Differentiation Between Brucellar and Tuberculous Spondylodiscitis in the Acute and Subacute Stages by MRI: A Retrospective Observational Study

Differentiation of tuberculous and brucellar spondylitis using conventional MRI-based deep learning algorithms

PURPOSE

To investigate the feasibility of deep learning (DL) based on conventional MRI to differentiate tuberculous spondylitis (TS) from brucellar spondylitis (BS).

METHODS

A total of 383 patients with TS (n = 182) or BS (n = 201) were enrolled from April 2013 to May 2023 and randomly divided into training (n = 307) and validation (n = 76) sets. Sagittal T1WI, T2WI, and fat-suppressed (FS) T2WI images were used to construct single-sequence DL models and combined models based on VGG19, VGG16, ResNet18, and DenseNet121 network. The area under the receiver operating characteristic curve (AUC) was used to assess the classification performance. The AUC of DL models was compared with that of two radiologists with different levels of experience.

RESULTS

The AUCs based on VGG19, ResNet18, VGG16, and DenseNet121 ranged from 0.885 to 0.973, 0.873 to 0.944, 0.882 to 0.929, and 0.801 to 0.933, respectively, and VGG19 models performed better. The diagnostic efficiency of combined models outperformed single-sequence DL models. The combined model of T1WI, T2WI, and FS T2WI based on VGG19 achieved optimal performance, with an AUC of 0.973. In addition, the performance of all combined models based on T1WI, T2WI, and FS T2WI was better than that of two radiologists (P<0.05).

CONCLUSION

The DL models have potential guiding value in the diagnosis of TS and BS based on conventional MRI and provide a certain reference for clinical work.

MRI-based interpretable radiomics nomogram for discrimination between Brucella spondylitis and Pyogenic spondylitis

Background

Pyogenic spondylitis (PS) and Brucella spondylitis (BS) are commonly seen spinal infectious diseases. Both types can lead to vertebral destruction, kyphosis, and long-term neurological deficits if not promptly diagnosed and treated. Therefore, accurately diagnosis is crucial for personalized therapy. Distinguishing between PS and BS in everyday clinical settings is challenging due to the similarity of their clinical symptoms and imaging features. Hence, this study aims to evaluate the effectiveness of a radiomics nomogram using magnetic resonance imaging (MRI) to accurately differentiate between the two types of spondylitis.

Methods

Clinical and MRI data from 133 patients (2017-2022) with pathologically confirmed PS and BS (68 and 65 patients, respectively) were collected. We have divided patients into training and testing cohorts. In order to develop a clinical diagnostic model, logistic regression was utilized to fit a conventional clinical model (M1). Radiomics features were extracted from sagittal fat-suppressed T2-weighted imaging (FS-T2WI) sequence. The radiomics features were preprocessed, including scaling using Z-score and undergoing univariate analysis to eliminate redundant features. Furthermore, the Least Absolute Shrinkage and Selection Operator (LASSO) was employed to develop a radiomics score (M2). A composite model (M3) was created by combining M1 and M2. Subsequently, calibration and decision curves were generated to evaluate the nomogram's performance in both training and testing groups. The diagnostic performance of each model and the indication was assessed using the receiver operating curve (ROC) with its area under the curve (AUC). Finally, we used the SHapley Additive exPlanations (SHAP) model explanations technique to interpret the model result.

Results

We have finally selected 9 significant features from sagittal FS-T2WI sequences. In the differential diagnosis of PS and BS, the AUC values of M1, M2, and M3 in the testing set were 0.795, 0.859, and 0.868. The composite model exhibited a high degree of concurrence with the ideal outcomes, as evidenced by the calibration curves. The nomogram's possible clinical application values were indicated by the decision curve analysis. By using SHAP values to represent prediction outcomes, our model's prediction results are more understandable.

Conclusions

The implementation of a nomogram that integrates MRI and clinical data has the potential to significantly enhance the accuracy of discriminating between PS and BS within clinical settings.

