Interactive Multimedia Reporting Technical Considerations: HIMSS-SIIM Collaborative White Paper.

Despite technological advances in the analysis of digital images for medical consultations, many health information systems lack the ability to correlate textual descriptions of image findings linked to the actual images. Images and reports often reside in separate silos in the medical record throughout the process of image viewing, report authoring, and report consumption. Forward-thinking centers and early adopters have created interactive reports with multimedia elements and embedded hyperlinks in reports that connect the narrative text with the related source images and measurements. Most of these solutions rely on proprietary single-vendor systems for viewing and reporting in the absence of any encompassing industry standards to facilitate interoperability with the electronic health record (EHR) and other systems. International standards have enabled the digitization of image acquisition, storage, viewing, and structured reporting. These provide the foundation to discuss enhanced reporting. Lessons learned in the digital transformation of radiology and pathology can serve as a basis for interactive multimedia reporting (IMR) across image-centric medical specialties. This paper describes the standard-based infrastructure and communications to fulfill recently defined clinical requirements through a consensus from an international workgroup of multidisciplinary medical specialists, informaticists, and industry participants. These efforts have led toward the development of an Integrating the Healthcare Enterprise (IHE) profile that will serve as a foundation for interoperable interactive multimedia reporting.

Analysis of Radiology Report Recommendation Characteristics and Rate of Recommended Action Performance.

Importance: Following up on recommendations from radiologic findings is important for patient care, but frequently there are failures to carry out these recommendations. The lack of reliable systems to characterize and track completion of actionable radiology report recommendations poses an important patient safety challenge. Objectives: To characterize actionable radiology recommendations and, using this taxonomy, track and understand rates of loop closure for radiology recommendations in a primary care setting. Design, Setting, and Participants: Radiology reports in a primary care clinic at a large academic center were redesigned to include actionable recommendations in a separate dedicated field. Manual review of all reports generated from imaging tests ordered between January 1 and December 31, 2018, by primary care physicians that contained actionable recommendations was performed. For this quality improvement study, a taxonomy system that conceptualized recommendations was developed based on 3 domains: (1) what is recommended (eg, repeat a test or perform a different test, specialty referral), (2) specified time frame in which to perform the recommended action, and (3) contingency language qualifying the recommendation. Using this framework, a 2-stage process was used to review patients' records to classify recommendations and determine loop closure rates and factors associated with failure to complete recommended actions. Data analysis was conducted from April to July 2021. Main Outcomes and Measures: Radiology recommendations, time frames, and contingencies. Rates of carrying out vs not closing the loop on these recommendations in the recommended time frame were assessed. Results: A total of 598 radiology reports were identified with structured recommendations: 462 for additional or future radiologic studies and 196 for nonradiologic actions (119 specialty referrals, 47 invasive procedures, and 43 other actions). The overall rate of completed actions (loop closure) within the recommended time frame was 87.4%, with 31 open loop cases rated by quality expert reviewers to pose substantial clinical risks. Factors associated with successful loop closure included (1) absence of accompanying contingency language, (2) shorter recommended time frames, and (3) evidence of direct radiologist communication with the ordering primary care physicians. A clinically significant lack of loop closure was found in approximately 5% of cases. Conclusions and Relevance: The findings of this study suggest that creating structured radiology reports featuring a dedicated recommendations field permits the development of taxonomy to classify such recommendations and determine whether they were carried out. The lack of loop closure suggests the need for more reliable systems.

Artificial intelligence to assess body composition on routine abdominal CT scans and predict mortality in pancreatic cancer- A recipe for your local application.

BACKGROUND: Body composition is associated with mortality; however its routine assessment is too time-consuming. PURPOSE: To demonstrate the value of artificial intelligence (AI) to extract body composition measures from routine studies, we aimed to develop a fully automated AI approach to measure fat and muscles masses, to validate its clinical discriminatory value, and to provide the code, training data and workflow solutions to facilitate its integration into local practice. METHODS: We developed a neural network that quantified the tissue components at the L3 vertebral body level using data from the Liver Tumor Challenge (LiTS) and a pancreatic cancer cohort. We classified sarcopenia using accepted skeletal muscle index cut-offs and visceral fat based its median value. We used Kaplan Meier curves and Cox regression analysis to assess the association between these measures and mortality. RESULTS: Applying the algorithm trained on LiTS data to the local cohort yielded good agreement [>0.8 intraclass correlation (ICC)]; when trained on both datasets, it had excellent agreement (>0.9 ICC). The pancreatic cancer cohort had 136 patients (mean age: 67 ± 11 years; 54% women); 15% had sarcopenia; mean visceral fat was 142 cm2. Concurrent with prior research, we found a significant association between sarcopenia and mortality [mean survival of 15 ± 12 vs. 22 ± 12 (p < 0.05), adjusted HR of 1.58 (95% CI: 1.03-3.33)] but no association between visceral fat and mortality. The detector analysis took 1 ± 0.5 s. CONCLUSIONS: AI body composition analysis can provide meaningful imaging biomarkers from routine exams demonstrating AI's ability to further enhance the clinical value of radiology reports.

