Bone Marrow Edema Research Articles

Magnetic Resonance Imaging in the Evaluation of Avulsion Injuries of the Pelvis and Hip in Adolescent Professional Footballers: A Case Series.

Pelvic apophyseal avulsion fractures are uncommon injuries that frequently affect adolescents while participating in sports. This occurs because the enthesis cannot withstand the tractional force applied because the apophysis has not yet fully fused. Due to its complex muscular structure, being the origin of several muscles that cross two lower extremity joints, the pelvis has an increased risk for such injuries. The diagnosis of pelvic avulsion injuries depends heavily on imaging. The best way to detect soft-tissue changes, including tendon or muscle strain, bone marrow edema, hematomas, and soft tissue avulsion injuries, is with an magnetic resonance imaging . It is also the best at showing tendon retraction and can help the clinician spot patients who might benefit from surgical treatment. We report six cases of adolescents professional footballers that suffered avulsion injuries while playing football. The patients had painfully restricted hip range of motion and were unable to bear weight. Some of them on physical examination felt pain at the palpation of the injured area. Magnetic resonance revealed apophysis growth plate avulsion with or without displaced bone fragments that were treated conservatively with an excellent clinical and radiological outcome. For an accurate diagnosis of pelvic avulsion injuries and clinical management, it is important that everyone caring for this patient population is aware of the common injury mechanisms, radiographic findings, and available treatments.

Use of Focused Shock Waves in an Acute Talar Head Fracture

Talar fractures are rare and can be difficult to manage. Even in the absence of complications, the treatment of this type of injury can be prolonged and uncomfortable for the patient. Focused shock waves have been shown to be effective in the treatment of delayed unions and non-unions. In this case report, we share our experience with the use of focused shock waves in an acute talus fracture in a patient with risk factors for healing. Keywords: Talus, Talar fractures, Shock waves, Bone marrow edema

The sacroiliac joint across ages - what is normal?

The anatomy of the sacroiliac joint (SIJ) is complex with wide variations inter-individually as well as intra-individually (right versus left) and a frequent occurrence of anatomical variants. Besides, the joints are subject to strain, which may elicit non-inflammatory subchondral changes such as bone marrow edema (BME), sclerosis, and fat deposition simulating inflammatory SIJ changes. Furthermore, normal physiological changes during skeletal maturation can make interpretation of SIJ magnetic resonance imaging in children challenging. Knowledge about the wide range of normal findings is therefore important to avoid misinterpretation of findings as pathological. This review describes the current knowledge about normal SIJ findings across all ages.

Wait-and-scan: an alternative for curettage in atypical cartilaginous tumours of the long bones.

Due to its indolent clinical behaviour, the treatment paradigm of atypical cartilaginous tumours (ACTs) in the long bones is slowly shifting from intralesional resection (curettage) and local adjuvants, towards active surveillance through wait-and-scan follow-up. In this retrospective cohort study performed in a tertiary referral centre, we studied the natural behaviour of ACT lesions by active surveillance with MRI. Clinical symptoms were not considered in the surveillance programme. The aim of this study was to see whether active surveillance is safe regarding malignant degeneration and local progression. In total, 117 patients were evaluated with MRI assessing growth, cortical destruction, endosteal scalloping, periosteal reaction, relation to the cortex, and perilesional bone marrow oedema. Patients received up to six follow-up scans. At the time of the first follow-up MRI, 8% of the lesions showed growth (n = 9), 86% remained stable (101), and 6% decreased in size (n = 7). During the third follow-up, with a mean follow-up time of 60 months (SD 23), 24 patients were scanned, of whom 13% had lesions that had grown and 13% lesions that had decreased in size. After 96 months (SD 37), at the sixth follow-up MRI, 100% of the lesions remained stable. None of the lesions showed malignant progression and although some lesions grew in size (mean 1 mm (SD 0.8)), no malignant progression occurred. We conclude that active surveillance with MRI is safe for ACTs in the long bones in the short- and mid-term follow-up.

Deep learning-based automated high-accuracy location and identification of fresh vertebral compression fractures from spinal radiographs: a multicenter cohort study.