Development of a Diagnostic Model for Differentiating Tuberculous Spondylitis and Pyogenic Spondylitis With MRI: A Multicenter Retrospective Observational Study

STUDY DESIGN

Multicenter retrospective observational study.

OBJECTIVE

This study aimed to distinguish tuberculous spondylitis (TS) from pyogenic spondylitis (PS) using magnetic resonance imaging (MRI). Further, a novel diagnostic model for differential diagnosis was developed.

SUMMARY OF BACKGROUND DATA

TS and PS are the two most common spinal infections. Distinguishing between these types clinically is challenging. Delayed diagnosis can lead to deficits or kyphosis. Currently, there is a lack of radiology-based diagnostic models for TS and PS.

METHODS

We obtained radiologic images from MRI imaging of patients with TS and PS and applied the least absolute shrinkage and selection operator regression to select the optimal features for a predictive model. Predictive models were built using multiple logistic regression analysis. Clinical utility was determined using decision curve analysis, and internal validation was performed using bootstrap resampling.

RESULTS

A total of 201 patients with TS (n=105) or PS (n=96) were enrolled. We identified significant differences in MRI features between both groups. We found that noncontiguous multivertebral and single-vertebral body involvement were common in TS and PS, respectively. Vertebral bone lesions were more severe in the TS group than in the PS group (Z=-4.553, P <0.001). The patients in the TS group were also more prone to vertebral intraosseous, epidural, and paraspinal abscesses ( P <0.001). A total of 8 predictors were included in the diagnostic model. Analysis of the calibration curve and area under the receiver operating characteristic curve suggested that the model was well-calibrated with high prediction accuracy.

CONCLUSIONS

This is the largest study comparing MRI features in TS and PS and the first to develop an MRI-based nomogram, which may help clinicians distinguish between TS and PS.

Efficacy of posterior fixation and bone graft fusion for treatment of lumbar brucellosis spondylitis

The purpose of this study is to verify whether early stage patients with single-segment lumbar Brucella spondylitis can still be cured through simple posterior fixation and bone grafting, even without debridement. A retrospective study was conducted on 63 patients diagnosed with single-segment lumbar brucellosis spondylitis, who underwent posterior-only debridement (or not), bone grafting, and instrumentation from June 2016 to June 2019. Group A comprised 34 patients who did not undergo debridement, while group B comprised 29 patients who underwent debridement. The clinical data and imaging results of the patients were compared between the 2 groups to evaluate the clinical effects of debridement or not. Both groups of patients completed at least 1 year of follow-up. The group A had significantly lower values for operation time, blood loss, and hospital stay compared to the group B (P < .05). There were no significant differences between the 2 groups in terms of erythrocyte sedimentation rate, C-reactive protein, visual analogue scores, improvement of Japanese Orthopaedic Association Evaluation of treatment score, and Cobb angle. The bone fusion rate was 92% (31 patients) in group A and 96% (28 patients) in group B, with no significant difference between the 2 groups (P > .05). In summary, these findings suggest that posterior fixation and bone graft fusion are effective treatments for single-segment lumbar brucellosis spondylitis in early stages even without debridement. Importantly, these procedures offer several benefits, such as minimal trauma, short operation times, rapid postoperative recovery, and favorable bone graft fusion outcomes.

MRI radiomics-based evaluation of tuberculous and brucella spondylitis

OBJECTIVES

We analyzed magnetic resonance imaging (MRI) and radiomics labels from tuberculous spondylitis (TBS) and brucella spondylitis (BS) to build machine learning models that differentiate TBS from BS and culture-positive TBS (TBS(+)) from culture-negative TBS (TBS(-).

METHODS

This retrospective study included 56 patients with BS, 63 patients with TBS(+) and 71 patients with TBS(-). Radiomics labels were extracted from T2-weighted fat-suppression images. MRI labels were analyzed via logistic regression (LR); radiomics labels were analyzed by t-tests, SelectKBest, and least absolute shrinkage and selection operator (LASSO). Random forest (RF) and support vector machine (SVM) models were established using radiomics or joint (radiomics+MRI) labels. Models were evaluated by receiver operating characteristic curves, areas under the curve (AUCs), decision curve analysis (DCA), and Hosmer-Lemeshow tests.

