Deep learning discrimination of rheumatoid arthritis from osteoarthritis on hand radiography.

PURPOSE: To develop a deep learning model to distinguish rheumatoid arthritis (RA) from osteoarthritis (OA) using hand radiographs and to evaluate the effects of changing pretraining and training parameters on model performance. MATERIALS AND METHODS: A convolutional neural network was retrospectively trained on 9714 hand radiograph exams from 8387 patients obtained from 2017 to 2021 at seven hospitals within an integrated healthcare network. Performance was assessed using an independent test set of 250 exams from 146 patients. Binary discriminatory capacity (no arthritis versus arthritis; RA versus not RA) and three-way classification (no arthritis versus OA versus RA) were evaluated. The effects of additional pretraining using musculoskeletal radiographs, using all views as opposed to only the posteroanterior view, and varying image resolution on model performance were also investigated. Area under the receiver operating characteristic curve (AUC) and Cohen's kappa coefficient were used to evaluate diagnostic performance. RESULTS: For no arthritis versus arthritis, the model achieved an AUC of 0.975 (95% CI: 0.957, 0.989). For RA versus not RA, the model achieved an AUC of 0.955 (95% CI: 0.919, 0.983). For three-way classification, the model achieved a kappa of 0.806 (95% CI: 0.742, 0.866) and accuracy of 87.2% (95% CI: 83.2%, 91.2%) on the test set. Increasing image resolution increased performance up to 1024 × 1024 pixels. Additional pretraining on musculoskeletal radiographs and using all views did not significantly affect performance. CONCLUSION: A deep learning model can be used to distinguish no arthritis, OA, and RA on hand radiographs with high performance.

Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT.

Background Adrenal masses are common, but radiology reporting and recommendations for management can be variable. Purpose To create a machine learning algorithm to segment adrenal glands on contrast-enhanced CT images and classify glands as normal or mass-containing and to assess algorithm performance. Materials and Methods This retrospective study included two groups of contrast-enhanced abdominal CT examinations (development data set and secondary test set). Adrenal glands in the development data set were manually segmented by radiologists. Images in both the development data set and the secondary test set were manually classified as normal or mass-containing. Deep learning segmentation and classification models were trained on the development data set and evaluated on both data sets. Segmentation performance was evaluated with use of the Dice similarity coefficient (DSC), and classification performance with use of sensitivity and specificity. Results The development data set contained 274 CT examinations (251 patients; median age, 61 years; 133 women), and the secondary test set contained 991 CT examinations (991 patients; median age, 62 years; 578 women). The median model DSC on the development test set was 0.80 (IQR, 0.78-0.89) for normal glands and 0.84 (IQR, 0.79-0.90) for adrenal masses. On the development reader set, the median interreader DSC was 0.89 (IQR, 0.78-0.93) for normal glands and 0.89 (IQR, 0.85-0.97) for adrenal masses. Interreader DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = .35). On the development test set, the model had a classification sensitivity of 83% (95% CI: 55, 95) and specificity of 89% (95% CI: 75, 96). On the secondary test set, the model had a classification sensitivity of 69% (95% CI: 58, 79) and specificity of 91% (95% CI: 90, 92). Conclusion A two-stage machine learning pipeline was able to segment the adrenal glands and differentiate normal adrenal glands from those containing masses. © RSNA, 2022 Online supplemental material is available for this article.

Utility of Normalized Body Composition Areas, Derived From Outpatient Abdominal CT Using a Fully Automated Deep Learning Method, for Predicting Subsequent Cardiovascular Events.

