardization of data elements, vendor contracts, and data valuation. This is Part 1 of a Report on the workgroup's efforts in exploring these issues.

Improving Billing Accuracy Through Enterprise-Wide Standardized Structured Reporting With Cross-Divisional Shared Templates.

OBJECTIVE: We describe our experience in implementing enterprise-wide standardized structured reporting for chest radiographs (CXRs) via change management strategies and assess the economic impact of structured template adoption. METHODS: Enterprise-wide standardized structured CXR reporting was implemented in a large urban health care enterprise in two phases from September 2016 to March 2019: initial implementation of division-specific structured templates followed by introduction of auto launching cross-divisional consensus structured templates. Usage was tracked over time, and potential radiologist time savings were estimated. Correct-to-bill (CTB) rates were collected between January 2018 and May 2019 for radiography. RESULTS: CXR structured template adoption increased from 46% to 92% in phase 1 and to 96.2% in phase 2, resulting in an estimated 8.5 hours per month of radiologist time saved. CTB rates for both radiographs and all radiology reports showed a linearly increasing trend postintervention with radiography CTB rate showing greater absolute values with an average difference of 20% throughout the sampling period. The CTB rate for all modalities increased by 12%, and the rate for radiography increased by 8%. DISCUSSION: Change management strategies prompted adoption of division-specific structured templates, and exposure via auto launching enforced widespread adoption of consensus templates. Standardized structured reporting resulted in both economic gains and projected radiologist time saved.

The State of Radiology AI: Considerations for Purchase Decisions and Current Market Offerings.

PURPOSE: To provide an overview of important factors to consider when purchasing radiology artificial intelligence (AI) software and current software offerings by type, subspecialty, and modality. MATERIALS AND METHODS: Important factors for consideration when purchasing AI software, including key decision makers, data ownership and privacy, cost structures, performance indicators, and potential return on investment are described. For the market overview, a list of radiology AI companies was aggregated from the Radiological Society of North America and the Society for Imaging Informatics in Medicine conferences (November 2016-June 2019), then narrowed to companies using deep learning for imaging analysis and diagnosis. Software created for image enhancement, reporting, or workflow management was excluded. Software was categorized by task (repetitive, quantitative, explorative, and diagnostic), modality, and subspecialty. RESULTS: A total of 119 software offerings from 55 companies were identified. There were 46 algorithms that currently have Food and Drug Administration and/or Conformité Européenne approval (as of November 2019). Of the 119 offerings, distribution of software targets was 34 of 70 (49%), 21 of 70 (30%), 14 of 70 (20%), and one of 70 (1%) for diagnostic, quantitative, repetitive, and explorative tasks, respectively. A plurality of companies are focused on nodule detection at chest CT and two-dimensional mammography. There is very little activity in certain subspecialties, including pediatrics and nuclear medicine. A comprehensive table is available on the website hitilab.org/pages/ai-companies. CONCLUSION: The radiology AI marketplace is rapidly maturing, with an increase in product offerings. Radiologists and practice administrators should educate themselves on current product offerings and important factors to consider before purchase and implementation.© RSNA, 2020See also the invited commentary by Sala and Ursprung in this issue.

The resuscitative endovascular balloon occlusion of aorta (REBOA) device-what radiologists need to know.

Resuscitative endovascular balloon occlusion of the aorta (REBOA) is a novel device approved by the Food and Drug administration (FDA) in 2017 as an alternative to resuscitative emergent thoracotomy (RET). Due to advancements in placement of REBOA, including newly validated placement using anatomic landmarks, REBOA is now widely used by interventional radiologists and emergency physicians in acute subdiaphragmatic hemorrhage. Increased use of REBOA necessitates that radiologists are familiar with verification of proper REBOA placement to minimize complications. This review describes the REBOA device, indications, placement, and complications, summarizing the current available literature.

The Application of Machine Learning to Quality Improvement Through the Lens of the Radiology Value Network.

Recent advances in machine learning and artificial intelligence offer promising applications to radiology quality improvement initiatives as they relate to the radiology value network. Coordination within the interlocking web of systems, events, and stakeholders in the radiology value network may be mitigated though standardization, automation, and a focus on workflow efficiency. In this article the authors present applications of these various strategies via use cases for quality improvement projects at different points in the radiology value network. In addition, the authors discuss opportunities for machine-learning applications in data aggregation as opposed to traditional applications in data extraction.

