Deep Learning-Driven Abbreviated Shoulder MRI Protocols: Diagnostic Accuracy in Clinical Practice

To evaluate the diagnostic accuracy of dual-energy computed tomography (CT) virtual non-calcium (VNCa) reconstructions for the depiction of traumatic knee bone marrow edema. Fifty-seven patients (mean age, 50years; range, 20-82years) with acute knee trauma further divided into 30 women and 27 men, who had undergone third-generation dual-source dual-energy CT and 3-T magnetic resonance imaging (MRI) within 7days between January 2017 and May 2018, were retrospectively analyzed. Six radiologists, blinded to clinical and MRI information, independently analyzed conventional grayscale dual-energy CT series for fractures; after 8weeks, readers evaluated color-coded VNCa reconstructions for the presence of bone marrow edema in six femoral and six tibial regions. Quantitative analysis of CT numbers on VNCa reconstructions was performed by a seventh radiologist. Two additional radiologists, blinded to clinical and CT information, analyzed MRI series in consensus to define the reference standard. Sensitivity, specificity, and the area under the curve (AUC) were the primary metrics of diagnostic accuracy. MRI revealed 197 areas with bone marrow edema (91/342 femoral, 106/342 tibial). In the qualitative analysis, VNCa showed high overall sensitivity (1108/1182 [94%]) and specificity (2789/2922 [95%]) for depicting bone marrow edema. The AUC was 0.96 (femur) and 0.97 (tibia). A cutoff value of - 51 Hounsfield units (HU) provided high sensitivity (102/106 [96%]) and specificity (229/236 [97%]) for differentiating tibial bone marrow edema. In both quantitative and qualitative analyses, dual-energy CT VNCa reconstructions yielded excellent diagnostic accuracy for depicting traumatic knee bone marrow edema compared with MRI. • Dual-energy CT (DECT) virtual non-calcium (VNCa) reconstructions are highly accurate in depicting bone marrow edema of the femur and tibia. • Diagnostic confidence, image noise, and image quality were rated as equivalent in VNCa reconstructions and MRI (magnetic resonance imaging) series. • VNCa images may serve as an alternative imaging approach to MRI.

Preoperative Bone Marrow Edema Negatively Impacts 10-Year Outcomes After Unicompartmental Knee Arthroplasty

Abstract:* Objective: This research aimed to investigate the association between the presence of bone marrow edema in the tibial plateau and the patient's inclination towards surgery in individuals diagnosed with stage 3 gonarthrosis. Background/Purpose: A cohort of 40 patients with confirmed stage 3 gonarthrosis was enrolled in this study. Magnetic Resonance Imaging (MRI) scans were employed to assess the presence and severity of bone marrow edema in the tibial plateau. Patient demographics, clinical history, and radiographic data were collected. A comprehensive statistical analysis, including chi-square tests and logistic regression, was performed to identify any significant relationships. Results: A statistically significant positive correlation was found between edema and age (r = 0.47, p < 0.01), indicating that as age increases, the presence of edema also tends to increase. No significant correlations were found between edema and BMI (r = -0.06, p = 0.70), or between BMI and age (r = 0.08, p = 0.62). This suggests that, within this sample, BMI does not significantly relate to either edema or age. Patients with more pronounced bone marrow edema were more likely to opt for surgery. Additionally, age and previous conservative treatment outcomes were identified as potential confounding factors influencing the decision-making process. Conclusion: The findings of this research underscore the relevance of bone marrow edema in the tibial plateau as a factor influencing the surgical inclination of stage 3 gonarthrosis patients. Understanding this relationship can contribute to a more personalized approach to treatment decisions in orthopedic practice, allowing healthcare professionals to better plan the interventions based on individual patient characteristics and preferences. Further studies are warranted to explore additional factors that may contribute to the complex decision-making process in managing advanced knee osteoarthritis.

The shoulder.