Digital radiography (DR) is a common and widely available examination. However, spinal DR cannot detect bone marrow edema, therefore, determining vertebral compression fractures (VCFs), especially fresh VCFs, remains challenging for clinicians. We trained, validated, and externally tested the deep residual network (DRN) model that automated the detection and identification of fresh VCFs from spinal DR images. A total of 1,747 participants from five institutions were enrolled in this study and divided into the training cohort, validation cohort and external test cohorts (YHDH and BMUH cohorts). We evaluated the performance of DRN model based on the area under the receiver operating characteristic curve (AUC), feature attention maps, sensitivity, specificity, and accuracy. We compared it with five other deep learning models and validated and tested the model internally and externally and explored whether it remains highly accurate for an external test cohort. In addition, the influence of old VCFs on the performance of the DRN model was assessed. The AUC was 0.99, 0.89, and 0.88 in the validation, YHDH, and BMUH cohorts, respectively, for the DRN model for detecting and discriminating fresh VCFs. The accuracies were 81.45% and 72.90%, sensitivities were 84.75% and 91.43%, and specificities were 80.25% and 63.89% in the YHDH and BMUH cohorts, respectively. The DRN model generated correct activation on the fresh VCFs and accurate peak responses on the area of the target vertebral body parts and demonstrated better feature representation learning and classification performance. The AUC was 0.90 (95% confidence interval [CI] 0.84-0.95) and 0.84 (95% CI 0.72-0.93) in the non-old VCFs and old VCFs groups, respectively, in the YHDH cohort (p = 0.067). The AUC was 0.89 (95% CI 0.84-0.94) and 0.85 (95% CI 0.72-0.95) in the non-old VCFs and old VCFs groups, respectively, in the BMUH cohort (p = 0.051). In present study, we developed the DRN model for automated diagnosis and identification of fresh VCFs from spinal DR images. The DRN model can provide interpretable attention maps to support the excellent prediction results, which is the key that most clinicians care about when using the model to assist decision-making.

Current MR imaging of cartilage in the context of knee osteoarthritis (part1) : Principles and sequences

Magnetic resonance imaging (MRI) is the clinical method of choice for cartilage imaging in the context of degenerative and nondegenerative joint diseases. The MRI-based definitions of osteoarthritis rely on the detection of osteophytes, cartilage pathologies, bone marrow edema and meniscal lesions but currently ascientific consensus is lacking. In the clinical routine proton density-weighted, fat-suppressed 2D turbo spin echo sequences with echo times of 30-40 ms are predominantly used, which are sufficiently sensitive and specific for the assessment of cartilage. The additionally acquired T1-weighted sequences are primarily used for evaluating other intra-articular and periarticular structures. Diagnostically relevant artifacts include magic angle and chemical shift artifacts, which can lead to artificial signal enhancement in cartilage or incorrect representations of the subchondral lamina and its thickness. Although scientifically validated, high-resolution 3D gradient echo sequences (for cartilage segmentation) and compositional MR sequences (for quantification of physical tissue parameters) are currently reserved for scientific research questions. The future integration of artificial intelligence techniques in areas such as image reconstruction (to reduce scan times while maintaining image quality), image analysis (for automated identification of cartilage defects), and image postprocessing (for automated segmentation of cartilage in terms of volume and thickness) will significantly improve the diagnostic workflow and advance the field further.

Effects of disease-modifying anti-rheumatic drugs on sacroiliac MRI score in axial spondyloarthritis: a systematic review and meta-analysis.

Sacroiliac bone marrow edema is an important factor in the diagnosis and management of axial spondyloarthritis (axSpA). The aim of this meta-analysis is to assess the effect of the different bDMARDs and tsDMARDs on the SPARCC score at 12-16 and 48-52 weeks. A systematic review, performed on PubMed (including Medline), Cochrane (CENTRAL) and DOAJ databases, included randomized controlled studies evaluating the sacroiliac joint (SIJ) SPARCC score at 12-16 or 48-52 weeks in patients with axSpA meeting the ASAS 2009 criteria or the modified New York criteria. We included studies evaluating the effects of the different treatments on the SPARCC score of SIJ in axial spondyloarthritis in comparison to a control group. Eighteen studies were included in the meta-analysis. Nine studies evaluated the effect of TNFα inhibitors (TNFi), three for IL-17 inhibitors, and four for JAK inhibitors. At 12 and 16 weeks, SIJ SPARCC score was significantly improved by TNFi (WMD: - 3.29 [95% CI - 4.25; - 2, 34]), by IL-17 inhibitors (WMD: - 4.66 [95% CI - 6.22; - 3.09]), and by JAK inhibitors (JAKi) (WMD: - 3.06 [95% CI - 3.24; - 2.89]). There was no difference between the molecule subgroups. At 48-52 weeks, TNFα inhibitors reduced more SIJ SPARCC, but not significantly (WMD: - 2.26 [95% CI - 4.94; 0.42]), than placebo groups who began a TNFi treatment with delay. Our meta-analysis shows a comparable improvement of the SIJ SPARCC score regarding TNFi, JAKi, and IL-17 inhibitors at three months and suggests the presence of an opportunity window. Key Points • Anti-TNF Ab, anti-IL17 Ab, and JAK inhibitor treatments reduce the sacroiliac joint SPARCC scores. • There is no difference between the different treatments in the reduction of the sacroiliac joint SPARCC score after 3 months in axial spondyloarthritis.