Multispecialty Enterprise Imaging Workgroup Consensus on Interactive Multimedia Reporting Current State and Road to the Future: HIMSS-SIIM Collaborative White Paper.

Diagnostic and evidential static image, video clip, and sound multimedia are captured during routine clinical care in cardiology, dermatology, ophthalmology, pathology, physiatry, radiation oncology, radiology, endoscopic procedural specialties, and other medical disciplines. Providers typically describe the multimedia findings in contemporaneous electronic health record clinical notes or associate a textual interpretative report. Visual communication aids commonly used to connect, synthesize, and supplement multimedia and descriptive text outside medicine remain technically challenging to integrate into patient care. Such beneficial interactive elements may include hyperlinks between text, multimedia elements, alphanumeric and geometric annotations, tables, graphs, timelines, diagrams, anatomic maps, and hyperlinks to external educational references that patients or provider consumers may find valuable. This HIMSS-SIIM Enterprise Imaging Community workgroup white paper outlines the current and desired clinical future state of interactive multimedia reporting (IMR). The workgroup adopted a consensus definition of IMR as "interactive medical documentation that combines clinical images, videos, sound, imaging metadata, and/or image annotations with text, typographic emphases, tables, graphs, event timelines, anatomic maps, hyperlinks, and/or educational resources to optimize communication between medical professionals, and between medical professionals and their patients." This white paper also serves as a precursor for future efforts toward solving technical issues impeding routine interactive multimedia report creation and ingestion into electronic health records.

Deep Learning to Quantify Pulmonary Edema in Chest Radiographs.

PURPOSE: To develop a machine learning model to classify the severity grades of pulmonary edema on chest radiographs. MATERIALS AND METHODS: In this retrospective study, 369 071 chest radiographs and associated radiology reports from 64 581 patients (mean age, 51.71 years; 54.51% women) from the MIMIC-CXR chest radiograph dataset were included. This dataset was split into patients with and without congestive heart failure (CHF). Pulmonary edema severity labels from the associated radiology reports were extracted from patients with CHF as four different ordinal levels: 0, no edema; 1, vascular congestion; 2, interstitial edema; and 3, alveolar edema. Deep learning models were developed using two approaches: a semisupervised model using a variational autoencoder and a pretrained supervised learning model using a dense neural network. Receiver operating characteristic curve analysis was performed on both models. RESULTS: The area under the receiver operating characteristic curve (AUC) for differentiating alveolar edema from no edema was 0.99 for the semisupervised model and 0.87 for the pretrained models. Performance of the algorithm was inversely related to the difficulty in categorizing milder states of pulmonary edema (shown as AUCs for semisupervised model and pretrained model, respectively): 2 versus 0, 0.88 and 0.81; 1 versus 0, 0.79 and 0.66; 3 versus 1, 0.93 and 0.82; 2 versus 1, 0.69 and 0.73; and 3 versus 2, 0.88 and 0.63. CONCLUSION: Deep learning models were trained on a large chest radiograph dataset and could grade the severity of pulmonary edema on chest radiographs with high performance.Supplemental material is available for this article.See also the commentary by Auffermann in this issue.© RSNA, 2021.

Do as AI say: susceptibility in deployment of clinical decision-aids.

Artificial intelligence (AI) models for decision support have been developed for clinical settings such as radiology, but little work evaluates the potential impact of such systems. In this study, physicians received chest X-rays and diagnostic advice, some of which was inaccurate, and were asked to evaluate advice quality and make diagnoses. All advice was generated by human experts, but some was labeled as coming from an AI system. As a group, radiologists rated advice as lower quality when it appeared to come from an AI system; physicians with less task-expertise did not. Diagnostic accuracy was significantly worse when participants received inaccurate advice, regardless of the purported source. This work raises important considerations for how advice, AI and non-AI, should be deployed in clinical environments.