Early and accurate diagnosis is vital for avoiding the development of nondisplaced fractures to displaced fractures. Dual-energy CT (Computed Tomography) can detect bone marrow edema (BME), which may help to detect non-displaced fractures. To evaluate the value of DECT (Dual-Energy Computed Tomography) VNCa (Virtual noncalcium) images for improving diagnostic performance and confidence in acute non-displaced knee fractures. 125 patients with clinical suspicion of knee fractures underwent both DECT and MR. Conventional linear-blended CT and VNCa images were obtained from DECT. First, five readers with varying levels of experience evaluated the presence of fractures on conventional linear-blended CT and graded their diagnostic confidence on a scale of 1 to 10. Then BME with VNCa images was evaluated and compared with MR. Finally, the VNCa images combined with conventional linear-blended CT images were used to reassess the presence of fractures and diagnostic confidence. Diagnostic performance and matched pair analyses were performed. 20 non-displaced knee fractures were detected. The consistency test of VNCa images and MR by five radiologists showed Kappa values are 0.76, 0.79, 0.81,0.85,and 0.90,respectively. The diagnostic performance of all readers was improved when using VNCa images combined with conventional linear-blended CT compared with that with conventional linear-blended CT alone. Diagnostic confidence was improved with combined conventional linear-blended CT and VNCa images (median score:8,8,9,9, and 10, respectively) compared with conventional linear-blended CT alone (median score:7,7,8,9, and 9). DECT VNCa images could improve the radiologists' diagnostic performance and confidence with varying levels of experience in the detection of non-displaced knee fractures.

Objectives:To investigate uniformity and pitfalls in structured radiological staging of rectal cancer.Methods:Twenty-one radiologists (12 countries) staged 75 rectal cancers on MRI using a structured reporting template. Interobserver agreement (IOA) was calculated as the percentage agreement between readers (categorical variables) and Krippendorff’s α (continuous variables). Agreement with an expert consensus served as a surrogate standard of reference to estimate diagnostic accuracy. Polychoric correlation coefficients were used to assess correlations between diagnostic confidence and accuracy (=agreement with expert consensus).Results:Uniformity to diagnose high-risk (≥cT3 ab) versus low-risk (≤cT3 cd) cT-stage, cN0 versus cN+, lateral nodes and tumour deposits, MRF and sphincter involvement, and solid versus mucinous tumours was high with IOA > 80% in the majority of cases (and >80% agreement with expert consensus). Results for assessing extramural vascular invasion, cT-stage (cT1-2/cT3/cT4a/cT4b), cN-stage (cN0/N1/N2), relation to the peritoneal reflection, extent of sphincter involvement (internal/intersphincteric/external) and morphology (solid/annular/semi-annular) were considerably poorer. IOA was high (α = 0.72–0.84) for tumour height/length and extramural invasion depth, but low for tumour-MRF distance and number of (suspicious) nodes (α = 0.05–0.55). There was a significant positive correlation between diagnostic confidence and accuracy (=agreement with expert consensus) (p < 0.001-p = 0.003).Conclusions:- Several staging items lacked sufficient reproducibility.- Results for cT- and N-staging g improved when using a dichotomized stratification.- Considering the significant correlation between diagnostic confidence and accuracy, a confidence level may be incorporated into structured reporting for specific items with low reproducibility.Advances in knowledge:Although structured reporting aims to achieve uniformity in reporting, several items lack sufficient reproducibility and might benefit from dichotomized assessment and incorporating confidence levels.