Analysis of influence of MR signs on Harris score in ARCO stages 2-4 femoral head necrosis

To analysis and determine MR signs of Harris score ARCO stages 2-4 in osteonecrosis of femoral head (ONFH). Thirty-four patients with ONFH of ARCO stages 2 to 4 who underwent routine MR, T2 mapping, 3D-SPACE sequence examination and Harris score were retrospectively collected from January 2019 to June 2020, and 3 patients were excluded, and 31 patients were finally included, including 23 males and 8 females, aged from 18 to 62 years old with an average of(40.0±10.8) years old. Among them 21 patients with bilateral femoral head necrosis, totally 52 cases, including 17 with ARCO stage 2 patients, 24 ARCO stage 3, and 11 ARCO stage 4. MR imaging signs (femoral head collapse depth, ONFH index, bone marrow edema, hyperplasia, grade and T2 value of cartilage injury, and joint effusion) were scored and measured on the picture archiving and communication system (PACS) workstation, and the cartilage quantitative parameter T2 value was calculated and measured on Siemens postprocessing workstation. Pearson correlation analysis was used to evaluate the correlation between various MR signs and Harris score, and then multiple linear regression analysis was used to examine impact of MR signs on Harris hip score. Femoral head collapse depth(r=-0.563, P=0.000), grade of cartilage injury(r=-0.500, P=0.000), and joint effusion (r=-0.535, P=0.000) were negatively correlated with Harris score by Pearson correlation analysis. Multiple linear regression analysis showed that joint effusion(β=-6.198, P=0.001) and femoral head collapse depth(β=-4.085, P=0.014) had a significant negative impact on Harris hip score. Femoral head collapse depth and joint effusion both had significant negative relationship with Harris hip score. It is recommended to routinely evaluate femoral head collapse depth and joint effusion quantitatively and gradedly, so as to efficiently and accurately assist clinical diagnosis and treatment.

To study magnetic resonance imaging findings and inflammatory markers in inflammatory sacroiliitis

Objectives: The objectives of the study are to determine magnetic resonance imaging (MRI) findings in inflammatory sacroiliitis and assign scores and grades to it and to determine and correlate erythrocyte sedimentation rate, C-reactive protein (CRP), and human leukocyte antigen-B27 (HLA-B27) in various grades of sacroiliitis. Material and Methods: An observational cross-sectional study was conducted on 30 patients who clinically presented with features of sacroiliitis and underwent an MRI of sacroiliac joint (SIJ). Various inflammatory and structural findings on MRI were used to do Spondyloarthritis Research Consortium of Canada scoring and grading. Then inflammatory markers including erythrocyte sedimentation rate, CRP, and HLA-B27 were studied in various grades of sacroiliitis. Results: Inflammatory sacroiliitis affects commonly the age group of 21–40 years. Periarticular edema was the most common finding seen with the iliac aspect more commonly involved. The majority of the subjects were graded moderate (50%). Values of erythrocyte sedimentation rate and CRP levels were raised whereas HLA-B27 was positive in 9 patients (30%) of inflammatory sacroiliitis. Conclusion: Inflammatory sacroiliitis presents with a chief complaint of low back ache. MRI helps to grade it into mild, moderate, and severe. STIR is the most sensitive sequence for the detection of bone marrow edema with bilateral symmetrical involvement but the iliac bone of SIJ is more involved than the sacral side. Contrast-enhanced sequences and diffusion images add no significant statistical role in the diagnosis of bone marrow edema. Inflammatory laboratory parameters were increased in higher grades of sacroiliitis. HLA-B27, although not specific to inflammatory sacroiliitis, increases in higher grades of sacroiliitis.

