Financial impact of incorporating deep learning reconstruction into magnetic resonance imaging routine.

PURPOSE: Artificial intelligence and deep learning solutions are increasingly utilized in healthcare and radiology. The number of studies addressing their enhancement of productivity and monetary impact is, however, still limited. Our hospital has faced a need to enhance MRI scanner throughput, and we investigate the utility of new commercial deep learning reconstruction (DLR) algorithm for this purpose. In this work, a multidisciplinary team evaluated the impact of the widespread deployment of a new commercial deep learning reconstruction (DLR) algorithm for our magnetic resonance imaging scanner fleet. METHODS: Our analysis centers on the DLR algorithm's effects on patient throughput and investment costs, contrasting these with alternative strategies for capacity expansion-namely, acquiring additional MRI scanners and increasing device utilization on weekends. We provide a framework for assessing the financial implications of new technologies in a trial phase, aiding in informed decision-making for healthcare investments. RESULTS: We demonstrate substantial reductions in total operating costs compared to other capacity-enhancing methods. Specifically, the cost of adopting the deep learning technology for our entire scanner fleet is only 11 % compared to procuring an additional scanner and 20 % compared to the weekend utilization costs of existing devices. CONCLUSIONS: Procuring DLR for our existing five-scanner fleet allows us to sustain our current MRI service levels without the need for an additional scanner, thereby achieving considerable cost savings. These reductions highlight the efficiency and economic viability of DLR in optimizing MRI service delivery.

Semiautomatic Assessment of Facet Tropism From Lumbar Spine MRI Using Deep Learning: A Northern Finland Birth Cohort Study.

STUDY DESIGN: This is a retrospective, cross-sectional, population-based study that automatically measured the facet joint (FJ) angles from T2-weighted axial magnetic resonance imagings (MRIs) of the lumbar spine using deep learning (DL). OBJECTIVE: This work aimed to introduce a semiautomatic framework that measures the FJ angles using DL and study facet tropism (FT) in a large Finnish population-based cohort. SUMMARY OF DATA: T2-weighted axial MRIs of the lumbar spine (L3/4 through L5/S1) for (n=1288) in the NFBC1966 Finnish population-based cohort were used for this study. MATERIALS AND METHODS: A DL model was developed and trained on 430 participants' MRI images. The authors computed FJ angles from the model's prediction for each level, that is, L3/4 through L5/S1, for the male and female subgroups. Inter-rater and intrarater reliability was analyzed for 60 participants using annotations made by two radiologists and a musculoskeletal researcher. With the developed method, we examined FT in the entire NFBC1966 cohort, adopting the literature definitions of FT thresholds at 7° and 10°. The rater agreement was evaluated both for the annotations and the FJ angles computed based on the annotations. FJ asymmetry ( - was used to evaluate the agreement and correlation between the raters. Bland-Altman analysis was used to assess the agreement and systemic bias in the FJ asymmetry. The authors used the Dice score as the metric to compare the annotations between the raters. The authors evaluated the model predictions on the independent test set and compared them against the ground truth annotations. RESULTS: This model scored Dice (92.7±0.1) and intersection over union (87.1±0.2) aggregated across all the regions of interest, that is, vertebral body (VB), FJs, and posterior arch (PA). The mean FJ angles measured for the male and female subgroups were in agreement with the literature findings. Intrarater reliability was high, with a Dice score of VB (97.3), FJ (82.5), and PA (90.3). The inter-rater reliability was better between the radiologists with a Dice score of VB (96.4), FJ (75.5), and PA (85.8) than between the radiologists and the musculoskeletal researcher. The prevalence of FT was higher in the male subgroup, with L4/5 found to be the most affected region. CONCLUSION: The authors developed a DL-based framework that enabled us to study FT in a large cohort. Using the proposed method, the authors present the prevalence of FT in a Finnish population-based cohort.

Assessment of articular cartilage of ankle joint in stable and unstable unilateral weber type-B/SER-type ankle fractures shortly after trauma using T2 relaxation time.

Background: Early detection of post-traumatic cartilage damage in the ankle joint in magnetic resonance images can be difficult due to disturbances to structures usually appearing over time. Purpose: To study the articular cartilage of unilateral Weber type-B/SER-type ankle fractures shortly post-trauma using T2 relaxation time. Material and Methods: Fifty one fractured ankles were gathered from consecutively screened patients, compiled initially for RCT studies, and treated at Oulu University Hospital and classified as stable (n = 28) and unstable fractures (n = 23) based on external-rotation stress test: medial clear space of ≥5 mm was interpreted as unstable. A control group of healthy young individuals (n = 19) was also gathered. All ankles were imaged on average 9 (range: 1 to 25) days after injury on a 3.0T MRI unit for T2 relaxation time assessment, and the cartilage was divided into sub-regions for comparison. Results: Control group displayed significantly higher T2 values in tibial cartilage compared to stable (six out of nine regions, p-values = .003-.043) and unstable (six out of nine regions, p-values = .001-.037) ankle fractures. No differences were detected in talar cartilage. Also, no differences were observed between stable and unstable fractures in tibial or talar cartilage. Conclusions: Lower T2 relaxation times of tibial cartilage in fractured ankles suggest intact extra cellular matrix (ECM) of the cartilage. Severity of the ankle fracture, measured by ankle stability, does not seem to increase ECM degradation immediately after trauma.