BACKGROUND. CT-based body composition (BC) measurements have historically been too resource intensive to analyze for widespread use and have lacked robust comparison with traditional weight metrics for predicting cardiovascular risk. OBJECTIVE. The aim of this study was to determine whether BC measurements obtained from routine CT scans by use of a fully automated deep learning algorithm could predict subsequent cardiovascular events independently from weight, BMI, and additional cardiovascular risk factors. METHODS. This retrospective study included 9752 outpatients (5519 women and 4233 men; mean age, 53.2 years; 890 patients self-reported their race as Black and 8862 self-reported their race as White) who underwent routine abdominal CT at a single health system from January 2012 through December 2012 and who were given no major cardiovascular or oncologic diagnosis within 3 months of undergoing CT. Using publicly available code, fully automated deep learning BC analysis was performed at the L3 vertebral body level to determine three BC areas (skeletal muscle area [SMA], visceral fat area [VFA], and subcutaneous fat area [SFA]). Age-, sex-, and race-normalized reference curves were used to generate z scores for the three BC areas. Subsequent myocardial infarction (MI) or stroke was determined from the electronic medical record. Multivariable-adjusted Cox proportional hazards models were used to determine hazard ratios (HRs) for MI or stroke within 5 years after CT for the three BC area z scores, with adjustment for normalized weight, normalized BMI, and additional cardiovascular risk factors (smoking status, diabetes diagnosis, and systolic blood pressure). RESULTS. In multivariable models, age-, race-, and sex-normalized VFA was associated with subsequent MI risk (HR of highest quartile compared with lowest quartile, 1.31 [95% CI, 1.03-1.67], p = .04 for overall effect) and stroke risk (HR of highest compared with lowest quartile, 1.46 [95% CI, 1.07-2.00], p = .04 for overall effect). In multivariable models, normalized SMA, SFA, weight, and BMI were not associated with subsequent MI or stroke risk. CONCLUSION. VFA derived from fully automated and normalized analysis of abdominal CT examinations predicts subsequent MI or stroke in Black and White patients, independent of traditional weight metrics, and should be considered an adjunct to BMI in risk models. CLINICAL IMPACT. Fully automated and normalized BC analysis of abdominal CT has promise to augment traditional cardiovascular risk prediction models.

Population-Scale CT-based Body Composition Analysis of a Large Outpatient Population Using Deep Learning to Derive Age-, Sex-, and Race-specific Reference Curves.

Background Although CT-based body composition (BC) metrics may inform disease risk and outcomes, obtaining these metrics has been too resource intensive for large-scale use. Thus, population-wide distributions of BC remain uncertain. Purpose To demonstrate the validity of fully automated, deep learning BC analysis from abdominal CT examinations, to define demographically adjusted BC reference curves, and to illustrate the advantage of use of these curves compared with standard methods, along with their biologic significance in predicting survival. Materials and Methods After external validation and equivalency testing with manual segmentation, a fully automated deep learning BC analysis pipeline was applied to a cross-sectional population cohort that included any outpatient without a cardiovascular disease or cancer who underwent abdominal CT examination at one of three hospitals in 2012. Demographically adjusted population reference curves were generated for each BC area. The z scores derived from these curves were compared with sex-specific thresholds for sarcopenia by using χ2 tests and used to predict 2-year survival in multivariable Cox proportional hazards models that included weight and body mass index (BMI). Results External validation showed excellent correlation (R = 0.99) and equivalency (P < .001) of the fully automated deep learning BC analysis method with manual segmentation. With use of the fully automated BC data from 12 128 outpatients (mean age, 52 years; 6936 [57%] women), age-, race-, and sex-normalized BC reference curves were generated. All BC areas varied significantly with these variables (P < .001 except for subcutaneous fat area vs age [P = .003]). Sex-specific thresholds for sarcopenia demonstrated that age and race bias were not present if z scores derived from the reference curves were used (P < .001). Skeletal muscle area z scores were significantly predictive of 2-year survival (P = .04) in combined models that included BMI. Conclusion Fully automated body composition (BC) metrics vary significantly by age, race, and sex. The z scores derived from reference curves for BC parameters better capture the demographic distribution of BC compared with standard methods and can help predict survival. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Summers in this issue.

Effects of age and sex on the distribution and symmetry of lumbar spinal and neural foraminal stenosis: a natural language processing analysis of 43,255 lumbar MRI reports.

