Search

Automated screening for vertebral fractures could improve outcomes. We achieved an AUC-ROC = 0.968 for the prediction of moderate to severe fracture using a GAM with age and three maximal vertebral body scores of fracture from a convolutional neural network. Maximal fracture scores resulted in a performant model for subject-level fracture prediction. Combining individual deep learning vertebral body fracture scores and demographic covariates for subject-level classification of osteoporotic fracture achieved excellent performance (AUC-ROC of 0.968) on a large dataset of radiographs with basic demographic data., Purpose: Osteoporotic vertebral fractures are common and morbid. Automated opportunistic screening for incidental vertebral fractures from radiographs, the highest volume imaging modality, could improve osteoporosis detection and management. We consider how to form patient-level fracture predictions and summarization to guide management, using our previously developed vertebral fracture classifier on segmented radiographs from a prospective cohort study of US men (MrOS). We compare the performance of logistic regression (LR) and generalized additive models (GAM) with combinations of individual vertebral scores and basic demographic covariates., Methods: Subject-level LR and GAM models were created retrospectively using all fracture predictions or summary variables such as order statistics, adjacent vertebral interactions, and demographic covariates (age, race/ethnicity). The classifier outputs for 8663 vertebrae from 1176 thoracic and lumbar radiographs in 669 subjects were divided by subject to perform stratified fivefold cross-validation. Models were assessed using multiple metrics, including receiver operating characteristic (ROC) and precision-recall (PR) curves., Results: The best model (AUC-ROC = 0.968) was a GAM using the top three maximum vertebral fracture scores and age. Using top-ranked scores only, rather than all vertebral scores, improved performance for both model classes. Adding age, but not ethnicity, to the GAMs improved performance slightly., Conclusion: Maximal vertebral fracture scores resulted in the highest-performing models. While combining multiple vertebral body predictions risks decreasing specificity, our results demonstrate that subject-level models maintain good predictive performance. Thresholding strategies can be used to control sensitivity and specificity as clinically appropriate., (© 2024. International Osteoporosis Foundation and Bone Health and Osteoporosis Foundation.)

Purpose: Osteoporotic vertebral compression fractures (OVCFs) are a highly prevalent source of morbidity and mortality, and preventive treatment has been demonstrated to be both effective and cost effective. To take advantage of the information available on existing chest and abdominal radiographs, the authors' study group has developed software to access these radiographs for OVCFs with high sensitivity and specificity using an established artificial intelligence deep learning algorithm. The aim of this analysis was to assess the potential cost-effectiveness of implementing this software., Methods: A deterministic expected-value cost-utility model was created, combining a tree model and a Markov model, to compare the strategies of opportunistic screening for OVCFs against usual care. Total costs and total quality-adjusted life-years were calculated for each strategy. Screening and treatment costs were considered from a limited societal perspective, at 2022 prices., Results: In the base case, assuming a cost of software implantation of $10 per patient screened, the screening strategy dominated the nonscreening strategy: it resulted in lower cost and increased quality-adjusted life-years. The lower cost was due primarily to the decreased costs associated with fracture treatment and decreased probability of requiring long-term care in patients who received preventive treatment. The screening strategy was dominant up to a cost of $46 per patient screened., Conclusions: Artificial intelligence-based opportunistic screening for OVCFs on existing radiographs can be cost effective from a societal perspective., (Published by Elsevier Inc.)