Comparative analysis of the results of multispiral computed tomography using color mapping and magnetic resonance imaging in the diagnosis of acute hematogenous osteomyelitis in children

BACKGROUND: Although acute hematogenous osteomyelitis is considered a fairly well-studied disease, several articles emphasize that the frequency of diagnostic errors remains quite high. The clinical presentation of acute hematogenous osteomyelitis largely depends on its reactivity and localization. The latter has features of the clinical course in children of different age groups. Osteomyelitis can be difficult to detect because of the variability and nonspecificity of symptoms and physical and laboratory parameters. Rapid diagnosis is crucial for successful disease outcomes because untimely treatment increases the number of complications. Therefore, visualization should be aimed at early diagnosis and, ultimately, successful treatment.
 AIM: This study aimed to evaluate the informative value of magnetic resonance imaging and multispiral computed tomography (MSCT) in the diagnosis of the intramedullary phase of acute hematogenous osteomyelitis as its earliest stage.
 MATERIALS AND METHODS: Thirty patients suspected with acute hematogenous osteomyelitis underwent magnetic resonance imaging and MSCT using color mapping techniques and X-ray density assessment. At the final stage of the diagnostic algorithm, osteotonometry was performed. The contents of the bone marrow canal were taken for microbiological and bacteriological studies.
 RESULTS: In the intramedullary phase of acute hematogenous osteomyelitis, magnetic resonance imaging and MSCT revealed signs of bone marrow edema in 96% of the cases. The sensitivity of magnetic resonance imaging was 96%, the same as that of MSCT; however, the specificity was significantly lower than that of MSCT using the color mapping method and X-ray density assessment, which was 67% and 83%, respectively (p 0.05).
 DISCUSSION: In recent years, the role of computed tomography in the diagnosis of acute hematogenous osteomyelitis has received considerable recognition in pediatric surgical practice, and MSCT with color mapping and X-ray density assessment in the diagnosis of acute hematogenous osteomyelitis in children has been used relatively recently. Simultaneously, many researchers have reported the high informativeness of MSCT in the diagnosis of acute hematogenous osteomyelitis.
 CONCLUSIONS: The intramedullary phase of acute hematogenous osteomyelitis according to magnetic resonance imaging and MSCT indicates bone marrow edema as its earliest stage. According to the data of the present study, MSCT using color mapping and X-ray density assessment has high specificity and can be used with MRI as the main method for diagnosing the intramedullary phase of acute hematogenous osteomyelitis.

Dissociation of clinical symptoms and magnetic resonance imaging data in axial psoriatic arthritis

Currently, there is no generally accepted definition of axial lesions in psoriatic arthritis (axPsA), and the diagnostic criteria are extrapolated from the recommendations for ankylosing spondylitis and axial spondyloarthritis.Objective: To evaluate data of magnetic resonance imaging (MRI) of spine and sacroiliac joints (SIJ) in patients with psoriasis complaining of chronic back pain of any cause.Material and methods. 143 patients were enrolled to the study, including 57 (39.9%) men and 86 (60.1%) women, median age – 47 [36; 57] years, mean duration of psoriasis was 17.4±13.4 years. In all patients, the agreement of the existing symptoms with the inflammatory back pain (IBP) criteria of A. Calin et al., M. Rudwaleit et al. and ASAS was checked. All patients underwent MRI of the spine and SIJ, determination of ESR, CRP levels, HLA-B27 and consultations with a dermatologist and a rheumatologist.Results and discussion. An association of bone marrow edema (BME) in the spine and SIJ with nail involvement (odds ratio, OR 2.32; 95% confidence interval, CI 1.12–4.81; p=0.035), palmoplantar psoriasis (OR 3.85; 95% CI 1.43–10.41; p=0.054) and a weak correlation with PASI (r=0.329, p=0.034) was found. There were no statistically significant differences in PASI between patients with BME and without BME. In patients with IBP who fulfilled the criteria of A. Calin et al., osteitis in the SIJ was present in 19 (34.5%; OR 2.79; 95% CI 1.26–6.19; p=0.01); Berlin criteria of 4 signs – 25 (28.7%; OR 2.42; 95% CI 1.00–5.84; p=0.045); Berlin criteria of 3 signs – in 18 (24.0%; OR 1.12; 95% CI 0.51–2.44; p=0.783); ASAS criteria – in 17 (34.0%; OR 2.48; 95% CI 1.12–5.49; p=0.023). In almost half of the patients with BME in the spine or SIJ, the symptoms did not fulfil the criteria for IBP. Signs such as the presence and duration of morning stiffness had a high prognostic value. Isolated spondylitis (presence of BME in vertebrae and absence of BME in SIJ) was rarely found in patients with IBP fulfilling various criteria (in 4.0–8.1% of cases).Conclusion. Considering the existing discrepancy between symptoms and MRI results, it is necessary to develop independent tools for screening and early diagnosis of axPsA.