RESULTS

When joint-label models were used to compare BS vs TBS(+) and BS vs TBS(-) groups, SVM AUCs were 0.904 and 0.944, respectively, whereas RF AUCs were 0.950 and 0.947, respectively; these were higher than the AUCs of the MRI label-based LR model. DCA showed that radiomics-based machine learning models had a greater net benefit; Hosmer-Lemeshow tests demonstrated good prediction consistency for all models.

CONCLUSIONS

Radiomics can help distinguish TBS from BS and TBS(+) from TBS(-).

Development and validation of a diagnostic model for differentiating tuberculous spondylitis from brucellar spondylitis using machine learning: A retrospective cohort study

Background

Tuberculous spondylitis (TS) and brucellar spondylitis (BS) are commonly observed in spinal infectious diseases, which are initially caused by bacteremia. BS is easily misdiagnosed as TS, especially in underdeveloped regions of northwestern China with less sensitive medical equipment. Nevertheless, a rapid and reliable diagnostic tool remains to be developed and a clinical diagnostic model to differentiate TS and BS using machine learning algorithms is of great significance.

Methods

A total of 410 patients were included in this study. Independent factors to predict TS were selected by using the least absolute shrinkage and selection operator (LASSO) regression model, permutation feature importance, and multivariate logistic regression analysis. A TS risk prediction model was developed with six different machine learning algorithms. We used several metrics to evaluate the accuracy, calibration capability, and predictability of these models. The performance of the model with the best predictability was further verified with the area under the curve (AUC) of the receiver operating characteristic (ROC) curve and the calibration curve. The clinical performance of the final model was evaluated by decision curve analysis.

Results

Six variables were incorporated in the final model, namely, pain severity, CRP, x-ray intervertebral disc height loss, x-ray endplate sclerosis, CT vertebral destruction, and MRI paravertebral abscess. The analysis of appraising six models revealed that the logistic regression model developed in the current study outperformed other methods in terms of sensitivity (0.88 ± 0.07) and accuracy (0.79 ± 0.07). The AUC of the logistic regression model predicting TS was 0.86 (95% CI, 0.81-0.90) in the training set and 0.86 (95% CI, 0.78-0.92) in the validation set. The decision curve analysis indicated that the logistic regression model displayed a higher clinical efficiency in the differential diagnosis.

Conclusions

The logistic regression model developed in this study outperformed other methods. The logistic regression model demonstrated by a calculator exerts good discrimination and calibration capability and could be applicable in differentiating TS from BS in primary health care diagnosis.

Imaging of Musculoskeletal Soft-Tissue Infections in Clinical Practice: A Comprehensive Updated Review

Musculoskeletal soft-tissue infections include a wide range of clinical conditions that are commonly encountered in both emergency departments and non-emergency clinical settings. Since clinical signs, symptoms, and even laboratory tests can be unremarkable or non-specific, imaging plays a key role in many cases. MRI is considered the most comprehensive and sensitive imaging tool available for the assessment of musculoskeletal infections. Ultrasound is a fundamental tool, especially for the evaluation of superficially located diseases and for US-guided interventional procedures, such as biopsy, needle-aspiration, and drainage. Conventional radiographs can be very helpful, especially for the detection of foreign bodies and in cases of infections with delayed diagnosis displaying bone involvement. This review article aims to provide a comprehensive overview of the radiological tools available and the imaging features of the most common musculoskeletal soft-tissue infections, including cellulitis, necrotizing and non-necrotizing fasciitis, foreign bodies, abscess, pyomyositis, infectious tenosynovitis, and bursitis.

One-stage posterior surgery combined with anti-Brucella therapy in the management of lumbosacral brucellosis spondylitis: a retrospective study

Background

This study aimed to assess the clinical efficacy of one-stage posterior surgery combined with anti-Brucella therapy in the treatment of lumbosacral brucellosis spondylitis (LBS).

