Spinal Magnetic Resonance Imaging Research Articles

Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging.

A deep learning (DL) model that can automatically detect and classify cervical canal and neural foraminal stenosis using cervical spine magnetic resonance imaging (MRI) can improve diagnostic accuracy and efficiency. A method comprising region-of-interest (ROI) detection and cascade prediction was formulated for diagnosing cervical spinal stenosis based on a DL model. First, three part-specific convolutional neural networks were employed to detect the ROIs in different parts of the cervical MR images. Cascade prediction of the stenosis categories was subsequently performed to record the stenosis level and position on each patient slice. Finally, the results were combined to obtain a patient-level diagnostic report. Performance was evaluated based on the accuracy (ACC), area under the curve (AUC), sensitivity, specificity, F1 Score, diagnosis time of the DL model, and recall rate for ROI detection localization. The average recall rate of the ROI localization was 89.3% (neural foramen) and 99.7% (central canal) under the five-fold cross-validation of the DL model. In the dichotomous classification (normal or mild vs. moderate or severe), the ACC and AUC of the DL model were comparable to those of the radiologists, and the F1 score (84.8%) of the DL model was slightly higher than that of the radiologists (83.8%) for the central canal. Diagnosing whether the central canal or neural foramen of a slice is narrowed in the cervical MRI scan required an average of 15 and 0.098s for the radiologists and DL model, respectively. The DL model demonstrated comparable performance with subspecialist radiologists for the detection and classification of central canal and neural foraminal stenosis on cervical spine MRI. Moreover, the DL model demonstrated significant timesaving ability.

Auto-Rad: End-to-End Report Generation from Lumber Spine MRI Using Vision–Language Model

Background: Lumbar spinal stenosis (LSS) is a major cause of chronic lower back and leg pain, and is traditionally diagnosed through labor-intensive analysis of magnetic resonance imaging (MRI) scans by radiologists. This study aims to streamline the diagnostic process by developing an automated radiology report generation (ARRG) system using a vision–language (VL) model. Methods: We utilized a Generative Image-to-Text (GIT) model, originally designed for visual question answering (VQA) and image captioning. The model was fine-tuned to generate diagnostic reports directly from lumbar spine MRI scans using a modest set of annotated data. Additionally, GPT-4 was used to convert semistructured text into coherent paragraphs for better comprehension by the GIT model. Results: The model effectively generated semantically accurate and grammatically coherent reports. The performance was evaluated using METEOR (0.37), BERTScore (0.886), and ROUGE-L (0.3), indicating its potential to produce clinically relevant content. Conclusions: This study highlights the feasibility of using vision–language models to automate report generation from medical imaging, potentially reducing the diagnostic workload for radiologists.

Diagnostic performance of dual-energy CT with electron-density reconstruction for lumbar disc herniation

Background: Magnetic resonance imaging (MRI) is used for the evaluation of degenerative spinal disease. However, its utility is restricted in routine practice because of contraindications and a lack of widespread availability. Dual-energy computed tomography (DECT) is a newer technique for the evaluation of degenerative spinal disease.Objectives: This study aimed to evaluate the diagnostic performance of DECT with electron-density (ED) image reconstruction compared to standard CT for the detection of lumbar disc herniation, with MRI as the gold standard.Method: The retrospective study included 84 patients between 01 July 2023 to 31 December 2023 who underwent DECT and 1.5-T MRI within 1 week. Four radiologists, blinded to the clinical and MRI information, independently evaluated the standard CT series and DECT series with ED reconstructions for lumbar disc herniation and spinal nerve root impingement. The gold standard for comparison was lumbar spine MRI, and diagnostic accuracy was measured with sensitivity and specificity.Results: MRI revealed 417 lumbar disc herniations. Dual-energy computed tomography with ED reconstruction showed higher sensitivity (86.36% [532/616] vs. 57.79% [356/616]) and specificity (96.86% [1019/1052] vs. 95.82% [1008/1052]) for the detection of lumbar disc herniation compared to standard CT.Conclusion: Dual-energy computed tomography with ED reconstruction shows better diagnostic performance for the detection of lumbar disc herniation compared to standard CT and can be a useful alternative imaging modality when MRI is contraindicated or unavailable.Contribution: This study shows the usefulness of DECT as an alternative imaging technique for screening of degenerative spinal disease whenever MRI is contraindicated or unavailable.