Analysis of Kinematic Differences in Hand Motion between Novice and Experienced Operators in IR: A Pilot Study.

PURPOSE: To prospectively validate electromagnetic hand motion tracking in interventional radiology to detect differences in operator experience using simulation. METHODS: Sheath task: Six attending interventional radiologists (experts) and 6 radiology trainees (trainees) placed a wire through a sheath and performed a "pin-pull" maneuver, while an electromagnetic motion detection system recorded the hand motion. Radial task: Eight experts and 12 trainees performed palpatory radial artery access task on a radial access simulator. The trainees repeated the task with the nondominant hand. The experts were classified by their most frequent radial artery access technique as having either palpatory, ultrasound, or overall limited experience. The time, path length, and number of movements were calculated. Mann-Whitney U tests were used to compare the groups, and P < .05 was considered significant. RESULTS: Sheath task: The experts took less time, had shorter path lengths, and used fewer movements than the trainees (11.7 seconds ± 3.3 vs 19.7 seconds ± 6.5, P < .01; 1.1 m ± 0.3 vs 1.4 m ± 0.4, P < .01; and 19.5 movements ± 8.5 vs 31.0 movements ± 8.0, P < .01, respectively). Radial task: The experts took less time, had shorter path lengths, and used fewer movements than the trainees (24.2 seconds ± 10.6 vs 33.1 seconds ± 16.9, P < .01; 2.0 m ± 0.5 vs 3.0 m ± 1.9, P < .001; and 36.5 movements ± 15.0 vs 54.5 movements ± 28.0, P < .001, respectively). The trainees had a shorter path length for their dominant hand than their nondominant hand (3.0 m ± 1.9 vs 3.5 m ± 1.9, P < .05). The expert palpatory group had a shorter path length than the ultrasound and limited experience groups (1.8 m ± 0.4 vs 2.0 m ± 0.4 and 2.3 m ± 1.2, respectively, P < .05). CONCLUSIONS: Electromagnetic hand motion tracking can differentiate between the expert and trainee operators for simulated interventional tasks.

Point of Care Image Capture with a Custom Smartphone Application: Experience with an Encounter-Based Workflow.

Medical documentation is one of the primary methods by which physicians share clinical information and impressions over time with one another. As the adage says, "a picture is worth a thousand words," and physicians have started leveraging consumer mobile technology to share images with one another. However, image sharing often uses short message service texting and similar methods, which can be noncompliant with privacy regulations and can also limit the ability to communicate information longitudinally and across specialties. Sharing of such information is increasingly important, however, as smaller practices are joining to create large geographically spread out health care networks. To this end, we developed an application to acquire and store images via smartphone and seamlessly transfer into the patient's electronic medical record (EMR) to enable digital consults and longitudinal evaluation in a private and compliant method.

MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports.

Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's chest, but requires specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. Here we describe MIMIC-CXR, a large dataset of 227,835 imaging studies for 65,379 patients presenting to the Beth Israel Deaconess Medical Center Emergency Department between 2011-2016. Each imaging study can contain one or more images, usually a frontal view and a lateral view. A total of 377,110 images are available in the dataset. Studies are made available with a semi-structured free-text radiology report that describes the radiological findings of the images, written by a practicing radiologist contemporaneously during routine clinical care. All images and reports have been de-identified to protect patient privacy. The dataset is made freely available to facilitate and encourage a wide range of research in computer vision, natural language processing, and clinical data mining.

Migrating to the Modern PACS: Challenges and Opportunities.

With progressive advancements in picture archiving and communication system (PACS) technology, radiology practices frequently look toward system upgrades and replacements to further improve efficiency and capabilities. The transition between PACS has the potential to derail the operations of a radiology department. Careful planning and attention to detail from radiology informatics leaders are imperative to ensure a smooth transition. This article is a review of the architecture of a modern PACS, highlighting areas of recent innovation. Key considerations for planning a PACS migration and important issues to consider in data migration, change management, and business continuity are discussed. Beyond the technical aspects of a PACS migration, the human factors to consider when managing the cultural change that accompanies a new informatics tool and the keys to success when managing technical failures are explored. Online supplemental material is available for this article. ©RSNA, 2018.

Fatal Hemoptysis After Closure of Gastrobronchial Fistula Using an Amplatzer Vascular Device.

