Holmes, David R.

Abstract Background/Purpose Diagnosing wrist ligament injuries is challenging; early detection and treatment are important to prevent osteoarthritis progression. Interosseous proximity maps, a proxy measure for joint space, can be generated from volumetric imaging data and may provide important information about wrist health. Artificial intelligence (AI) could enhance accuracy of noninvasive diagnosis based on imaging-derived metrics. This work demonstrates feasibility of AI training using synthetic proximity map data generated from finite element models (FEMs). Methods Personalized wrist FEMs for two asymptomatic participants were created from four-dimensional computed tomography-derived anatomic and kinematic data. Monte Carlo sampling varied 22 ligament material properties and simulated 7,500 unique injury scenarios generating 9,000,000 labeled red, green, and blue (RGB) images of interosseous proximity vector fields from FEM-derived motions. Images were associated with 17 descriptive metrics, including gross wrist angles and bone surface pairs, and used to develop mixed-input convolutional neural networks (CNNs). Model performance was evaluated for identifying specific ligament injuries. Results Average area under receiver operating characteristic curve (AUROC) for CNNs was 0.757 across all injury types and kinematics. In a subset with clinically-relevant functional angles, the average AUROC was 0.824. Best-performing individual ligament AUROCs ranged from 0.807 to 0.999. Sensitivities and specificities exceeded 0.99 for some ligament injury simulations under specific wrist angles and bone surface pairs. Conclusion This study demonstrates the feasibility of using synthetic data from FEMs to train AI models for classifying wrist ligament injuries. Proximity-based RGB images may be a relevant biomarker of ligamentous injury.

Abstract Growing evidence has demonstrated the clinical benefit of percutaneous left atrial appendage closure (LAAC) in patients with atrial fibrillation. Although procedural complication rates have declined with increasing experience, post-procedural device-related complications persist, impacting prognosis and reducing the long-term benefits of the procedure. Given the potential impact of these complications, surveillance imaging after LAAC is mandatory. Currently, different imaging modalities offer unique advantages to manage these complications which warrant a combined approach to optimize both short- and long-term follow-up. The aims of this review are to explore the distinct characteristics of each imaging modality, highlighting the primary findings to be assessed during follow-up imaging. Additionally, we propose an optimized clinical imaging surveillance roadmap from discharge to long-term follow-up.

Background SynthesiZed Improved Resolution and Concurrent nOise reductioN (ZIRCON) is a multi-kernel synthesis method that creates a single series of thin-slice computed tomography (CT) images displaying low noise and high spatial resolution, increasing reader efficiency and minimizing partial volume averaging. Purpose To compare the diagnostic performance of a single set of ZIRCON images to two routine clinical image series using conventional CT head and bone reconstruction kernels for diagnosing intracranial findings and fractures in patients with trauma or suspected acute neurologic deficit. Material and Methods In total, 50 patients underwent clinically indicated head CT in the ER (15 normal, 35 abnormal cases). A non-reader neuroradiologist established the reference standard. Three neuroradiologists reviewed two routine clinical series (head and bone kernels) and a single ZIRCON series, detecting intracranial findings or fractures and rating confidence (0–100). Sensitivity, specificity, and jackknife free-response receiver operating characteristic (JAFROC) figure of merit (FOM) were compared (limit of non-inferiority: −0.10). Results ZIRCON and conventional images demonstrated comparable performance for fractures (sensitivity: 51.5% vs. 54.5%; specificity: 40.2% vs. 34.2%) and intracranial findings (sensitivity: 88.2% vs. 91.4%; specificity: 77.2% vs. 73.7%).The estimated difference of JAFROC FOM demonstrated ZIRCON non-inferiority for acute pathologies overall (0.003 [95% CI=−0.051–0.057]) and fractures (0.048 [95% CI=−0.050–0.145]) but not for intracranial findings alone (−0.024 [95% CI=−0.100–0.052]). Conclusion Thin-slice, low noise, and high spatial resolution images can be created to display intracranial findings and fractures replacing multiple images series in head CT with similar performance. Future studies in more patients and further algorithmic development are warranted.