PURPOSE: The purpose of this study is to investigate relationship of patient age and sex to patterns of degenerative spinal stenosis on lumbar MRI (LMRI), rated as moderate or greater by a spine radiologist, using natural language processing (NLP) tools. METHODS: In this retrospective, IRB-approved study, LMRI reports acquired from 2007 to 2017 at a single institution were parsed with a rules-based natural language processing (NLP) algorithm for free-text descriptors of spinal canal stenosis (SCS) and neural foraminal stenosis (NFS) at each of six spinal levels (T12-S1) and categorized according to a 6-point grading scale. Demographic differences in the anatomic distribution of moderate (grade 3) or greater SCS and NFS were calculated by sex, and age and within-group differences for NFS symmetry (left vs. right) were calculated as odds ratios. RESULTS: Forty-three thousand two hundred fifty-five LMRI reports (34,947 unique patients, mean age = 54.7; sex = 54.9% women) interpreted by 152 radiologists were studied. Prevalence of significant SCS and NFS increased caudally from T12-L1 to L4-5 though less at L5-S1. NFS was asymmetrically more prevalent on the left at L2-L3 and L5-S1 (p < 0.001). SCS and NFS were more prevalent in men and SCS increased with age at all levels, but the effect size of age was largest at T12-L3. Younger patients (< 50 years) had relatively higher NFS prevalence at L5-S1. CONCLUSION: NLP can identify patterns of lumbar spine degeneration through analysis of a large corpus of radiologist interpretations. Demographic differences in stenosis prevalence shed light on the natural history and pathogenesis of LSDD.

The Composite Severity Score for Lumbar Spine MRI: a Metric of Cumulative Degenerative Disease Predicts Time Spent on Interpretation and Reporting.

Conventional measures of radiologist efficiency, such as the relative value unit, fail to account for variations in the complexity and difficulty of a given study. For lumbar spine MRI (LMRI), an ideal performance metric should account for the global severity of lumbar degenerative disease (LSDD) which may influence reporting time (RT), thereby affecting clinical productivity. This study aims to derive a global LSDD metric and estimate its effect on RT. A 10-year archive of LMRI reports comprising 13,388 exams was reviewed. Objective reporting timestamps were used to calculate RT. A natural language processing (NLP) tool was used to extract radiologist-assigned stenosis severity using a 6-point scale (0 = "normal" to 5 = "severe") at each lumbar level. The composite severity score (CSS) was calculated as the sum of each of 18 stenosis grades. The predictive values of CSS, sex, age, radiologist identity, and referring service on RT were examined with multiple regression models. The NLP tool accurately classified LSDD in 94.8% of cases in a validation set. The CSS increased with patient age and differed between men and women. In a univariable model, CSS was a significant predictor of mean RT (R2 = 0.38, p < 0.001) and independent predictor of mean RT (p < 0.001) controlling for patient sex, patient age, service location, and interpreting radiologist. The predictive strength of CSS was stronger for the low CSS range (CSS = 0-25, R2 = 0.83, p < 0.001) compared to higher CSS values (CSS > 25, R2 = 0.15, p = 0.05). Individual radiologist study volume was negatively correlated with mean RT (Pearson's R = - 0.35, p < 0.001). The composite severity score predicts radiologist reporting efficiency in LMRI, providing a quantitative measure of case complexity which may be useful for workflow planning and performance evaluation.

The Trials and Tribulations of Assembling Large Medical Imaging Datasets for Machine Learning Applications.

With vast interest in machine learning applications, more investigators are proposing to assemble large datasets for machine learning applications. We aim to delineate multiple possible roadblocks to exam retrieval that may present themselves and lead to significant time delays. This HIPAA-compliant, institutional review board-approved, retrospective clinical study required identification and retrieval of all outpatient and emergency patients undergoing abdominal and pelvic computed tomography (CT) at three affiliated hospitals in the year 2012. If a patient had multiple abdominal CT exams, the first exam was selected for retrieval (n=23,186). Our experience in attempting to retrieve 23,186 abdominal CT exams yielded 22,852 valid CT abdomen/pelvis exams and identified four major categories of challenges when retrieving large datasets: cohort selection and processing, retrieving DICOM exam files from PACS, data storage, and non-recoverable failures. The retrieval took 3 months of project time and at minimum 300 person-hours of time between the primary investigator (a radiologist), a data scientist, and a software engineer. Exam selection and retrieval may take significantly longer than planned. We share our experience so that other investigators can anticipate and plan for these challenges. We also hope to help institutions better understand the demands that may be placed on their infrastructure by large-scale medical imaging machine learning projects.