The Role of Generative Adversarial Networks in Radiation Reduction and Artifact Correction in Medical Imaging.

Adversarial networks were developed to complete powerful image-processing tasks on the basis of example images provided to train the networks. These networks are relatively new in the field of deep learning and have proved to have unique strengths that can potentially benefit radiology. Specifically, adversarial networks have the potential to decrease radiation exposure to patients through minimizing repeat imaging due to artifact, decreasing acquisition time, and generating higher quality images from low-dose or no-dose studies. The authors provide an overview of a specific type of adversarial network called a "generalized adversarial network" and review its uses in current medical imaging research.

Emergency department imaging superusers.

PURPOSE: To identify and characterize the most frequent users of emergency department (ED) imaging. MATERIALS AND METHODS: All patients with at least one ED visit in 2016 across a four-hospital healthcare system were retrospectively identified and their ED imaging utilization characterized. RESULTS: Overall, 126,940 unique patients underwent 187,603 ED visits (mean 1.5 ± 1.7) and a total of 192,142 imaging examinations (mean 1.7 ± 2.7). Fifty-eight percent of patients were imaged (73,672) and underwent a mean 2.6 ± 2.7 exams. When ranked by ED visits, 1.6% (2007) of patients had ≥ 4 ED visits (mean 6.1 ± 5.4). These ED "clinical superusers" accounted for 7.7% (14,409) of total ED visits and underwent 6.8 ± 5.4 imaging examinations, while non-superusers underwent 1.5 ± 2.2 (p < 0.01). When ranked by ED imaging utilization, 12.3% (15,575) of patients underwent ≥ 4 ED imaging examinations and consumed 49.5% (95,053) of all imaging services. A subset of just 1.3% (1608) of ED patients underwent > 10 annual ED examinations (ED "imaging superusers") and accounted for 12.4% (23,787) of all ED imaging services. Only 0.4% (n = 472) of patients were both clinical and imaging superusers. Despite similar ED visits to clinical superusers (6.0 ± 5.6 vs. 6.1 ± 5.4, p = 0.92), imaging superusers underwent significantly more imaging (14.8 ± 4.8 vs. 6.8 ± 5.4 examinations, p < 0.01). CONCLUSION: Just 12% of ED patients consume 50% of all ED imaging services, and 1.3% consume 12.4%. These ED imaging superusers represent a distinct group from clinical superusers. Prospective identification of this newly described subgroup might permit targeted interventions to control ED imaging volume, restrain costs, and minimize per-patient radiation exposure.

Assessing Contribution of Higher Order Clinical Risk Factors to Prediction of Outcome in Aneurysmal Subarachnoid Hemorrhage Patients.

The goal of this study was to investigate the application of machine learning models capable of capturing multiplica tive and temporal clinical risk factors for outcome prediction inpatients with aneurysmal subarachnoid hemorrhage (aSAH). We examined a cohort of 575 aSAH patients from Emory Healthcare, identified via digital subtraction angiog- raphy. The outcome measure was the modified Ranking Scale (mRS) after 90 days. Predictions were performed with longitudinal clinical and imaging risk factors as inputs into a regularized Logistic Regression, a feedforward Neural Network and a multivariate time-series prediction model known as the long short-term memory (LSTM) architecture. Through extraction of higher-order risk factors, the LSTM model achieved an AUC of 0.89 eight days into hospitaliza tion, outperforming other techniques. Our preliminary findings indicate the proposed model has the potential to aid treatment decisions and effective imaging resource utilization in high-risk patients by providing actionable predictions prior to the development of neurological deterioration.

Protecting Your Patients' Interests in the Era of Big Data, Artificial Intelligence, and Predictive Analytics.