Background and Purpose: Vertebral compression fractures may indicate osteoporosis but are underdiagnosed and underreported by radiologists. We have developed an ensemble of vertebral body (VB) segmentation models for lateral radiographs as a critical component of an automated, opportunistic screening tool. Our goal is to detect the approximate location of thoracic and lumbar VBs, including fractured vertebra, on lateral radiographs., Materials and Methods: The Osteoporotic Fractures in Men Study (MrOS) data set includes spine radiographs of 5994 men aged ≥65 years from 6 clinical centers. Two segmentation models, U-Net and Mask-RCNN (Region-based Convolutional Neural Network), were independently trained on the MrOS data set retrospectively, and an ensemble was created by combining them. Primary performance metrics for VB detection success included precision, recall, and F1 score for object detection on a held-out test set. Intersection over union (IoU) and Dice coefficient were also calculated as secondary metrics of performance for the test set. A separate external data set from a quaternary health care enterprise was acquired to test generalizability, comprising diagnostic clinical radiographs from men and women aged ≥65 years., Results: The trained models achieved F1 score of U-Net = 83.42%, Mask-RCNN = 86.30%, and ensemble = 88.34% in detecting all VBs, and F1 score of U-Net = 87.88%, Mask-RCNN = 92.31%, and ensemble = 97.14% in detecting severely fractured vertebrae. The trained models achieved an average IoU per VB of 0.759 for U-Net and 0.709 for Mask-RCNN. The trained models achieved F1 score of U-Net = 81.11%, Mask-RCNN = 79.24%, and ensemble = 87.72% in detecting all VBs in the external data set., Conclusions: An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development., (© 2024 by American Journal of Neuroradiology.)

With promising artificial intelligence (AI) algorithms receiving FDA clearance, the potential impact of these models on clinical outcomes must be evaluated locally before their integration into routine workflows. Robust validation infrastructures are pivotal to inspecting the accuracy and generalizability of these deep learning algorithms to ensure both patient safety and health equity. Protected health information concerns, intellectual property rights, and diverse requirements of models impede the development of rigorous external validation infrastructures. The authors propose various suggestions for addressing the challenges associated with the development of efficient, customizable, and cost-effective infrastructures for the external validation of AI models at large medical centers and institutions. The authors present comprehensive steps to establish an AI inferencing infrastructure outside clinical systems to examine the local performance of AI algorithms before health practice or systemwide implementation and promote an evidence-based approach for adopting AI models that can enhance radiology workflows and improve patient outcomes., (Copyright © 2024 American College of Radiology. Published by Elsevier Inc. All rights reserved.)

Rationale and Objectives: Spinal osteoporotic compression fractures (OCFs) can be an early biomarker for osteoporosis but are often subtle, incidental, and underreported. To ensure early diagnosis and treatment of osteoporosis, we aimed to build a deep learning vertebral body classifier for OCFs as a critical component of our future automated opportunistic screening tool., Materials and Methods: We retrospectively assembled a local dataset, including 1790 subjects and 15,050 vertebral bodies (thoracic and lumbar). Each vertebral body was annotated using an adaption of the modified-2 algorithm-based qualitative criteria. The Osteoporotic Fractures in Men (MrOS) Study dataset provided thoracic and lumbar spine radiographs of 5994 men from six clinical centers. Using both datasets, five deep learning algorithms were trained to classify each individual vertebral body of the spine radiographs. Classification performance was compared for these models using multiple metrics, including the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and positive predictive value (PPV)., Results: Our best model, built with ensemble averaging, achieved an AUC-ROC of 0.948 and 0.936 on the local dataset's test set and the MrOS dataset's test set, respectively. After setting the cutoff threshold to prioritize PPV, this model achieved a sensitivity of 54.5% and 47.8%, a specificity of 99.7% and 99.6%, and a PPV of 89.8% and 94.8%., Conclusion: Our model achieved an AUC-ROC>0.90 on both datasets. This testing shows some generalizability to real-world clinical datasets and a suitable performance for a future opportunistic osteoporosis screening tool., Competing Interests: Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Nathan Cross, Qifei Dong, Sandra Johnston, Jessica Perry, and David Haynor report financial support was provided by the National Institute of Arthritis and Musculoskeletal and Skin Diseases. Gang Luo reports financial support was provided by the National Institute of Arthritis and Musculoskeletal and Skin Diseases and National Heart Lung and Blood Institute. Jeffrey Jarvik reports financial support was provided by the National Institute of Arthritis and Musculoskeletal and Skin Diseases and reports a relationship with the General Electric-Association of University Radiologists Radiology Research Academic Fellowship (GERRAF) that includes travel reimbursement. Nathan Cross reports financial support was provided by the General Electric-Association of University Radiologists Radiology Research Academic Fellowship (GERRAF). Nathan M. Cross, Jeffrey Jarvik, David R. Haynor, Gang Luo, Sandra Johnston, Qifei Dong, Jonathan Renslo, Brian Chang, and Jessica Perry have patent #63/463823 pending to the University of Washington., (Copyright © 2023 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Purpose: Many MRI sequences are sensitive to motion and its associated artifacts. The linearized geometric solution (LGS), a balanced steady-state free precession (bSSFP) off-resonance signal demodulation technique, is evaluated with respect to motion artifact resilience., Theory and Methods: The mechanism and extent of LGS motion artifact resilience is examined in simulated, flow phantom, and in vivo clinical imaging. Motion artifact correction capabilities are decoupled from susceptibility artifact correction when feasible to permit controlled analysis of motion artifact correction when comparing the LGS with standard and phase-cycle-averaged (complex sum) bSSFP imaging., Results: Simulations reveal that the LGS demonstrates motion artifact reduction capabilities similar to standard clinical bSSFP imaging techniques, with slightly greater resilience in high SNR regions and for shorter-duration motion. Flow phantom experiments assert that the LGS reduces shorter-duration motion artifact error by ∼24%-65% relative to the complex sum, whereas reconstructions exhibit similar error reduction for constant motion. In vivo analysis demonstrates that in the internal auditory canal/orbits, the LGS was deemed to have less artifact in 24%/49% and similar artifact in 76%/51% of radiological assessments relative to the complex sum, and the LGS had less artifact in 97%/81% and similar artifact in 3%/16% of assessments relative to standard bSSFP. Only 2 of 63 assessments deemed the LGS inferior to either complex sum or standard bSSFP in terms of artifact reduction., Conclusion: The LGS provides sufficient bSSFP motion artifact resilience to permit robust elimination of susceptibility artifacts, inspiring its use in a wide variety of applications., (© 2022 International Society for Magnetic Resonance in Medicine.)