A Conference-Friendly, Hands-on Introduction to Deep Learning for Radiology Trainees.

Artificial or augmented intelligence, machine learning, and deep learning will be an increasingly important part of clinical practice for the next generation of radiologists. It is therefore critical that radiology residents develop a practical understanding of deep learning in medical imaging. Certain aspects of deep learning are not intuitive and may be better understood through hands-on experience; however, the technical requirements for setting up a programming and computing environment for deep learning can pose a high barrier to entry for individuals with limited experience in computer programming and limited access to GPU-accelerated computing. To address these concerns, we implemented an introductory module for deep learning in medical imaging within a self-contained, web-hosted development environment. Our initial experience established the feasibility of guiding radiology trainees through the module within a 45-min period typical of educational conferences.

Using DICOM Metadata for Radiological Image Series Categorization: a Feasibility Study on Large Clinical Brain MRI Datasets.

The growing interest in machine learning (ML) in healthcare is driven by the promise of improved patient care. However, how many ML algorithms are currently being used in clinical practice? While the technology is present, as demonstrated in a variety of commercial products, clinical integration is hampered by a lack of infrastructure, processes, and tools. In particular, automating the selection of relevant series for a particular algorithm remains challenging. In this work, we propose a methodology to automate the identification of brain MRI sequences so that we can automatically route the relevant inputs for further image-related algorithms. The method relies on metadata required by the Digital Imaging and Communications in Medicine (DICOM) standard, resulting in generalizability and high efficiency (less than 0.4 ms/series). To support our claims, we test our approach on two large brain MRI datasets (40,000 studies in total) from two different institutions on two different continents. We demonstrate high levels of accuracy (ranging from 97.4 to 99.96%) and generalizability across the institutions. Given the complexity and variability of brain MRI protocols, we are confident that similar techniques could be applied to other forms of radiological imaging.

The RSNA Pediatric Bone Age Machine Learning Challenge.

Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application of machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration to catalyze AI model creation, and identify innovators in medical imaging. Materials and Methods The goal of this challenge was to solicit individuals and teams to create an algorithm or model using ML techniques that would accurately determine skeletal age in a curated data set of pediatric hand radiographs. The primary evaluation measure was the mean absolute distance (MAD) in months, which was calculated as the mean of the absolute values of the difference between the model estimates and those of the reference standard, bone age. Results A data set consisting of 14 236 hand radiographs (12 611 training set, 1425 validation set, 200 test set) was made available to registered challenge participants. A total of 260 individuals or teams registered on the Challenge website. A total of 105 submissions were uploaded from 48 unique users during the training, validation, and test phases. Almost all methods used deep neural network techniques based on one or more convolutional neural networks (CNNs). The best five results based on MAD were 4.2, 4.4, 4.4, 4.5, and 4.5 months, respectively. Conclusion The RSNA Pediatric Bone Age Machine Learning Challenge showed how a coordinated approach to solving a medical imaging problem can be successfully conducted. Future ML challenges will catalyze collaboration and development of ML tools and methods that can potentially improve diagnostic accuracy and patient care. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Siegel in this issue.

Using clinically acquired MRI to construct age-specific ADC atlases: Quantifying spatiotemporal ADC changes from birth to 6-year old.