Methods

From June 2010 to June 2020, the clinical and radiographic data of patients with LBS treated by one-stage posterior surgery combined with anti-Brucella therapy were retrospectively analyzed. The visual analogue scale (VAS), Japanese Orthopaedic Association (JOA) and Oswestry Disability Index scores (ODI) were used to evaluate the clinical outcomes. Frankel’s classification system was employed to access the initial and final neurologic function. Fusion of the bone grafting was classified by Bridwell’s grading system.

Results

A total of 55 patients were included in this study with a mean postoperative follow-up time of 2.6 ± 0.8 years (range, 2 to 5). There were 40 males and 15 females with a mean age of 39.8 ± 14.7 years (range, 27 to 57). The Brucella agglutination test was ≥ 1:160 in all patients, but the blood culture was positive in 43 patients (78.1%). A statistical difference was observed in ESR, CRP, VAS, ODI, and JOA between preoperative and final follow-up (P < 0.05). Neurological function was significantly improved in 20 patients with preoperative neurological dysfunction after surgery. According to Bridwell’s grading system, the fusion of bone grafting in 48 cases (87.2%) was defined as grade I, and grade II in 7 cases (12.7%). None of the infestation recurrences was observed.

Conclusion

One-stage posterior surgery combined with anti-Brucella therapy was a practical method in the treatment of LBS with severe neurological compression and spinal sagittal imbalance.

Bone and Joint Infections: The Role of Imaging in Tailoring Diagnosis to Improve Patients' Care

Imaging is needed for the diagnosis of bone and joint infections, determining the severity and extent of disease, planning biopsy, and monitoring the response to treatment. Some radiological features are pathognomonic of bone and joint infections for each modality used. However, imaging diagnosis of these infections is challenging because of several overlaps with non-infectious etiologies. Interventional radiology is generally needed to verify the diagnosis and to identify the microorganism involved in the infectious process through imaging-guided biopsy. This narrative review aims to summarize the radiological features of the commonest orthopedic infections, the indications and the limits of different modalities in the diagnostic strategy as well as to outline recent findings that may facilitate diagnosis.

Differentiating brucella spondylitis from tuberculous spondylitis by the conventional MRI and MR T2 mapping: a prospective study

Background

Brucella spondylitis (BS) and tuberculous spondylitis (TS), caused initially by bacteremia, are the two leading types of granulomatous spinal infections. BS is easy to miss or may be misdiagnosed as TS. Our purpose aims to differentiate BS from TS in conventional MR imaging and MR T2 mapping.

Methods

We performed on 26 BS and 27 TS patients conventional MR imaging and MR T2 mapping. We analyzed the features in conventional MR imaging and measured T2 values of the lesion vertebrae (LV) and unaffected adjacent vertebrae (UAV) in BS and TS patients, respectively.

Results

There were no significant differences in sex, age, national between BS and TS. There was significantly lower severity of vertebral destruction, vertebral posterior convex deformity, dead bone, and abscess scope in BS when compared to TS (p  <  0.001, p  =  0.048, p  <  0.001, p  <  0.001, respectively). The vertebral hyperplasia was significantly higher in BS when compared to TS (p  <  0.001). The T2 value of the LV with BS was markedly higher than that in the UAV with BS and that in the LV and UAV with TS (p  <  0.001, p  <  0.037, p  <  0.001, respectively). The T2 value of the LV with TS was significantly higher than that of the UAV in TS and BS (p  <  0.001, p  <  0.001, respectively). There were no significant differences in the T2 value of the UAV between BS and TS (p  =  0.568).

Conclusions

The qualitative and quantitative evaluation may differentiate BS from TS. The conventional MR imaging helps to distinguish BS from TS by several distinctive features. MR T2 mapping has the additional potential to provide quantitative information between BS and TS.

Differentiation between infectious spondylodiscitis versus inflammatory or degenerative spinal changes: How can magnetic resonance imaging help the clinician?