Infectious sacroiliitis: MRI- and CT-based assessment of disease extent, complications, and anatomic correlation.

To describe the frequency of MR and CT features of infectious sacroiliitis (ISI) and assess its extent and complications MATERIALS AND METHODS: This retrospective study included patients with ISI who were evaluated between 2008 and 2021 in a single center. Two radiologists reviewed MRI and CT images to determine the anatomical distribution (unilateral/bilateral, iliac/sacral bone, proximal/middle/distal), severity (bone marrow edema [BME]/periostitis/erosions), concurrent infection (vertebral/nonvertebral), and complications (abscess/probable adjacent osteomyelitis/cavitation/devitalized areas/sequestrum/pelvic venous thrombosis) of ISI. Interobserver reproducibility was assessed. Correlation analysis evaluated the effect of the causative microorganism on severity. Two human bodies were dissected to outline possible ways that ISI can spread. Forty patients with ISI (40 years ± 22; 26 women) were evaluated. Ten patients had bilateral ISI. Concurrent vertebral infection was associated in 15% of cases. Reproducibility of sacral BME, periostitis, and reactive locoregional abnormalities was perfect (κ = 1). Reproducibility was low for erosion count (κ = 0.52[0.52-0.82]) and periarticular osteopenia (κ = 0.50[0.18-0.82]). Inflammatory changes were BME (42/42 joints), muscle edema (38/42), and severe periostitis along the ilium (33/37). Destructive structural changes occurred with confluent erosions (iliac, 20/48; sacral, 13/48), sequestrum (20/48), and cavitation (12/48). Complications occurred in 75% of cases, including periarticular abscesses (n = 30/47), probable adjacent osteomyelitis (n = 16/37), and pelvic thrombophlebitis (n = 3). Tuberculous ISI (6/40) correlated with sclerosis (rs = 0.45[0.16; 0.67]; p < 10-2) and bone devitalization (rs = 0.38[0.16; 0.67]; p = .02). The anatomical study highlighted the shared venous vascularization of sacroiliac joints, pelvic organs, and mobile spine. Complications of ISI are frequent, including abscesses, adjacent osteomyelitis, and periostitis. ISI had bilateral involvement nonrarely and is commonly associated with another spinal infection.

Short-segment spinal fusion for chronic low back pain with bone marrow edema adjacent to the vertebral endplate in adult spinal deformity.

Corrective long spinal fusion is a widely accepted surgical method for patients with adult spinal deformities. However, instrumented long fusion is associated with a significant risk of complications. Therefore, we aimed to assess the success of short-segment spinal fusion, particularly for bone marrow edema (BME) adjacent to the vertebral endplate, in patients with low back pain (LBP) and spinal deformity. A prospective study was performed at multiple hospitals wherein we monitored patients with spinal deformities and accompanying LBP. Patients aged ≥ 50years with a minimum LBP severity score of 40mm on the visual analog scale (VAS) were included in the study. We also included patients with lumbar BME on magnetic resonance imaging. Short spinal fusion was performed on segments with BME. Clinical evaluations of LBP on VAS and Oswestry Disability Index (ODI), and radiological parameters for sagittal vertical axis (SVA), pelvic incidence (PI), lumbar lordosis (LL) and pelvic tilt (PT) were carried out. Overall, 35 patients (22 men and 13 women), with a mean age of 66.7years and a mean follow-up period of 32months, were included in the study. The mean VAS and ODI scores were 72.4mm and 49.0% before surgery and 25.5mm and 29.9% at the final follow-up, respectively; these parameters significantly improved after surgery. The SVA, PI-LL, and PT scores were 70.1mm, 20.9°, and 22.8° before surgery and 85.4mm, 13.8°, and 22.7° at the final follow-up, respectively. The spinal alignment parameters did not change significantly after surgery. Short-segment spinal fusion is effective for treating LBP and spinal deformity with BME adjacent to the vertebral endplate without spinal correction.