Diffusion imaging is critical for detecting acute brain injury. However, normal apparent diffusion coefficient (ADC) maps change rapidly in early childhood, making abnormality detection difficult. In this article, we explored clinical PACS and electronic healthcare records (EHR) to create age-specific ADC atlases for clinical radiology reference. Using the EHR and three rounds of multiexpert reviews, we found ADC maps from 201 children 0-6 years of age scanned between 2006 and 2013 who had brain MRIs with no reported abnormalities and normal clinical evaluations 2+ years later. These images were grouped in 10 age bins, densely sampling the first 1 year of life (5 bins, including neonates and 4 quarters) and representing the 1-6 year age range (an age bin per year). Unbiased group-wise registration was used to construct ADC atlases for 10 age bins. We used the atlases to quantify (a) cross-sectional normative ADC variations; (b) spatiotemporal heterogeneous ADC changes; and (c) spatiotemporal heterogeneous volumetric changes. The quantified age-specific whole-brain and region-wise ADC values were compared to those from age-matched individual subjects in our study and in multiple existing independent studies. The significance of this study is that we have shown that clinically acquired images can be used to construct normative age-specific atlases. These first of their kind age-specific normative ADC atlases quantitatively characterize changes of myelination-related water diffusion in the first 6 years of life. The quantified voxel-wise spatiotemporal ADC variations provide standard references to assist radiologists toward more objective interpretation of abnormalities in clinical images. Our atlases are available at https://www.nitrc.org/projects/mgh_adcatlases. Hum Brain Mapp 38:3052-3068, 2017. © 2017 Wiley Periodicals, Inc.

Clinical Applications of a CT Window Blending Algorithm: RADIO (Relative Attenuation-Dependent Image Overlay).

A methodology is described using Adobe Photoshop and Adobe Extendscript to process DICOM images with a Relative Attenuation-Dependent Image Overlay (RADIO) algorithm to visualize the full dynamic range of CT in one view, without requiring a change in window and level settings. The potential clinical uses for such an algorithm are described in a pictorial overview, including applications in emergency radiology, oncologic imaging, and nuclear medicine and molecular imaging.

High throughput tools to access images from clinical archives for research.

Historically, medical images collected in the course of clinical care have been difficult to access for secondary research studies. While there is a tremendous potential value in the large volume of studies contained in clinical image archives, Picture Archiving and Communication Systems (PACS) are designed to optimize clinical operations and workflow. Search capabilities in PACS are basic, limiting their use for population studies, and duplication of archives for research is costly. To address this need, we augment the Informatics for Integrating Biology and the Bedside (i2b2) open source software, providing investigators with the tools necessary to query and integrate medical record and clinical research data. Over 100 healthcare institutions have installed this suite of software tools that allows investigators to search medical record metadata including images for specific types of patients. In this report, we describe a new Medical Imaging Informatics Bench to Bedside (mi2b2) module ( www.mi2b2.org ), available now as an open source addition to the i2b2 software platform that allows medical imaging examinations collected during routine clinical care to be made available to translational investigators directly from their institution's clinical PACS for research and educational use in compliance with the Health Insurance Portability and Accountability Act (HIPAA) Omnibus Rule. Access governance within the mi2b2 module is customizable per institution and PACS minimizing impact on clinical systems. Currently in active use at our institutions, this new technology has already been used to facilitate access to thousands of clinical MRI brain studies representing specific patient phenotypes for use in research.

Lung volumes and emphysema in smokers with interstitial lung abnormalities.