Background: The compensatory reserve metric (CRM) provides a novel marker of hemodynamic status in prediction of sudden cardiovascular decompensation during central hypovolemia. The CRM has previously been calculated using arterial waveforms obtained from a photoplethysmographic volume-clamp technique. However, the in-field use of pulse oximetry is becoming more prominent in research and medicine. To improve in-field applicability of the CRM, this project aimed to validate pulse-oximetry derived CRM values relative to physiologic data during simulated hemorrhage through application of lower body negative pressure (LBNP). Methods: Forty-nine healthy adults (25 females) underwent a graded LBNP protocol with the following 5-minute stages: -0, -15, -30, -45, -60, -70, -80, -90, and 100 mmHg, or until the onset of pre-syncopal symptoms (tolerance) was reached. Arterial waveforms were sampled using pulse oximetry (Massimo Radical 7). The CRM was calculated using a validated one-dimensional convolutional neural network. A brachial artery catheter was used to measure intraarterial pressure. A 3-lead ECG was used to measure heart rate. SpO2 was measured using pulse oximetry. Cardiac output and stroke volume were estimated using the photoplethysmographic volume-clamp. Data were binned for the last thirty seconds of each completed stage, and at tolerance. Fixed-effect linear mixed models with repeated measures were used to examine the association between CRM values and physiologic variables. A priori significance was set at P<0.05. Results: The median LBNP stage reached was 70 mmHg (Range: 45-100 mmHg). Relative to baseline, at tolerance there was a 50±12% ( P<0.001) mean reduction in stroke volume, 65±27% ( P<0.001) increase in heart rate, 18±8% ( P<0.001) reduction in mean arterial pressure, 21±7% ( P<0.001) systolic blood pressure, 8±9% ( P<0.001) diastolic blood pressure, and 39±12% ( P<0.001) pulse pressure. The CRM obtained using pulse oximetry was significantly associated with a reduction in stroke volume ( P<0.001), increase in heart rate ( P<0.001), and reductions in systolic ( P=0.033), diastolic ( P=0.036), and pulse pressure ( P=0.002). There was no statistically significant association between CRM and cardiac output ( P=0.421), SpO2 ( P=0.408), or mean arterial pressure ( P=0.214). Conclusion: The CRM obtained using pulse oximetry may be a valid, reliable marker of hemodynamic status with promising in-field applications. Future studies warrant investigation of feasibility and applicability within various contexts ranging from the operating room to the battlefield. The presented work was funded in part by the Congressionally Directed Medical Research Program (Award No. DM180240) and Offce of Naval Research (Awards No. N00014-18-D-7001 and N00014-19-C-2017). This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Abstract Percutaneous Coronary Intervention (PCI) is a widely utilized standard ofcare and efficacious intervention in the management of coronary artery disease,improving prognosis and symptoms for many patients. Prediction of post-PCIoutcomes contributes to effective patient management and quality improvementinitiatives in healthcare. Our study focuses on comparative performance analysisfor state-of-the-art vision transformer (ViT) and convolutional neural network(CNN) on multimodal data analysis in a joint fusion framework. We integrateimages of electrocardiogram (ECG) data and tabular electronic health records(EHR) to predict 3 clinically relevant post-PCI (6 months) endpoints - heart failure hospitalization, all-cause mortality, and ischemic stroke. To design a comparativemodel for ViT, we proposed a new joint fusion architecture that consistsof a convolutional neural network (CNN) with a convolutional block attentionmodule (CBAM). The learned representations are combined at an intermediatelayer followed by processing these representations using a fully connectedlayer. The proposed model demonstrates excellent performance with the highestAUROC scores of 0.849, 0.913, and 0.794 for predicting heart failure hospitalization,all-cause mortality, and stroke, respectively. Surpassing the baseline EHRmodel and ViT, the proposed CNN+CBAM fusion model showcases superiorpredictive capabilities for heart failure prediction.

Objective Preeclampsia, a hypertensive pregnancy disorder, increases the risk for cardiovascular disease including coronary artery calcification (CAC) as women age. Controversy exists regarding the relationship between bone mineral density (BMD) and CAC in menopausal women. This study was designed to determine and compare the relationship between BMD and CAC in postmenopausal women with defined histories of either normotensive or preeclamptic pregnancies. Methods Women who gave birth in Olmsted County, MN between 1976 and 1982 were identified from their medical record as having a preeclamptic pregnancy (PE, n=40) and were age/parity‐matched with women having normotensive pregnancies (NP, n=40). The study was approved by the IRB at Mayo Clinic and all participants gave written informed consent. Quantitative Computed Tomography was used to assess vertebral (T7‐9) BMD and CAC. Statistical analyses included linear regression with general estimating equation (GEE) to correct for within‐subject correlations. Results Women averaged 35 years since the index pregnancy and were 60 years of age at the time of the study. CAC was significantly greater in women of the PE group (median (25 th , 75 th percentiles: 0 (0, 0.3) NP and 0 (0, 25) PE, P=0.026). There were no significant differences in cortical, trabecular or central BMD between PE and NP groups. However, there was a positive correlation between cortical BMD and CAC in the PE group (ρ=0.336, P=0.042) and a negative correlation between central BMD and CAC in the NP group (ρ=−0.392, P=0.017). Conclusions Although CAC was greater in women with a history PE, BMD did not differ from women with a history of NP. Associations between cortical and central BMD with CAC differed by pregnancy history suggesting that there may be underlying differences in calcium metabolism associated with PE. Support or Funding Information This work was funded by grants from the NIH AG44170, AG034676, UL1 TR000135 and the Mayo Foundation.