Bone marrow edema in the acromioclavicular joint after arthroscopic rotator cuff repair

BackgroundBone marrow edema (BME) in the acromioclavicular joint (ACj) may occur after arthroscopic rotator cuff repair (ARCR), resulting in persistent postoperative ACj pain. We investigated the incidence and clinical characteristics of BME in ACj after ARCR. MethodsPatients exhibiting ACj-related symptoms prior to ARCR surgery, no BME in the ACj on MRI, and an ability to undergo 2-year postoperative physical and MRI examinations of the ACj were included. Patients who underwent distal clavicle resection or osteophyte resection below the ACj and those unable to achieve primary repair of the rotator cuff were excluded. MRI evaluation was performed preoperatively and at 3, 6, 12, and 24 months postoperatively. Patients who showed BME in ACj on fat-suppressed T2 MRI at 24 months postoperatively were classified into the BME + group, and those with no BME were classified into the BME− group. Patient background, operation time, Japanese Orthopedic Association (JOA) score, re-tear rate, ACj tenderness, and cross-body adduction test were compared between groups. In addition, we examined the time of occurrence of BME. ResultsA total of 345 ARCRs were performed during the study period. After the exclusion of 114 shoulders, the remaining 231 shoulders were included in this study. There were 208 cases in the BME− group and 23 cases in the BME + group. The incidence of BME was 9.96 %. Although the JOA scores of both groups showed a significant improvement postoperatively compared to preoperatively, there was no significant difference between the two groups. In terms of re-tear, there was 1 case in the BME + group and 7 in the BME− group. Positive ACj tenderness and cross-body adduction test were significantly higher in the BME + group (P < 0.001). BME occurred in 6 cases at 3 months, 9 cases at 6 months, and 8 cases at 1 year postoperatively. None of the patients developed BME at more than 1 year postoperatively. BME was observed on MRI in all cases at 2 years postoperatively. ConclusionsThe rate of occurrence of BME in the ACj after ARCR was 9.96 %. Patients with BME were significantly more likely to have ACj tenderness and positive cross-body adduction test. BME in the ACj often occurs within 6 months to 1 year after ARCR of small-to-medium rotator cuff tears, suggesting a relationship with postoperative functional improvement of the shoulder joint. The ACj should be considered as a potential site of persistent pain after ARCR for small-to-medium rotator cuff tears.

Spinal Involvement in Patients with Chronic Non-Bacterial Osteomyelitis (CNO): An Analysis of Distinctive Imaging Features

Spinal involvement by chronic non-bacterial osteomyelitis (CNO) has been increasingly reported in recent years, often being presented as a diagnostic dilemma requiring differential diagnosis with bacterial spondylodiscitis and/or neoplasia. This study was aimed at identifying the imaging features of CNO facilitating its differentiation from other spinal diseases. Two radiologists assessed the imaging studies of 45 patients (16 male and 29 female, aged from 6 to 75 years, 15 children) with CNO collected from 5 referential centers. Spinal lesions were found in 17 patients (2 children and 15 adults), most often in the thoracic spine. In children, the lesions involved short segments with a destruction of vertebral bodies. In adults, the main findings were prominent bone marrow edema and osteosclerosis, endplate irregularities, and ankylosing lesions extending over long segments; paraspinal inflammation was mild and abscesses were not observed. In both children and adults, the involvement of posterior elements (costovertebral and facet joints) emerged as an important discriminator between CNO and neoplasia/other inflammatory conditions. In conclusion, a careful inspection of imaging studies may help to reduce the number of biopsies performed in the diagnostic process of CNO.