BACKGROUND: Cigarette smoking is associated with emphysema and radiographic interstitial lung abnormalities. The degree to which interstitial lung abnormalities are associated with reduced total lung capacity and the extent of emphysema is not known. METHODS: We looked for interstitial lung abnormalities in 2416 (96%) of 2508 high-resolution computed tomographic (HRCT) scans of the lung obtained from a cohort of smokers. We used linear and logistic regression to evaluate the associations between interstitial lung abnormalities and HRCT measurements of total lung capacity and emphysema. RESULTS: Interstitial lung abnormalities were present in 194 (8%) of the 2416 HRCT scans evaluated. In statistical models adjusting for relevant covariates, interstitial lung abnormalities were associated with reduced total lung capacity (-0.444 liters; 95% confidence interval [CI], -0.596 to -0.292; P<0.001) and a lower percentage of emphysema defined by lung-attenuation thresholds of -950 Hounsfield units (-3%; 95% CI, -4 to -2; P<0.001) and -910 Hounsfield units (-10%; 95% CI, -12 to -8; P<0.001). As compared with participants without interstitial lung abnormalities, those with abnormalities were more likely to have a restrictive lung deficit (total lung capacity <80% of the predicted value; odds ratio, 2.3; 95% CI, 1.4 to 3.7; P<0.001) and were less likely to meet the diagnostic criteria for chronic obstructive pulmonary disease (COPD) (odds ratio, 0.53; 95% CI, 0.37 to 0.76; P<0.001). The effect of interstitial lung abnormalities on total lung capacity and emphysema was dependent on COPD status (P<0.02 for the interactions). Interstitial lung abnormalities were positively associated with both greater exposure to tobacco smoke and current smoking. CONCLUSIONS: In smokers, interstitial lung abnormalities--which were present on about 1 of every 12 HRCT scans--were associated with reduced total lung capacity and a lesser amount of emphysema. (Funded by the National Institutes of Health and the Parker B. Francis Foundation; ClinicalTrials.gov number, NCT00608764.).

Estimating patient dose from x-ray tube output metrics: automated measurement of patient size from CT images enables large-scale size-specific dose estimates.

PURPOSE: To test the hypothesis that patient size can be accurately calculated from axial computed tomographic (CT) images, including correction for the effects of anatomy truncation that occur in routine clinical CT image reconstruction. MATERIALS AND METHODS: Institutional review board approval was obtained for this HIPAA-compliant study, with waiver of informed consent. Water-equivalent diameter (D(W)) was computed from the attenuation-area product of each image within 50 adult CT scans of the thorax and of the abdomen and pelvis and was also measured for maximal field of view (FOV) reconstructions. Linear regression models were created to compare D(W) with the effective diameter (D(eff)) used to select size-specific volume CT dose index (CTDI(vol)) conversion factors as defined in report 204 of the American Association of Physicists in Medicine. Linear regression models relating reductions in measured D(W) to a metric of anatomy truncation were used to compensate for the effects of clinical image truncation. RESULTS: In the thorax, D(W)versus D(eff) had an R(2) of 0.51 (n = 200, 50 patients at four anatomic locations); in the abdomen and pelvis, R(2) was 0.90 (n = 150, 50 patients at three anatomic locations). By correcting for image truncation, the proportion of clinically reconstructed images with an extracted D(W) within ±5% of the maximal FOV D(W) increased from 54% to 90% in the thorax (n = 3602 images) and from 95% to 100% in the abdomen and pelvis (6181 images). CONCLUSION: The D(W) extracted from axial CT images is a reliable measure of patient size, and varying degrees of clinical image truncation can be readily corrected. Automated measurement of patient size combined with CT radiation exposure metrics may enable patient-specific dose estimation on a large scale.

Automated critical test result notification system: architecture, design, and assessment of provider satisfaction.

OBJECTIVE: Communicating critical results of diagnostic imaging procedures is a national patient safety goal. The purposes of this study were to describe the system architecture and design of Alert Notification of Critical Results (ANCR), an automated system designed to facilitate communication of critical imaging results between care providers; to report providers' satisfaction with ANCR; and to compare radiologists' and ordering providers' attitudes toward ANCR. MATERIALS AND METHODS: The design decisions made for each step in the alert communication process, which includes user authentication, alert creation, alert communication, alert acknowledgment and management, alert reminder and escalation, and alert documentation, are described. To assess attitudes toward ANCR, internally developed and validated surveys were administered to all radiologists (n = 320) and ordering providers (n = 4323) who sent or received alerts 3 years after ANCR implementation. RESULTS: The survey response rates were 50.4% for radiologists and 36.1% for ordering providers. Ordering providers were generally dissatisfied with the training received for use of ANCR and with access to technical support. Radiologists were more satisfied with documenting critical result communication (61.1% vs 43.2%; p = 0.0001) and tracking critical results (51.6% vs 35.1%; p = 0.0003) than were ordering providers. Both groups agreed use of ANCR reduces medical errors and improves the quality of patient care. CONCLUSION: Use of ANCR enables automated communication of critical test results. The survey results confirm overall provider satisfaction with ANCR but highlight the need for improved training strategies for large numbers of geographically dispersed ordering providers. Future enhancements beyond acknowledging receipt of critical results are needed to help ensure timely and appropriate follow-up of critical results to improve quality and patient safety.