ObjectivesTo compare dual-energy CT (DECT) and MRI for assessing presence and extent of traumatic bone marrow edema (BME) and fracture line depiction in acute vertebral fractures.MethodsEighty-eight consecutive patients who underwent dual-source DECT and 3-T MRI of the spine were retrospectively analyzed. Five radiologists assessed all vertebrae for presence and extent of BME and for identification of acute fracture lines on MRI and, after 12 weeks, on DECT series. Additionally, image quality, image noise, and diagnostic confidence for overall diagnosis of acute vertebral fracture were assessed. Quantitative analysis of CT numbers was performed by a sixth radiologist. Two radiologists analyzed MRI and grayscale DECT series to define the reference standard.ResultsFor assessing BME presence and extent, DECT showed high sensitivity (89% and 84%, respectively) and specificity (98% in both), and similarly high diagnostic confidence compared to MRI (2.30 vs. 2.32; range 0–3) for the detection of BME (p = .72). For evaluating acute fracture lines, MRI achieved high specificity (95%), moderate sensitivity (76%), and a significantly lower diagnostic confidence compared to DECT (2.42 vs. 2.62, range 0–3) (p < .001). A cutoff value of − 0.43 HU provided a sensitivity of 89% and a specificity of 90% for diagnosing BME, with an overall AUC of 0.96.ConclusionsDECT and MRI provide high diagnostic confidence and image quality for assessing acute vertebral fractures. While DECT achieved high overall diagnostic accuracy in the analysis of BME presence and extent, MRI provided moderate sensitivity and lower confidence for evaluating fracture lines.Key Points• In the setting of spinal trauma, dual-energy CT (DECT) is highly accurate in the evaluation of acute vertebral fractures and bone marrow edema presence and extent.• MRI provides moderate sensitivity and lower diagnostic confidence for the depiction of acute fracture lines, when compared to DECT, which might result in potentially inaccurate and underestimated severity assessment of injuries in certain cases when no fracture lines are visible on MRI.• DECT may represent a valid imaging alternative to MRI in specific settings of acute spinal trauma and in follow-up examinations, especially in elderly or unstable patients and in cases of subtle or complex orientated fracture lines.

BackgroundIntraoperative intraperitoneal chemotherapy using sustained-release fluorouracil implants has been used to reduce the recurrence of gastrointestinal tumors. However, these implants may persist and present as tumor-like lesions in imaging studies, potentially leading to false-positive interpretations as metastatic sites, affecting patient management. Our study aimed to enhance the diagnostic accuracy of radiologists in assessing gastric and colorectal cancer patients with fluorouracil implants.MethodsThis retrospective study comprised a summary of fluorouracil implant-related lesion characteristics by a multidisciplinary team (MDT), and a three-stage evaluation of tumor-like lesions by two radiologists. In total, 240 computed tomography (CT) examinations were randomly selected from all the available CT examinations of all patients, whom were then further divided evenly into three groups. Two radiologists independently assessed the implant-related tumor-like lesions across the following three stages: stage 1: pre-training without surgical information; stage 2: post-training without surgical information; and stage 3: post-training with surgical details provided. The training was based on the characteristics of the lesions identified earlier by the MDT. The radiologists evaluated the malignancy or benignity of each lesion, and rated their diagnostic confidence using a three-point scale. The reference standard was determined by the MDT. Diagnostic accuracy and diagnostic confidence were compared using Pearson’s Chi-squared test and the Wilcoxon rank-sum test.ResultsA total of 168 fluorouracil implants were confirmed in the subdiaphragmatic regions, paracolic gutters, and tumor beds of 164 patients. Imaging features such as a typical foreign body reaction (85.71%), no contrast enhancement on CT/magnetic resonance imaging, and no diffusion restriction on diffusion-weighted imaging were important for differentiating between fluorouracil implant–related lesions and malignant lesions. Follow-up CT scans showed a size reduction in 67.26% of the lesions and density changes in 52.98%. The diagnostic accuracy and confidence of the radiologists were improved in stage 2 (accuracy: 91.25%; confidence: most often classified as medium) compared to stage 1 (accuracy: 67.5%; confidence: most often classified as low; both P<0.001). When surgical information was available, the diagnostic accuracy and confidence of the radiologists were improved in stage 3 (accuracy: 100%; confidence most often classified as high) compared to stage 2 (accuracy: P=0.007; confidence: P<0.001).ConclusionsThe diagnostic accuracy and confidence of radiologists can be improved by providing them with training on implant imaging characteristics and precise surgical record documentation on the implant location and quantity.

Bone marrow edema (BME) is one of the most common findings on magnetic resonance imaging (MRI) after an ankle injury but can be present even without a history of trauma. This article will provide a systematic overview of the most common disorders in the ankle and foot associated with BME.The presence of BME is an unspecific but sensitive sign of primary pathology and may act as a guide to correct and systematic interpretation of the MR examination. The distribution of BME allows for a determination of the trauma mechanism and a correct assessment of soft tissue injury. The BME pattern following an inversion injury involves the lateral malleolus, the medial part of the talar body, and the medial part of the distal tibia. In other cases, a consideration of the distribution of BME may indicate the mechanism of injury or impingement. Bone in direct contact with a tendon may lead to alterations in the bone marrow signal where BME may indicate tendinopathy or dynamic tendon dysfunction. Changed mechanical forces between bones in coalition may lead to BME. Degenerative changes or minor cartilage damage may lead to subchondral BME. Early avascular necrosis, inflammation, or stress fracture may lead to more diffuse BME; therefore, a detailed medical history is crucial for correct diagnosis.A systematic analysis of BME on MRI can help to determine the trauma mechanism and thus assess soft tissue injuries and help to differentiate between different etiologies of nontraumatic BME.