Constructing a Deep Learning Radiomics Model Based on X-ray Images and Clinical Data for Predicting and Distinguishing Acute and Chronic Osteoporotic Vertebral Fractures: A Multicenter Study

To construct and validate a deep learning radiomics (DLR) model based on X-ray images for predicting and distinguishing acute and chronic osteoporotic vertebral fractures (OVFs). A total of 942 cases (1076 vertebral bodies) with both vertebral X-ray examination and MRI scans were included in this study from three hospitals. They were divided into a training cohort (n=712), an internal validation cohort (n=178), an external validation cohort (n=111), and a prospective validation cohort (n=75). The ResNet-50 model architecture was used for deep transfer learning (DTL), with pre-training performed on RadImageNet and ImageNet datasets. DTL features and radiomics features were extracted from lateral X-ray images of OVFs patients and fused together. A logistic regression model with the least absolute shrinkage and selection operator was established, with MRI showing bone marrow edema as the gold standard for acute OVFs. The performance of the model was evaluated using receiver operating characteristic curves. Eight machine learning classification models were evaluated for their ability to distinguish between acute and chronic OVFs. The Nomogram was constructed by combining clinical baseline data to achieve visualized classification assessment. The predictive performance of the best RadImageNet model and ImageNet model was compared using the Delong test. The clinical value of the Nomogram was evaluated using decision curve analysis (DCA). Pre-training resulted in 34 and 39 fused features after feature selection and fusion. The most effective machine learning algorithm in both DLR models was Light Gradient Boosting Machine. Using the Delong test, the area under the curve (AUC) for distinguishing between acute and chronic OVFs in the training cohort was 0.979 and 0.972 for the RadImageNet and ImageNet models, respectively, with no statistically significant difference between them (P=0.235). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.629, 0.886 vs 0.817, and 0.933 vs 0.661, respectively, with statistically significant differences in all comparisons (P<0.05). The deep learning radiomics nomogram (DLRN) was constructed by combining the predictive model of RadImageNet with clinical baseline features, resulting in AUCs of 0.981, 0.974, 0.895, and 0.902 in the training cohort, internal validation cohort, external validation cohort, and prospective validation cohort, respectively. Using the Delong test, the AUCs for the fused feature model and the DLRN in the training cohort were 0.979 and 0.981, respectively, with no statistically significant difference between them (P=0.169). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.974, 0.886 vs 0.895, and 0.933 vs 0.902, respectively, with statistically significant differences in all comparisons (P<0.05). The Nomogram showed a slight improvement in predictive performance in the internal and external validation cohort, but a slight decrease in the prospective validation cohort (0.933 vs 0.902). DCA showed that the Nomogram provided more benefits to patients compared to the DLR models. Compared to the ImageNet model, the RadImageNet model has higher diagnostic value in distinguishing between acute and chronic OVFs. Furthermore, the diagnostic performance of the model is further improved when combined with clinical baseline features to construct the Nomogram.

Foot and Ankle Bone Marrow Edema Assessment in Long Distance Runners.

The clinical significance of foot and ankle bone marrow edema (BME) is poorly understood. Magnetic resonance imaging (MRI) and the visual analog scale (VAS) pain scores were collected for 17 runners who participated in the Twin Cities Marathon, immediately postmarathon and at a 6-week follow-up. Bone marrow edema lesions were classified using lesion frequency, anatomical location, and grading scale change to calculate a BME score for each affected bone. Spearman rank correlation coefficient test was used to identify a possible correlation between VAS and postmarathon BME. A paired Student t test was used to detect differences between total mileage ran 6 weeks postmarathon in participants with or without BME. After completing the marathon, 8 BME lesions were identified in 5 participants (29.4%; 5/17), 3 were men, and 2 were women, with a mean age of 33.8 years (range: 24-52), and BMI of 22.9 ± 4. All lesions were resolved on 6-week follow-up imaging. VAS pain scores did not correlate with postmarathon BME. A significant difference in total miles logged over 6 weeks postmarathon could not be found among participants with and without BME. Foot and ankle BME changes identified by MRI were not correlated to clinical symptoms and may resolve with self-directed activity in less time than other areas of the lower extremity. Level II, Prospective Cohort Study.

Beyond the horizon: Innovations and future directions in axial-spondyloarthritis.