Four-year impact of an alert notification system on closed-loop communication of critical test results.

OBJECTIVE: One of the patient safety goals proposed by the Joint Commission urges hospitals to develop a policy for communicating critical test results and to measure adherence to that policy. We evaluated the impact of an alert notification system on policy adherence for communicating critical imaging test results to referring providers and assessed system adoption over the first 4 years after implementation. MATERIALS AND METHODS: This study was performed in a 753-bed academic medical center. The intervention, an automated alert notification system for critical results, was implemented in January 2010. The primary outcome was adherence to institutional policy for timely closed-loop communication of critical imaging results, and the secondary outcome was system adoption. Policy adherence was determined through manual review of a random sample of radiology reports from the first 4 years after the intervention (n = 37,604) compared with baseline outcomes 1 year before the intervention (n = 9430). Adoption was evaluated by quantifying the use of the system overall and the proportion of alerts that used noninterruptive communication as a percentage of all reports generated by 320 radiologists (n = 1,538,059). A statistical analysis of the trend at 6-month intervals over 4 years was performed using a chi-square trend test. RESULTS: Adherence to the policy increased from 91.3% before the intervention to 95.0% after the intervention (p < 0.0001). There was a ninefold increase in the critical results communicated via the system (chi-square trend test, p < 0.0001). During the first 4 years after the intervention, 41,445 alerts (41% of the total number of alerts) used the system's noninterruptive process for communicating less urgent critical results, which was substantially unchanged over the 4 years postintervention, thus reducing unnecessary paging interruptions. CONCLUSION: An automated alert notification system for communicating critical imaging results was successfully adopted and was associated with increased adherence to institutional policy for communicating critical test results and with reduced workflow interruptions.

Primary care provider perspectives on the value of opportunistic CT screening.

BACKGROUND: Clinical adoption of AI applications requires stakeholders see value in their use. AI-enabled opportunistic-CT-screening (OS) capitalizes on incidentally-detected findings within CTs for potential health benefit. This study evaluates primary care providers' (PCP) perspectives on OS. METHODS: A survey was distributed to US Internal and Family Medicine residencies. Assessed were familiarity with AI and OS, perspectives on potential value/costs, communication of results, and technology implementation. RESULTS: 62 % of respondents (n = 71) were in Family Medicine, 64.8 % practiced in community hospitals. Although 74.6 % of respondents had heard of AI/machine learning, 95.8 % had little-to-no familiarity with OS. The majority reported little-to-no trust in AI. Reported concerns included AI accuracy (74.6 %) and unknown liability (73.2 %). 78.9 % of respondents reported that OS applications would require radiologist oversight. 53.5 % preferred OS results be included in a separate "screening" section within the Radiology report, accompanied by condition risks and management recommendations. The majority of respondents reported results would likely affect clinical management for all queried applications, and that atherosclerotic cardiovascular disease risk, abdominal aortic aneurysm, and liver fibrosis should be included within every CT report regardless of reason for examination. 70.5 % felt that PCP practices are unlikely to pay for OS. Added costs to the patient (91.5 %), the healthcare provider (77.5 %), and unknown liability (74.6 %) were the most frequently reported concerns. CONCLUSION: PCP preferences and concerns around AI-enabled OS offer insights into clinical value and costs. As AI applications grow, feedback from end-users should be considered in the development of such technology to optimize implementation and adoption. Increasing stakeholder familiarity with AI may be a critical prerequisite first step before stakeholders consider implementation.

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.

A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.