Currently, there is no reproducible, widely accepted gold standard to classify osteoporotic vertebral body fractures (OVFs). The purpose of this study is to refine a method with clear rules to classify OVFs for machine learning purposes. The method was found to have moderate interobserver agreement that improved with training., Introduction: The current methods to classify osteoporotic vertebral body fractures are considered ambiguous; there is no reproducible, accepted gold standard. The purpose of this study is to refine classification methodology by introducing clear, unambiguous rules and a refined flowchart to allow consistent classification of osteoporotic vertebral body fractures., Methods: We developed a set of rules and refinements that we called m2ABQ to classify vertebrae into five categories. A fracture-enriched database of thoracic and lumbar spine radiographs of patients 65 years of age and older was retrospectively obtained from clinical institutional radiology records using natural language processing. Five raters independently classified each vertebral body using the m2ABQ system. After each annotation round, consensus sessions that included all raters were held to discuss and finalize a consensus annotation for each vertebral body where individual raters' evaluations differed. This process led to further refinement and development of the rules., Results: Each annotation round showed increase in Fleiss kappa both for presence vs absence of fracture 0.62 (0.56-0.68) to 0.70 (0.65-0.75), as well as for the whole m2ABQ scale 0.29 (0.25-0.33) to 0.54 (0.51-0.58)., Conclusion: The m2ABQ system demonstrates moderate interobserver agreement and practical feasibility for classifying osteoporotic vertebral body fractures. Future studies to compare the method to existing studies are warranted, as well as further development of its use in machine learning purposes., (© 2022. International Osteoporosis Foundation and Bone Health and Osteoporosis Foundation.)