Pediatric rotator cuff (RTC) injuries are uncommon, yet supraspinatus tendon (SST) signal alterations on T2-weighted imaging are frequently observed. To compare rates of SST signal alterations on shoulder MRIs of adolescents who are considered low- and high-risk for RTC injury. We retrospectively reviewed non-arthrogram shoulder MRI reports in 12-17-year-old patients at a large tertiary children's hospital (01/2010-09/2024). We identified a low-risk patient cohort who lacked (a) clinical concern for RTC pathology, (b) athletic history associated with RTC injuries, (c) recent trauma, or (d) prior shoulder intervention. We also identified an age- and sex-matched high-risk patient cohort who had clinical concern for RTC pathology. Two experienced pediatric radiologists independently and blindly reviewed the shoulder MRIs in a random order from these cohorts. SST was evaluated using coronal oblique fat-suppressed T2-weighted sequences. Logistic regression models were developed to investigate differences between cohorts. Both low- and high-risk cohorts included 26 patients (14 males). Their median (inter-quartile range) ages were 14.0 (2.0) years and 14.5 (3.0) years, respectively. In the low-risk cohort, SST signal alterations were identified in 23 (88.5%) and 22 (84.6%) patients by readers 1 and 2, respectively. In the high-risk group, SST signal alterations were identified in 24 (92.3%) and 23 (88.5%) patients by readers 1 and 2, respectively. Overall inter-reader agreement was substantial (Cohen's kappa=0.63). There was no statistical difference in the SST signal alteration grades between the low- and high-risk cohorts (P≥0.07). SST signal alterations are common in adolescent shoulder MRIs regardless of the clinical concern for RTC injury.

Purpose; To evaluate the diagnostic accuracy of dual-energy computed tomography (DECT) to identify non-traumatic bone marrow edema (BME) of the knee.&#x0D; Methods; This prospective study, approved by the institutional review board, comprised a cohort of 40 consecutive patients (comprising 23 males and 17 females, with a mean age of 52.3 years) who underwent examination using Dual-Energy Computed Tomography (DECT) with settings of 80 kV and a tin filter at 150 kV, in addition to Magnetic Resonance Imaging (MRI), all conducted within 5 days. Subsequently, DECT data underwent post-processing and were evaluated by two experienced radiologists, resulting in the visualization of Bone Marrow Edema (BME) on color-coded maps. To determine the diagnostic accuracy of DECT in detecting BME, receiver operator curves and the area under the curve (AUC) were computed, with MRI serving as the reference standard. Interobserver agreement was calculated with k-statistics. A p-value &lt;0.05 was considered significant.&#x0D; Results; At MRI, BME was identified in 30/40 patients, with 106/480 (22,1%) involved partitions. Sensitivity and specificity of Reader 1 were 67,9% (95% CI: 58,2 - 76,7) and 95,99% (95% CI: 93,5 - 97,7), respectively. Sensitivity and specificity of Reader 2 were 69,8% (95% CI: 60,1 - 78,3) and 95,99% (95% CI: 93,5 - 97,7), respectively. Similar diagnostic accuracy values were achieved by the 2 readers, with an AUC of 0.82 for R1 and 0.829 for R2 (p=.743). The inter-observer agreement was k=0.68.&#x0D; Conclusions; DECT is an accurate imaging technique for the evidence of non-traumatic BME of the knee when compared to MRI.

ObjectivesLumbar bone stress injury (‘bone stress injury’) is common in junior fast bowlers. The repetitive loading of cricket fast bowling may cause bone marrow oedema (BMO), detectable on MRI, before...