AbstractPurposeEye‐tracking approaches have been used to understand the visual search process in radiology. However, previous eye‐tracking work in computer tomography (CT) has been limited largely to single cross‐sectional images or video playback of the reconstructed volume, which do not accurately reflect radiologists' visual search activities and their interactivity with three‐dimensional image data at a computer workstation (e.g., scroll, pan, and zoom) for visual evaluation of diagnostic imaging targets. We have developed a platform that integrates eye‐tracking hardware with in‐house‐developed reader workstation software to allow monitoring of the visual search process and reader‐image interactions in clinically relevant reader tasks. The purpose of this work is to validate the spatial accuracy of eye‐tracking data using this platform for different eye‐tracking data acquisition modes.MethodsAn eye‐tracker was integrated with a previously developed workstation designed for reader performance studies. The integrated system captured real‐time eye movement and workstation events at 1000 Hz sampling frequency. The eye‐tracker was operated either in head‐stabilized mode or in free‐movement mode. In head‐stabilized mode, the reader positioned their head on a manufacturer‐provided chinrest. In free‐movement mode, a biofeedback tool emitted an audio cue when the head position was outside the data collection range (general biofeedback) or outside a narrower range of positions near the calibration position (strict biofeedback). Four radiologists and one resident were invited to participate in three studies to determine eye‐tracking spatial accuracy under three constraint conditions: head‐stabilized mode (i.e., with use of a chin rest), free movement with general biofeedback, and free movement with strict biofeedback. Study 1 evaluated the impact of head stabilization versus general or strict biofeedback using a cross‐hair target prior to the integration of the eye‐tracker with the image viewing workstation. In Study 2, after integration of the eye‐tracker and reader workstation, readers were asked to fixate on targets that were randomly distributed within a volumetric digital phantom. In Study 3, readers used the integrated system to scroll through volumetric patient CT angiographic images while fixating on the centerline of designated blood vessels (from the left coronary artery to dorsalis pedis artery). Spatial accuracy was quantified as the offset between the center of the intended target and the detected fixation using units of image pixels and the degree of visual angle.ResultsThe three head position constraint conditions yielded comparable accuracy in the studies using digital phantoms. For Study 1 involving the digital crosshairs, the median ± the standard deviation of offset values among readers were 15.2 ± 7.0 image pixels with the chinrest, 14.2 ± 3.6 image pixels with strict biofeedback, and 19.1 ± 6.5 image pixels with general biofeedback. For Study 2 using the random dot phantom, the median ± standard deviation offset values were 16.7 ± 28.8 pixels with use of a chinrest, 16.5 ± 24.6 pixels using strict biofeedback, and 18.0 ± 22.4 pixels using general biofeedback, which translated to a visual angle of about 0.8° for all three conditions. We found no obvious association between eye‐tracking accuracy and target size or view time. In Study 3 viewing patient images, use of the chinrest and strict biofeedback demonstrated comparable accuracy, while the use of general biofeedback demonstrated a slightly worse accuracy. The median ± standard deviation of offset values were 14.8 ± 11.4 pixels with use of a chinrest, 21.0 ± 16.2 pixels using strict biofeedback, and 29.7 ± 20.9 image pixels using general biofeedback. These corresponded to visual angles ranging from 0.7° to 1.3°.ConclusionsAn integrated eye‐tracker system to assess reader eye movement and interactive viewing in relation to imaging targets demonstrated reasonable spatial accuracy for assessment of visual fixation. The head‐free movement condition with audio biofeedback performed similarly to head‐stabilized mode.

Background: The CABANA trial (Catheter Ablation Versus Antiarrhythmic Drug Therapy for Atrial Fibrillation) was a randomized, prospective trial of left atrial catheter ablation versus drug therapy for treatment of atrial fibrillation (AF). As part of CABANA, a prospective imaging substudy was conducted. The main objectives were to describe the patterns of changes in the dimensions of the left atrium and pulmonary veins (PVs), and the relationship between these changes with treatment assignment and clinical outcomes. Methods: Computed tomography or magnetic resonance imaging was acquired at baseline and follow-up in 121 ablation (median follow-up 101 days) and 85 drug patients (median follow-up 97 days). Left atrial volume index, mean PV ostial diameter, and ostial diameters of each PV separately were computed. We examined the relationship between the change from baseline to follow-up with subsequent clinical outcomes (composite of death, disabling stroke, serious bleeding, or cardiac arrest [CABANA primary end point], total mortality or cardiovascular hospitalization, first AF recurrence after the 90-day blanking period, first AF/atrial flutter/atrial tachycardia after the 90-day blanking period) using Cox proportional-hazards models. Results: The median (25th to 75th) change from baseline for left atrial volume index was −7.8 mL/m 2 (−16.4 to 0.2), ablation arm and −3.5 mL/m 2 (−11.4 to 2.6), drug therapy arm. The left atrial volume index decreased in 52.9% of ablation patients versus 40.0% of drug therapy patients. Change for mean PV was −2.7 mm (−4.2 to −1.3) in the ablation arm versus −0.1 mm (−1.5 to 0.8) in the drug therapy arm. Changes in left atrium and PV dimensions had no consistent relationship with the risk of developing the study primary end point. Reductions in left atrial volume index, and in mean PV diameter were associated with decreased risk of AF recurrence. Conclusions: Ablation patients demonstrated more frequent and larger atrial structural changes compared with drug patients. These changes suggest a critical relationship between structural features and AF generation.