Rationale and Objectives: Osteoporosis affects 9% of individuals over 50 in the United States and 200 million women globally. Spinal osteoporotic compression fractures (OCFs), an osteoporosis biomarker, are often incidental and under-reported. Accurate automated opportunistic OCF screening can increase the diagnosis rate and ensure adequate treatment. We aimed to develop a deep learning classifier for OCFs, a critical component of our future automated opportunistic screening tool., Materials and Methods: The dataset from the Osteoporotic Fractures in Men Study comprised 4461 subjects and 15,524 spine radiographs. This dataset was split by subject: 76.5% training, 8.5% validation, and 15% testing. From the radiographs, 100,409 vertebral bodies were extracted, each assigned one of two labels adapted from the Genant semiquantitative system: moderate to severe fracture vs. normal/trace/mild fracture. GoogLeNet, a deep learning model, was trained to classify the vertebral bodies. The classification threshold on the predicted probability of OCF outputted by GoogLeNet was set to prioritize the positive predictive value (PPV) while balancing it with the sensitivity. Vertebral bodies with the top 0.75% predicted probabilities were classified as moderate to severe fracture., Results: Our model yielded a sensitivity of 59.8%, a PPV of 91.2%, and an F 1 score of 0.72. The areas under the receiver operating characteristic curve (AUC-ROC) and the precision-recall curve were 0.99 and 0.82, respectively., Conclusion: Our model classified vertebral bodies with an AUC-ROC of 0.99, providing a critical component for our future automated opportunistic screening tool. This could lead to earlier detection and treatment of OCFs., (Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Objective: This study aimed to assess the changes and values on follow-up computed tomography (F/U-CT) for isolated falcine (F-SDH) and tentorial (T-SDH) subdural hematomas (SDHs)., Method: Fifty-four cases of isolated F-SDH and/or T-SDH were retrospectively reviewed. Subdural hematoma morphology, mass effect on the adjacent parenchyma, and interval change at F/U-CT were evaluated. Subdural hematoma size was measured parallel and perpendicular to the falx/tentorium (long or short axis, respectively)., Results: Short-axis increase on F/U-CT was seen only in 5 F-SDHs (16%) and 7 T-SDHs (19%), with a maximum of a 2-mm increase. Long-axis growth was more prominent and frequent, seen in 18 F-SDH patients (56.2%) and 19 T-SDH patients (51.4%), with maximum change of up to 43 mm. Falcine SDH and T-SDH were ipsilateral and contiguous in 77.8% of patients. Minimal mass effect was seen in 13 patients (24.1%), which was resolved or stable on F/U-CT. Anticoagulation did not affect SDH size. No patients required neurosurgery or died., Conclusions: Based on our limited data, the current standard of F/U-CT may be unnecessary in patients with isolated F-SDH and/or T-SDH, which expand minimally along the short axis without a significant mass effect. Characteristic anatomic structure of the tentorium and falx, and their connectivity may direct SDH expansion and limit mass effect as well as injury to the adjacent parenchyma., Competing Interests: The authors declare no conflict of interest., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.)

Objective: We reviewed the literature to describe outcomes associated with abnormal neuroimaging findings among adult COVID-19 patients., Methods: We performed a systematic literature review using PubMed and Embase databases. We included all studies reporting abnormal neuroimaging findings among hospitalized patients with confirmed COVID-19 and outcomes. Data elements including patient demographics, neuroimaging findings, acuity of neurological symptoms and/or imaging findings relative to COVID-19 onset (acute, subacute, chronic), and patient outcomes were recorded and summarized., Results: After review of 775 unique articles, a total of 39 studies comprising 884 COVID-19 patients ≥ 18 years of age with abnormal neuroimaging findings and reported outcomes were included in our analysis. Ischemic stroke was the most common neuroimaging finding reported (49.3%, 436/884) among patients with mortality outcomes data. Patients with intracranial hemorrhage (ICH) had the highest all-cause mortality (49.7%, 71/143), followed by patients with imaging features consistent with leukoencephalopathy (38.5%, 5/13), and ischemic stroke (30%, 131/436). There was no mortality reported among COVID-19 patients with acute disseminated encephalomyelitis without necrosis (0%, 0/8) and leptomeningeal enhancement alone (0%, 0/12). Stroke was a common acute or subacute neuroimaging finding, while leukoencephalopathy was a common chronic finding., Conclusion: Among hospitalized COVID-19 patients with abnormal neuroimaging findings, those with ICH had the highest all-cause mortality; however, high mortality rates were also seen among COVID-19 patients with ischemic stroke in the acute/subacute period and leukoencephalopathy in the chronic period., Advances in Knowledge: Specific abnormal neuroimaging findings may portend differential mortality outcomes, providing a potential prognostic marker for hospitalized COVID-19 patients.