The Hippocratic oath and the Belmont report articulate foundational principles for how physicians interact with patients and research subjects. The increasing use of big data and artificial intelligence techniques demands a re-examination of these principles in light of the potential issues surrounding privacy, confidentiality, data ownership, informed consent, epistemology, and inequities. Patients have strong opinions about these issues. Radiologists have a fiduciary responsibility to protect the interest of their patients. As such, the community of radiology leaders, ethicists, and informaticists must have a conversation about the appropriate way to deal with these issues and help lead the way in developing capabilities in the most just, ethical manner possible.

Incompletely obliterated cranial arteriovenous fistulae are safely and effectively treated with adjuvant ε-aminocaproic acid.

BACKGROUND: Administration of ε-aminocaproic acid (εACA), as adjuvant therapy following incompletely embolized cranial dural arteriovenous (dAVFs) and direct carotid artery to cavernous sinus fistulae (CCFs), is a strategy to promote post-procedural thrombosis. However, the efficacy of εACA to treat incompletely obliterated dAVFs and CCFs has not been published. The purpose of this study was to determine if administration of εACA following incomplete embolization of cranial dAVFs or CCFs was associated with an increased likelihood of cure on follow-up imaging compared with patients not given adjuvant εACA. METHODS: A retrospective cohort study was performed. All patients who underwent treatment of a dAVF or CCF at our institution between 1998 and 2016 were reviewed (n=262). Patients with residual shunting following the first attempted endovascular embolization were included in the analysis (n=52). The study groups were those treated with εACA following incomplete obliteration of the fistula and those who were not. The primary outcome was obliteration of the fistula on initial follow-up imaging. Complication rates between cohorts were compared. RESULTS: 20 (38%) patients with incompletely obliterated fistulae were treated with adjuvant εACA. A trend towards an improved rate of complete obliteration on initial follow-up imaging was observed in the group treated with εACA (55% vs 34% in the group not treated with εACA, p=0.14). No difference in clinical outcomes or thromboembolic complications was observed between the groups. CONCLUSIONS: In summary, these data suggest that administration of εACA is a safe adjuvant therapy in the management of cranial dAVFs and CCFs that are incompletely treated endovascularly.

Machine Learning in Radiology: Applications Beyond Image Interpretation.

Much attention has been given to machine learning and its perceived impact in radiology, particularly in light of recent success with image classification in international competitions. However, machine learning is likely to impact radiology outside of image interpretation long before a fully functional "machine radiologist" is implemented in practice. Here, we describe an overview of machine learning, its application to radiology and other domains, and many cases of use that do not involve image interpretation. We hope that better understanding of these potential applications will help radiology practices prepare for the future and realize performance improvement and efficiency gains.

Towards Consensus: Training in Procedural Skills for Diagnostic Radiology Residents-Current Opinions of Residents and Faculty at a Large Academic Center.

RATIONALE AND OBJECTIVES: The Diagnostic Radiology Milestones Project provides a framework for measuring resident competence in radiologic procedures, but there are limited data available to assist in developing these guidelines. We performed a survey of current radiology residents and faculty at our institution as a first step toward obtaining data for this purpose. The survey addressed attitudes toward procedural standardization and procedures that trainees should be competent by the end of residency. MATERIALS AND METHODS: Current residents and faculty members were surveyed about whether or not there should be standardization of procedural training, in which procedures residents should achieve competency, and the number of times a procedure needs to be performed to achieve competency. RESULTS: Survey data were received from 60 study participants with an overall response rate of 32%. Sixty-five percent of respondents thought that procedural training should be standardized. Standardization of procedural training would include both the list of procedures that trainees should be competent in at the end of residency and the standard minimum number of procedures to achieve competency. Procedures that both residents and faculty agreed are important in which to achieve competency included central line/port procedures; CT-guided abdominal, thoracic, and musculoskeletal procedures; minor fluoroscopic-guided procedures; general fluoroscopy; peripheral line placements; and US-guided abdominal procedures. For most of these categories, most respondents believed that these procedures needed to be performed 6-20 times to achieve competency. CONCLUSION: Both resident and faculty respondents agreed that procedural training should be standardized during residency, and competence in specific procedures should be achieved at the completion of residency. Although this study is limited to a single institution, our data may provide assistance in developing future guidelines for standardizing image-guided procedure training. Future studies could be expanded to create a national consensus regarding the implementation of the Diagnostic Radiology Milestones Project.