The Amplatzer family of vascular devices has been used off-label for the treatment of complex gastrointestinal and airway fistulas. We report a case in which closure of a benign gastrobronchial fistula with the use of an Amplatzer device resulted in massive hemoptysis and death.

Resident iPad use: has it really changed the game?

PURPOSE: The purpose of this study was to assess residents' usage patterns and opinions of the iPad as a tool for radiology education and clinical practice at an academic medical center. METHODS: All 38 radiology residents in our radiology program (postgraduate years 2 to 5) were provided with iPad 2 tablets and subscriptions to e-Anatomy and STATdx. After 6 months of device use, residents were surveyed to assess their opinions regarding the technology as a tool for education and clinical practice. RESULTS: A total of 36 residents (95%) completed the survey. Eighty-six percent reported daily iPad use. Radiology-specific applications, particularly e-Anatomy, were used weekly or daily by 88% of respondents. Most preferred to read journal articles on the iPad (70%), but the number of respondents preferring to read textbooks on the iPad (48.5%) compared with the traditional bound form (48.5%) was evenly divided. Residents were also divided on the clinical utility of the iPad. Most had not used the iPad to view radiologic examinations (75%). Fewer than half (47%) used their iPads during readout. Finally, only 12% had used the iPad to edit dictated reports. CONCLUSIONS: The iPad has generated excitement within the radiology community, particularly among resident educators, who are increasingly recognizing the unique needs of "millennial learners." This study showed that the majority of residents at the authors' institution have incorporated the iPad as an educational tool and use it as a learning aid. Incorporation of the iPad into clinical workflow has been less pronounced.

Prevalence of left ventricular regional dysfunction in arrhythmogenic right ventricular dysplasia: a tagged MRI study.

BACKGROUND: Although arrhythmogenic right ventricular dysplasia (ARVD) predominantly affects the right ventricle (RV), genetic/molecular and histological changes are biventricular. Regional left ventricular (LV) function has not been systematically studied in ARVD. METHODS AND RESULTS: The study population included 21 patients with suspected ARVD who underwent evaluation with MRI including tagging. Eleven healthy volunteers served as control subjects. Peak systolic regional circumferential strain (Ecc, %) was calculated by harmonic phase from tagged MRI based on the 16-segment model. Patients who met ARVD Task Force criteria were classified as definite ARVD, whereas patients with a positive family history who had 1 additional minor criterion and patients without a family history with 1 major or 2 minor criteria were classified as probable ARVD. Of the 21 ARVD subjects, 11 had definite ARVD and 10 had probable ARVD. Compared with control subjects, probable ARVD patients had similar RV ejection fraction (58.9+/-6.2% versus 53.5+/-7.6%, P=0.20), but definite ARVD patients had significantly reduced RV ejection fraction (58.9+/-6.2% versus 45.2+/-6.0%, P=0.001). LV ejection fraction was similar in all 3 groups. Compared with control subjects, peak systolic Ecc was significantly less negative in 6 of 16 (37.5%) segments in definite ARVD and 3 of 16 segments (18.7%) in probable ARVD (all P<0.05). CONCLUSIONS: ARVD is associated with regional LV dysfunction, which appears to parallel degree of RV dysfunction. Further large studies are needed to validate this finding and to better define implications of subclinical segmental LV dysfunction.

Axial black blood turbo spin echo imaging of the right ventricle.

Black blood turbo spin echo (TSE) imaging of the right ventricle (RV) free wall is highly sensitive to cardiac motion, frequently resulting in nondiagnostic images. Temporal and spatial parameters of a black blood TSE pulse sequence were evaluated for visualization of the RV free wall. Seventy-four patient studies were retrospectively evaluated for the effects of acquisition timing on image quality. Axial black blood TSE images were acquired on 10 healthy volunteers to assess the role of spatial misregistration on right ventricle visualization; increasing the double inversion recovery (DIR) slice thickness beyond 300% had no effect on image quality (P = 0.2). Thirty-five patient studies were prospectively evaluated with inversion times (TIs) corresponding to the mid-diastolic rest period and end-systole based on visual analysis of a four chamber cine. When TIs were chosen to be within the patients' RV rest period, mean image quality score was significantly improved (2.3 vs 1.86; P < 0.001) and the number of clinically diagnostic images increased from 32% to 46%. Black blood TSE imaging of the RV free wall is highly sensitive to cardiac motion. Image quality can be improved by choosing TIs concordant with the rest period of the patient's RV that may occur at mid-diastole or end-systole.