Spondylodiscitis is a complex disease whose diagnosis and management are still challenging. The differentiation between infectious and non-infectious aetiology is mandatory to avoid delays in the treatment of life-threatening infectious conditions. Imaging methods, in particular magnetic resonance imaging (MRI), play a key role in differential diagnosis. MRI provides detailed anatomical information, especially regarding the epidural space and spinal cord, and may allow differential diagnosis by assessing the characteristics of certain infectious and inflammatory/degenerative lesions. In this article, we provide an overview of the radiological characteristics and differentiating features of non-infectious inflammatory spinal disorders and infectious spondylodiscitis, focussing on MRI results and presenting relevant clinical and pathological features that help early diagnosis.

Tuberculous and Brucellar Spondylodiscitis: Comparative Analysis of Clinical, Laboratory, and Radiological Features

Study Design

This was a retrospective study.

Purpose

The aim was to compare the clinical, laboratory, radiological, and evolutionary features of tuberculous spondylodiscitis (TS) and brucellar spondylodiscitis (BS).

Overview of Literature

Clinical presentation of spondylodiscitis varies according to the underlying etiology, among which brucellosis and tuberculosis represent the primary cause, in endemic countries. Only a few studies have compared the characteristics between TS and BS.

Methods

A retrospective study was conducted using the data of all patients hospitalized for TS and BS in the infectious diseases department between 1991 and 2018.

Results

Among a total of 117 patients, 73 had TS (62.4%) and 44 had BS (37.6%). Females were significantly more affected with TS than males (56.2% vs. 22.7%, p<0.001). Fever (72.7% vs. 45.2%, p=0.004) and sweating (72.7% vs. 47.9%, p=0.009) were significantly more frequent among patients with BS. The median erythrocyte sedimentation rate was significantly higher in the TS group (median, 70 mm/hr; interquartile range [IQR], 45–103 mm/hr) than in the BS group (median, 50 mm/hr; IQR, 16–75 mm/hr) (p=0.003). Thoracic involvement was significantly more frequent in the TS group (53.4% vs. 34.1%, p=0.04), whereas lumbar involvement was significantly more frequent in the BS group (72.7% vs. 49.3%, p=0.01). Initial imaging findings revealed significantly higher frequencies of posterior vertebral arch involvement, vertebral compaction, and spinal cord compression in the TS group. Percutaneous abscess drainage (20.5% vs. 2.3%, p=0.005) and surgical treatment (17.8% vs. 2.3%, p=0.01) were more frequently indicated in the TS group, with a significant difference.

Conclusions

A combination of clinical, laboratory, and radiological features can be used to distinguish between TS and BS while these patients await diagnosis confirmation.

Brucellar spondylodiscitis: A case series with focus on histopathological features

Brucellar spondylodiscitis (BS) is the most common form of musculoskeletal brucellosis. The isolation of Brucella spp from blood, other body fluids or tissue cultures is the gold standard for definitive diagnosis of BS. BS shows a large histopathological spectrum of lesions with non-specific and granulomatous forms, and its histopathological features are not widely reported. This case series study reported the histopathological features of a series of 21 BS. Ten cases revealed nonspecific forms of BS. Lymphocytes were the predominant inflammatory cells in this group. In one case neutrophils were predominant. The eleven remaining were granulomatous. The 11 exhibited histiocytic type granulomas. Ten were non-necrotizing. One case, taken from abscess wall, contained minimal deposition of caseous like necrotic material. This case and 2 others corresponding to abscess wall biopsies, showed histiocytic granulomas mixed with small aggregates of epithelioid cells without well-formed epithelioid granuloma nor giant cell. The histopathological diagnosis of BS is challenging. Nonspecific forms of BS, mimiking pyogenic spondylodiscitis, are observed in about half of the cases. Although nonspecific forms of BS are characterized by the predominance of lymphocytes and plasmocytes, BS forms with predominant neutrophil cell infiltration do exist. Histiocytic granuloma is highly suggestive of BS. Purely epithelioid forms of BS were not observed in the present series. Caseous like necrosis suggestive of tuberculosis is a possible feature of BS.