Detecting Patient Safety Errors by Characterizing Incidents Reported by Medical Imaging Staff.

The objectives of the study were to characterize events related to patient safety reported by medical imaging personnel in Finland in 2007-2017, the number and quality of reported injuries, the risk assessment, and the planned improvement of operations. The information was collected from a healthcare patient safety incident register system. The data contained information on the nature of the patient safety errors, harms and near-misses in medical imaging, the factors that lead to the events, the consequences for the patient, the level of risks, and future measures. The number of patient safety incident reports included in the study was 7,287. Of the incident reports, 75% concerned injuries to patients and 25% were near-misses. The most common consequence of adverse events and near-misses were minor harm (37.2%) related to contrast agent, or no harm (27.9%) related to equipment malfunction. Supervisors estimated the risks as low (47.7%) e.g., data management, insignificant (35%) e.g., verbal communication or moderate (15.7%) e.g., the use of contrast agent. The most common suggestion for learning from the incident was discussing it with the staff (58.1%), improving operations (5.7%) and submitting it to a higher authority (5.4%). Improving patient safety requires timely, accurate and clear reporting of various patient safety incidents. Based on incident reports, supervisors can provide feedback to staff, develop plans to prevent accidents, and monitor the impact of measures taken. Information on the development of occupational safety should be disseminated to all healthcare professionals so that the same mistakes are not repeated.

Stability assessment of the ankle mortise in supination-external rotation-type ankle fractures: lack of additional diagnostic value of MRI.

BACKGROUND: This prospective diagnostic study assessed the utility of MRI (magnetic resonance imaging) findings for the deep aspect of the deltoid ligament in evaluating the stability of the ankle mortise in patients who have an SER (supination-external rotation)-type lateral malleolar fracture with no widening of the medial clear space. METHODS: Sixty-one patients with a unilateral lateral malleolar fracture resulting from an SER mechanism were enrolled. Two surgeons assessed the stability of the ankle mortise with use of an external-rotation stress test. The anterior and posterior parts of the deep deltoid ligament were investigated with 3.0-T MRI and were graded (as normal, edematous, partial tear, or complete tear) by two musculoskeletal radiologists. The medial clear space was measured and compared with the MRI findings for the deep deltoid ligament in stable and unstable injuries. Interobserver reliability was calculated for both external-rotation stress testing and MRI assessment. RESULTS: Thirty-three patients had a medial clear space of ≥ 5 mm in the external-rotation stress test. According to MRI, all of these patients had an injury involving the deep deltoid ligament (an edematous ligament in five, a partial tear in twenty-six, and a total tear in two). Twenty-eight patients had a medial clear space of <5 mm, and MRI indicated a deep deltoid ligament injury in all of these patients as well (an edematous ligament in nine and a partial tear in nineteen). The medial clear space increased according to the severity of the deep deltoid ligament injury as indicated by MRI (p < 0.001). The interobserver agreement of the external-rotation stress test was excellent (94% agreement; kappa = 0.87), whereas the interobserver reliability of the MRI assessments by the two musculoskeletal radiologists was fair to moderate (72% agreement for the posterior part of the deep deltoid ligament and 56% for the anterior part; kappa = 0.46 and 0.22, respectively). CONCLUSIONS: On the basis of the study results, we do not recommend the use of MRI when choosing between operative and nonoperative treatment of an SER-type ankle fracture.

Assessment of association between low back pain and paraspinal muscle atrophy using opposed-phase magnetic resonance imaging: a population-based study among young adults.

STUDY DESIGN: A cross-sectional imaging study of young adults. OBJECTIVE: To evaluate whether severity of low back symptoms predicts atrophy in the paraspinal muscles of young adults. SUMMARY OF BACKGROUND DATA: Although an increased fat content of the lumbar muscles has been observed among adults with chronic LBP, there is limited knowledge of this association in younger populations. METHODS: The population-based study sample consisted of 554 subjects (321 females and 233 males) from the 1986 Northern Finland Birth Cohort. Latent Class Analysis (LCA) was used to cluster the subjects according to the low back symptoms and functional limitations at 18, 19, and 21 years. The mean age of the subjects at the time of the MRI (magnetic resonance imaging) was 21 years (range, 20-23). Muscle atrophy was evaluated by assessing the fat content of the paraspinal muscles using Opposed-Phase MRI. The cross-sectional areas (CSAs) of the erector spinae and multifidus muscles were also measured. RESULTS: LCA analysis produced five clusters differing in symptoms, ranging from a cluster (n = 65) in which subjects had high likelihood of symptoms and functional limitations at all time points, to a cluster (n = 165) with no pain ever. The fat content of the multifidus muscles was significantly higher among women than men (14.0% vs. 5.3%, P < 0.001), but it was not significantly associated with symptom severity. The CSA of both erector spinae and multifidus muscles were significantly larger among men than women (P < 0.001 in all of the muscles), but were not associated with pain severity. CONCLUSION: Low back symptoms and functional limitations over a 3-year period were not associated with increased fat content or a reduction in the cross-sectional area of lumbar paraspinal muscles among young adults.