The purpose of this review is to understand the role of imaging in the diagnosis and management of non-traumatic subarachnoid hemorrhage (SAH). SAH is a life-threatening emergency and a relatively common entity, the most common etiology being ruptured aneurysms. Multiple conundrums exist in literature at various steps of its imaging workup: diagnosis, management, and follow-up. We target our review to highlight the most effective practice and suggest efficient workup plans based on literature search, and describe in detail the clinical diagnostic and prognostic scales, role of CT scan, lumbar puncture, and MR, including angiography in the diagnosis and workup of SAH and its complications, and try to simplify the conundrums. Practical knowledge of imaging workup of SAH can help guide correct management of these patients, so as to reduce morbidity and mortality without resource overutilization., (© 2021. American Society of Emergency Radiology.)

Manufacturing technologies continue to be developed and utilized in medical prototyping, simulations, and imaging phantom production. For radiologic image-guided simulation and instruction, models should ideally have similar imaging characteristics and physical properties to the tissues they replicate. Due to the proliferation of different printing technologies and materials, there is a diverse and broad range of approaches and materials to consider before embarking on a project. Although many printed materials' biomechanical parameters have been reported, no manufacturer includes medical imaging properties that are essential for realistic phantom production. We hypothesize that there are now ample materials available to create high-fidelity imaging anthropomorphic phantoms using 3D printing and casting of common commercially available materials. A material database of radiological, physical, manufacturing, and economic properties for 29 castable and 68 printable materials was generated from samples fabricated by the authors or obtained from the manufacturer and scanned with CT at multiple tube voltages. This is the largest study assessing multiple different parameters associated with 3D printing to date. These data are being made freely available on GitHub, thus affording medical simulation experts access to a database of relevant imaging characteristics of common printable and castable materials. Full data available at: https://github.com/nmcross/Material-Imaging-Characteristics .

Patients and patient advocates express a desire to speak directly with radiologists, who are ideally suited to answer imaging-related questions and recommend for further imaging or testing. While web-based patient portals have improved patient access to reports of radiology examinations, they do little to help patients understand the report, and rarely facilitate contact with their radiologists. We implemented an alias phone number that forwarded to the smartphone of each participating radiologist and embedded it in 3896 reports over 8 months. It was embedded as an invitation to the individual viewing the report to call with questions. For each call received, we logged parameters such as call duration, call reason, and required radiologist time/resources. Finally, the call was documented in the electronic medical record. Radiologists received 27 calls exclusively about cross-sectional exams: 22 from patients or caregivers, and 5 from physicians. The reasons for the calls included term definitions, correction of dictation errors, findings not specifically mentioned, and clinical impact of findings. Time spent on the phone with patients averaged 8.6 min. When including the time spent reviewing the images, patient chart, and/or literature; the total radiologist time per call was approximately 13.9 min. Averaged over all of the exams in the study, this service added 5 s to each exam. While the total call rate was low, implementation of this program required minimal effort. The aliased phone number masked the radiologist's phone number and allowed scheduled consultation hours. Even when called, the time to address questions appears to be minimal., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Background and Purpose: Motion artifacts are a frequent source of image degradation in the clinical application of MR imaging (MRI). Here we implement and validate an MRI motion-artifact correction method using a multiscale fully convolutional neural network., Materials and Methods: The network was trained to identify motion artifacts in axial T2-weighted spin-echo images of the brain. Using an extensive data augmentation scheme and a motion artifact simulation pipeline, we created a synthetic training dataset of 93,600 images based on only 16 artifact-free clinical MRI cases. A blinded reader study using a unique test dataset of 28 additional clinical MRI cases with real patient motion was conducted to evaluate the performance of the network., Results: Application of the network resulted in notably improved image quality without the loss of morphologic information. For synthetic test data, the average reduction in mean squared error was 41.84%. The blinded reader study on the real-world test data resulted in significant reduction in mean artifact scores across all cases ( P  < .03)., Conclusions: Retrospective correction of motion artifacts using a multiscale fully convolutional network is promising and may mitigate the substantial motion-related problems in the clinical MRI workflow., (© 2020 by American Journal of Neuroradiology.)