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the spine and sacroiliac joints. This review discusses recent advances across multiple scientific fields that promise to transform axSpA management. Traditionally, axSpA was considered an immune-mediated disease driven by human leukocyte antigen B27 (HLA-B27), interleukin (IL)-23/IL-17 signaling, biomechanics, and dysbiosis. Diagnosis relies on clinical features, laboratory tests, and imaging, particularly magnetic resonance imaging (MRI) nowadays. Management includes exercise, lifestyle changes, non-steroidal anti-inflammatory drugs and if this is not sufficient to achieve disease control also biological and targeted-synthetic disease modifying anti-rheumatic drugs. Beyond long-recognized genetic risks like HLA-B27, high-throughput sequencing has revealed intricate gene-environment interactions influencing dysbiosis, immune dysfunction, and aberrant bone remodeling. Elucidating these mechanisms promises screening approaches to enable early intervention. Advanced imaging is revolutionizing the assessment of axSpA's hallmark: sacroiliac bone-marrow edema indicating inflammation. Novel magnetic resonance imaging (MRI) techniques sensitively quantify disease activity, while machine learning automates complex analysis to improve diagnostic accuracy and monitoring. Hybrid imaging like synthetic MRI/computed tomography (CT) visualizes structural damage with new clarity. Meanwhile, microbiome analysis has uncovered gut ecosystem alterations that may initiate joint inflammation through HLA-B27 misfolding or immune subversion. Correcting dysbiosis represents an enticing treatment target. Moving forward, emerging techniques must augment patient care. Incorporating patient perspectives will be key to ensure innovations like genetics, microbiome, and imaging biomarkers translate into improved mobility, reduced pain, and increased quality of life. By integrating cutting-edge, multidisciplinary science with patients' lived experience, researchers can unlock the full potential of new technologies to deliver transformative outcomes. The future is bright for precision diagnosis, tightly controlled treatment, and even prevention of axSpA.

Radiomics Texture Analysis of Bone Marrow Alterations in MRI Knee Examinations.

Accurate diagnosis and timely intervention are key to addressing common knee conditions effectively. In this work, we aim to identify textural changes in knee lesions based on bone marrow edema (BME), injury (INJ), and osteoarthritis (OST). One hundred and twenty-one MRI knee examinations were selected. Cases were divided into three groups based on radiological findings: forty-one in the BME, thirty-seven in the INJ, and forty-three in the OST groups. From each ROI, eighty-one radiomic descriptors were calculated, encoding texture information. The results suggested differences in the texture characteristics of regions of interest (ROIs) extracted from PD-FSE and STIR sequences. We observed that the ROIs associated with BME exhibited greater local contrast and a wider range of structural diversity compared to the ROIs corresponding to OST. When it comes to STIR sequences, the ROIs related to BME showed higher uniformity in terms of both signal intensity and the variability of local structures compared to the INJ ROIs. A combined radiomic descriptor managed to achieve a high separation ability, with AUC of 0.93 ± 0.02 in the test set. Radiomics analysis may provide a non-invasive and quantitative means to assess the spatial distribution and heterogeneity of bone marrow edema, aiding in its early detection and characterization.

Machine Learning Pipeline for Predicting Bone Marrow Edema Along the Sacroiliac Joints on Magnetic Resonance Imaging.

We aimed to develop and validate a fully automated machine learning (ML) algorithm that predicts bone marrow edema (BME) on a quadrant level in sacroiliac (SI) joint magnetic resonance imaging (MRI). A computer vision workflow automatically locates the SI joints, segments regions of interest (ilium and sacrum), performs objective quadrant extraction, and predicts presence of BME, suggestive of inflammatory lesions, on a quadrant level in semicoronal slices of T1/T2-weighted MRI scans. Ground truth was determined by consensus among human readers. The inflammation classifier was trained using a ResNet18 backbone and five-fold cross-validated on scans of patients with spondyloarthritis (SpA) (n=279), postpartum individuals (n=71), and healthy subjects (n=114). Independent SpA patient MRI scans (n=243) served as test data set. Patient-level predictions were derived from aggregating quadrant-level predictions, ie, at least one positive quadrant. The algorithm automatically detects the SI joints with a precision of 98.4% and segments ilium/sacrum with an intersection over union of 85.6% and 67.9%, respectively. The inflammation classifier performed well in cross-validation: area under the curve (AUC) 94.5%, balanced accuracy (B-ACC) 80.5%, and F1 score 64.1%. In the test data set, AUC was 88.2%, B-ACC 72.1%, and F1 score 50.8%. On a patient level, the model achieved a B-ACC of 81.6% and 81.4% in the cross-validation and test data set, respectively. We propose a fully automated ML pipeline that enables objective and standardized evaluation of BME along the SI joints on MRI. This method has the potential to screen large numbers of patients with (suspected) SpA and is a step closer towards artificial intelligence-assisted diagnosis and follow-up.