It is About "Time": Academic Neuroradiologist Time Distribution for Interpreting Brain MRIs

Use of MRI in patients with severe diffuse traumatic brain injury: A matched National Trauma Data Bank analysis

OBJECTIVE

Magnetic resonance imaging (MRI) is increasingly used to evaluate patients with diffuse traumatic brain injury (dTBI). However, the utility of early MRI is understudied. We hypothesize that early MRI patients will have increased length of stay but no changes in intracranial pressure (ICP) management or disposition.

METHODS

The 2019 National Trauma Data Bank was queried for patients with dTBI and Glasgow Coma Scale score ≤8. Extra-axial and focal intra-axial hemorrhages were excluded. Clinical characteristics were controlled for. Patients with and without MRI were compared for ICP management, outcome, mortality, and disposition. A propensity score matching algorithm was used to create a 1:1 match cohort.

RESULTS

In 2568 patients, MRI was less common in severe dTBI patients with clear reasons for poor examination, including bilaterally unreactive pupils or midline shift. After matching, 501 patients who underwent MRI within 1 week were compared with 501 patients without MRI. Magnetic resonance imaging patients had longer intensive care unit stays (11.6 ± 9.6 vs. 13.4 ± 9.5, p < 0.01; 95% confidence interval [95% CI], -3.03 to -0.66). There was no difference between groups in ICP monitor (23.6% vs. 27.3%; p = 0.17; 95% CI, -0.09 to 0.02) or ventriculostomy placement (13.6% vs. 13.2%, p = 0.85; 95% CI, -0.04 to 0.05) or in withdrawal of care (15.0% vs. 18.6%, p = 0.12; 95% CI, -0.08 to 0.01). MRI patients were more likely to be discharged to inpatient rehabilitation (42.9% vs. 33.5%; p < 0.01; 95% CI, 0.03-0.15) but not to home (9.4% vs. 9.0%; p = 0.83; 95% CI, -0.03 to 0.04).

CONCLUSION

The decision to pursue early brain MRI may be driven by lack of obvious reasons for a patient's poor neurologic status. MRI patients had longer intensive care unit stays but no difference in rates of placement of ICP monitors or ventriculostomies or withdrawal of care. Further study is required to define the role of early MRI in dTBI patients.

LEVEL OF EVIDENCE

Prognostic and Epidemiological; Level IV.

"Are They Listening, and Do They Find It Useful?"-Evaluation of Mid-Rotation Formative Subjective and Objective Feedback to Radiology Trainees

BACKGROUND

Residents commonly receive only end-of-rotation evaluations and thus are often unaware of their progress during a rotation. In 2021, our neuroradiology section instituted mid-rotation feedback in which rotating residents received formative subjective and objective feedback. The purpose of this study was to describe our feedback method and to evaluate if residents found it helpful.

METHODS

Radiology residents rotate 3-4 times on the neuroradiology service for 1-month blocks. At the midpoint of the rotation (2 weeks), 7-10 neuroradiology attendings discussed the rotating residents' subjective performance. One attending was tasked with facilitating this discussion and taking notes. Objective metrics were obtained from our dictation software. Compiled feedback was relayed to residents via email. A 16-question anonymous survey was sent to 39 radiology residents (R1-R4) to evaluate the perceived value of mid-rotation feedback. Odds ratios and 95% confidence intervals were computed using logistic regression.

RESULTS

Sixty-nine percent (27/39) of residents responded to the survey; 92.6% (25/27) of residents reported receiving mid-rotation feedback in ≥50% of neuroradiology rotations; 92.3% (24/26) of residents found the subjective feedback helpful; 88.4% (23/26) of residents reported modifying their performance as suggested (100% R1-R2 vs 70% R3-R4; OR: 15.4 CI:1.26, >30.0);59.1% (13/22) of residents found the objective metrics helpful (75% R1-R2 vs 40% R3-R4; OR: 3.92 CI:0.74, 24.39) and 68.2% (15/22) stated they modified their performance based on these metrics (83.3% R1-R2 vs 50.0% R3-R4; OR:4.2 CI:0.73, 30.55); and 84.6% (22/26) of residents stated that mid-rotation subjective feedback and 45.5% (10/22) stated that mid-rotation objective feedback should be implemented in other sections.

CONCLUSIONS

Majority of residents found mid-rotation feedback to be helpful in informing them about their progress and areas for improvement in the neuroradiology rotation, more so for subjective feedback than objective feedback. The majority of residents stated all rotations should provide mid-rotation subjective feedback.

Automatically tracking brain metastases after stereotactic radiosurgery

Background and purpose

Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2-3 months. This study investigated whether it is possible to automatically track BMs on longitudinal imaging and quantify the tumor response after radiotherapy.