Background and Purpose: Compressed sensing-sensitivity encoding is a promising MR imaging acceleration technique. This study compares the image quality of compressed sensing-sensitivity encoding accelerated imaging with conventional MR imaging sequences., Materials and Methods: Patients with known, treated, or suspected brain tumors underwent compressed sensing-sensitivity encoding accelerated 3D T1-echo-spoiled gradient echo or 3D T2-FLAIR sequences in addition to the corresponding conventional acquisition as part of their clinical brain MR imaging. Two neuroradiologists blinded to sequence and patient information independently evaluated both the accelerated and corresponding conventional acquisitions. The sequences were evaluated on 4- or 5-point Likert scales for overall image quality, SNR, extent/severity of artifacts, and gray-white junction and lesion boundary sharpness. SNR and contrast-to-noise ratio values were compared., Results: Sixty-six patients were included in the study. For T1-echo-spoiled gradient echo, image quality in all 5 metrics was slightly better for compressed sensing-sensitivity encoding than conventional images on average, though it was not statistically significant, and the lower bounds of the 95% confidence intervals indicated that compressed sensing-sensitivity encoding image quality was within 10% of conventional imaging. For T2-FLAIR, image quality of the compressed sensing-sensitivity encoding images was within 10% of the conventional images on average for 3 of 5 metrics. The compressed sensing-sensitivity encoding images had somewhat more artifacts ( P = .068) and less gray-white matter sharpness ( P = .36) than the conventional images, though neither difference was significant. There was no significant difference in the SNR and contrast-to-noise ratio. There was 25% and 35% scan-time reduction with compressed sensing-sensitivity encoding for FLAIR and echo-spoiled gradient echo sequences, respectively., Conclusions: Compressed sensing-sensitivity encoding accelerated 3D T1-echo-spoiled gradient echo and T2-FLAIR sequences of the brain show image quality similar to that of standard acquisitions with reduced scan time. Compressed sensing-sensitivity encoding may reduce scan time without sacrificing image quality., (© 2019 by American Journal of Neuroradiology.)

MRI is a ubiquitous medical imaging technology typically using superconductivity to generate a strong, homogeneous, and generally ceaseless magnetic field. MRI and its magnetic field pose many safety hazards, including magnetic forces on metals, tissue heating and burns, nerve stimulation, bioeffects, acoustic noise, and contrast agent complications. The primary concern is that a wide variety of patients, staff members, technologists, and physicians can approach the incessant magnetic field, creating great potential for accidents that could occur if metals from the environment, adornments, implants, and other unintended sources are also present in or near the field. Many accidents have occurred and are occasionally reported in the United States and countries all over the world. Through carefully structured oversight and the establishment of strict guidelines regarding access, responsibilities, and training, these risks can be mitigated, and accidents can be prevented. Fortunately, there is currently a wide variety of resources available to facilitate the successful implementation of an effective MRI safety program. This article presents a general overview of and the authors' experience with an MRI safety program in terms of risk management and training. The MR safety program requirements and regulations in the United States devised by The Joint Commission and the ACR are also discussed. With these resources and a carefully selected team, the risk for MRI-related accidents can be vastly reduced if not completely eliminated., (Copyright © 2018 American College of Radiology. Published by Elsevier Inc. All rights reserved.)

Radiologists routinely make decisions with only limited information when assigning protocol instructions for the performance of advanced medical imaging examinations. Opportunity exists to simultaneously improve the safety, quality and efficiency of this workflow through the application of an electronic solution leveraging health system resources to provide concise, tailored information and decision support in real-time. Such a system has been developed using an open source, open standards design for use within the Veterans Health Administration. The Radiology Protocol Tool Recorder (RAPTOR) project identified key process attributes as well as inherent weaknesses of paper processes and electronic emulators of paper processes to guide the development of its optimized electronic solution. The design provides a kernel that can be expanded to create an integrated radiology environment. RAPTOR has implications relevant to the greater health care community, and serves as a case model for modernization of legacy government health information systems.