IntroductionLow back pain is a global health issue causing disability and missed work days. Commonly used MRI scans including T1-weighted and T2-weighted images provide detailed information of the spine and surrounding tissues. Artificial intelligence showed promise in improving image quality and simultaneously reducing scan time. This study evaluates the performance of deep learning (DL)-based T2 turbo spin-echo (TSE, T2DLR) and T1 TSE (T1DLR) in lumbar spine imaging regarding acquisition time, image quality, artifact resistance, and diagnostic confidence.Material and methodsThis retrospective monocentric study included 60 patients with lower back pain who underwent lumbar spinal MRI between February and April 2023. MRI parameters and DL reconstruction (DLR) techniques were utilized to acquire images. Two neuroradiologists independently evaluated image datasets based on various parameters using a 4-point Likert scale.ResultsAccelerated imaging showed significantly less image noise and artifacts, as well as better image sharpness, compared to standard imaging. Overall image quality and diagnostic confidence were higher in accelerated imaging. Relevant disk herniations and spinal fractures were detected in both DLR and conventional images. Both readers favored accelerated imaging in the majority of examinations. The lumbar spine examination time was cut by 61% in accelerated imaging compared to standard imaging.ConclusionIn conclusion, the utilization of deep learning-based image reconstruction techniques in lumbar spinal imaging resulted in significant time savings of up to 61% compared to standard imaging, while also improving image quality and diagnostic confidence. These findings highlight the potential of these techniques to enhance efficiency and accuracy in clinical practice for patients with lower back pain.

Study DesignProspective cohort study.PurposeTo prospectively investigate the influence of presence of bone marrow edema (BME) in non acute osteoporotic verterbral compression fractures on postoperative clinical outcome in patients treated by percutaneous vertebroplasty (PV).Overview of LiteratureAlthough PV is widely used to treat osteoporotic collapsed vertebral compression fractures (VCF); little is known about the influence of BME in osteoporotic VCF or about its relation with relief of pain.MethodsSixty seven patients with non acute osteoporotic verterbral compression fractures treated with PV. They were divided into edema group (56 patients with apparent vertebral BME in their magnetic resonance [MR] images), and non edema group (11 patients with no vertebral BME detected in their MR images). Pain was evaluated one week, one month, six months, and one year post procedure using visual analogue scale. Statistical analysis including a 2-tailed t test comparing postoperative data with preoperative values was done.ResultsA good clinical response to PV procedure was seen in all patients. Significant difference was seen between two groups in one week, and one month follow up periods. Regarding pain relief in the other periods of follow up, no significant difference was seen between two groups.ConclusionsPV resulted in significantly clinical improvement in patients with BME pattern than in those without in one week and one month follow up periods. But the absence of vertebral BME did not influence pain relief in patients with osteoporotic VCFs in six months, and one year post procedure.

To determine whether T1 post-gadolinium chelate images (T1Gd) can replace T2-weighted images (T2) for evaluating bone marrow oedema (BME), thereby allowing a shorter magnetic resonance imaging (MRI) protocol in rheumatoid arthritis (RA). In 179 early arthritis patients and 43 advanced RA patients, wrist and metacarpophalangeal joints were examined on a 1.5-T extremity MRI system with a standard protocol (coronal T1, T2 fat-saturated and coronal and axial T1 fat-saturated after Gd). BME was scored according to OMERACT RAMRIS by two observers with and without T2 images available. Agreement was assessed using intraclass correlation coefficients (ICCs) for semi-quantitative scores and test characteristics with T2 images as reference. Agreement between scores based on T2 and T1Gd images was excellent ICC (0.80-0.99). At bone level, sensitivity and specificity of BME on T1Gd compared to T2 were high for both patient groups and both readers (all ≥80%). T1Gd and T2 images are equally suitable for evaluating BME. Because contrast is usually administered to assess (teno)synovitis, a short MRI protocol of T1 and T1Gd is sufficient in RA. • Bone marrow oedema scores are equal on T2 and T1-Gd-chelate enhanced sequences. • Agreement between scores based on T2 and T1-Gd-chelate images was excellent. • Sensitivity and specificity for presence of bone marrow oedema were high. • A short protocol without T2 images suffices in rheumatoid arthritis patients.