Methods

The METRO process (MEtastasis Tracking with Repeated Observations was developed to automatically process patient data and track BMs. A longitudinal intrapatient registration method for T1 MR post-Gd was conceived and validated on 20 patients. Detections and volumetric measurements of BMs were obtained from a deep learning model. BM tracking was validated on 32 separate patients by comparing results with manual measurements of BM response and radiologists' assessments of new BMs. Linear regression and residual analysis were used to assess accuracy in determining tumor response and size change.

Results

A total of 123 irradiated BMs and 38 new BMs were successfully tracked. 66 irradiated BMs were visible on follow-up imaging 3-9 months after radiotherapy. Comparing their longest diameter changes measured manually vs. METRO, the Pearson correlation coefficient was 0.88 (p < 0.001); the mean residual error was -8 ± 17%. The mean registration error was 1.5 ± 0.2 mm.

Conclusions

Automatic, longitudinal tracking of BMs using deep learning methods is feasible. In particular, the software system METRO fulfills a need to automatically track and quantify volumetric changes of BMs prior to, and in response to, radiation therapy.

Brain MRI Deep Learning and Bayesian Inference System Augments Radiology Resident Performance

Automated quantitative and probabilistic medical image analysis has the potential to improve the accuracy and efficiency of the radiology workflow. We sought to determine whether AI systems for brain MRI diagnosis could be used as a clinical decision support tool to augment radiologist performance. We utilized previously developed AI systems that combine convolutional neural networks and expert-derived Bayesian networks to distinguish among 50 diagnostic entities on multimodal brain MRIs. We tested whether these systems could augment radiologist performance through an interactive clinical decision support tool known as Adaptive Radiology Interpretation and Education System (ARIES) in 194 test cases. Four radiology residents and three academic neuroradiologists viewed half of the cases unassisted and half with the results of the AI system displayed on ARIES. Diagnostic accuracy of radiologists for top diagnosis (TDx) and top three differential diagnosis (T3DDx) was compared with and without ARIES. Radiology resident performance was significantly better with ARIES for both TDx (55% vs 30%; P < .001) and T3DDx (79% vs 52%; P = 0.002), with the largest improvement for rare diseases (39% increase for T3DDx; P < 0.001). There was no significant difference between attending performance with and without ARIES for TDx (72% vs 69%; P = 0.48) or T3DDx (86% vs 89%; P = 0.39). These findings suggest that a hybrid deep learning and Bayesian inference clinical decision support system has the potential to augment diagnostic accuracy of non-specialists to approach the level of subspecialists for a large array of diseases on brain MRI.

Am I Ready to Be an Independent Neuroradiologist? Objective Trends in Neuroradiology Fellows' Performance during the Fellowship Year

BACKGROUND AND PURPOSE

Aside from basic Accreditation Council for Graduate Medical Education guidelines, few metrics are in place to monitor fellows' progress. The purpose of this study was to determine objective trends in neuroradiology fellowship training on-call performance during an academic year.

MATERIALS AND METHODS

We retrospectively reviewed the number of cross-sectional neuroimaging studies dictated with complete reports by neuroradiology fellows during independent call. Monthly trends in total call cases, report turnaround times, relationships between volume and report turnaround times, and words addended to preliminary reports by attending neuroradiologists were evaluated with regression models. Monthly variation in frequencies of call-discrepancy macros were assessed via χ² tests. Changes in frequencies of specific macro use between fellowship semesters were assessed via serial 2-sample tests of proportions.

RESULTS

From 2012 to 2017, for 29 fellows, monthly median report turnaround times significantly decreased during the academic year: July (first month) = 79 minutes (95% CI, 71-86 minutes) and June (12th month) = 55 minutes (95% CI, 52-60 minutes; P value = .023). Monthly report turnaround times were inversely correlated with total volumes for CT (r = -0.70, F = 9.639, P value = .011) but not MR imaging. Words addended to preliminary reports, a surrogate measurement of report clarity, slightly improved and discrepancy rates decreased during the last 6 months of fellowship. A nadir for report turnaround times, discrepancy errors, and words addended to reports was seen in December and January.

CONCLUSIONS

Progress through fellowship correlates with a decline in report turnaround times and discrepancy rates for cross-sectional neuroimaging call studies and slight improvement in indirect quantitative measurement of report clarity. These metrics can be tracked throughout the academic year, and the midyear would be a logical time point for programs to assess objective progress of fellows and address any deficiencies.

Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI

Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.

Artificial intelligence for precision education in radiology

In the era of personalized medicine, the emphasis of health care is shifting from populations to individuals. Artificial intelligence (AI) is capable of learning without explicit instruction and has emerging applications in medicine, particularly radiology. Whereas much attention has focused on teaching radiology trainees about AI, here our goal is to instead focus on how AI might be developed to better teach radiology trainees. While the idea of using AI to improve education is not new, the application of AI to medical and radiological education remains very limited. Based on the current educational foundation, we highlight an AI-integrated framework to augment radiology education and provide use case examples informed by our own institution's practice. The coming age of "AI-augmented radiology" may enable not only "precision medicine" but also what we describe as "precision medical education," where instruction is tailored to individual trainees based on their learning styles and needs.