An unusual late complication of peridural anesthesia: The case of a subdural spinal epidermoid cyst: A case report and literature review

The peridural approach is primarily used today to provide analgesia in obstetrics and postoperative care. Peridural analgesia is not only more effective than systemic analgesia, but it also has benefits in terms of morbidity, particularly regarding postoperative respiratory complications and the shortened duration of postoperative ileus. Unlike dural tears, immediate and severe neurological complications such as hematomas or abscesses are very rare. Long-term sequelae are less well known because the relationship with epidural analgesia performed several months or years earlier is not always well established. We report a rare case of a 35-year-old patient with a history of epidural anesthesia five years ago during childbirth, who was admitted with cauda equina syndrome. MRI (magnetic resonance imaging) of the lumbar spine showed a subdural lesion at the level of L3. The patient underwent resection of the lesion, and the pathological examination of the surgical specimen concluded it was an epidermoid cyst.

DNAR-13. LONG TERM FOLLOW-UP OF A LYNCH SYNDROME-ASSOCIATED GLIOBLASTOMA RESISTANT TO STANDARD-OF-CARE CHEMORADIATION

Abstract BACKGROUND Lynch syndrome is caused by pathogenic germline variants in the DNA mismatch repair (MMR) genes, predisposing individuals to malignancies, including glioblastoma (GBM). MMR-deficient tumors are resistant to monofunctional alkylators such as temozolomide but not to bifunctional alkylators such as the nitrosourea lomustine. Anti-programmed cell death protein 1 (PD1) immune checkpoint inhibitor (ICI) pembrolizumab represents another treatment option, which is approved by the United States Food and Drug Administration (FDA) for the treatment of mismatch repair deficient cancers. METHODS We present a patient with multifocal GBM and Lynch syndrome who experienced rapid progression following standard-of-care chemoradiation, followed by durable responses to lomustine and then to pembrolizumab. RESULTS A 58-year-old man with Lynch syndrome (MSH2 mutation) and prior history of colon cancer presented with seizures. Magnetic resonance imaging (MRI) brain identified right frontal and left parietal masses. Right frontal tumor was resected; pathology was consistent with GBM, IDH wildtype, MGMT-unmethylated. Both lesions were treated with radiation therapy (60 Gy, 30 fractions) with concurrent and adjuvant temozolomide. After two cycles of adjuvant temozolomide, his left parietal tumor progressed and was subtotally resected, followed by four cycles of lomustine (stopped due to myelotoxicity). He remained progression-free for 15 months. Surveillance MRI identified new enhancement involving the left frontal lobe, left periventricular white matter, and right internal auditory canal, concerning for leptomeningeal dissemination. MRI spine identified no additional lesions. Cerebrospinal fluid cytology was negative for tumor cells on two occasions. Patient was treated with pembrolizumab. He remains on treatment with stable disease four months after ICI initiation and 31 months after GBM diagnosis. CONCLUSIONS Patients with MMR-deficient GBM resist standard chemoradiation. Alternatives such as nitrosourea or ICI therapy may achieve durable responses. While data is insufficient to administer these agents as upfront therapy in this specific setting, both should be considered as options for recurrent disease.

Compare three deep learning-based artificial intelligence models for classification of calcified lumbar disc herniation: a multicenter diagnostic study.

To develop and validate an artificial intelligence diagnostic model for identifying calcified lumbar disc herniation based on lateral lumbar magnetic resonance imaging(MRI). During the period from January 2019 to March 2024, patients meeting the inclusion criteria were collected. All patients had undergone both lumbar spine MRI and computed tomography(CT) examinations, with regions of interest (ROI) clearly marked on the lumbar sagittal MRI images. The participants were then divided into separate sets for training, testing, and external validation. Ultimately, we developed a deep learning model using the ResNet-34 algorithm model and evaluated its diagnostic efficacy. A total of 1,224 eligible patients were included in this study, consisting of 610 males and 614 females, with an average age of 53.34 ± 10.61 years. Notably, the test datasets displayed an impressive classification accuracy rate of 91.67%, whereas the external validation datasets achieved a classification accuracy rate of 88.76%. Among the test datasets, the ResNet34 model outperformed other models, yielding the highest area under the curve (AUC) of 0.96 (95% CI: 0.93, 0.99). Additionally, the ResNet34 model also exhibited superior performance in the external validation datasets, exhibiting an AUC of 0.88 (95% CI: 0.80, 0.93). In this study, we established a deep learning model with excellent performance in identifying calcified intervertebral discs, thereby offering a valuable and efficient diagnostic tool for clinical surgeons.

Magnetic Resonance Imaging Diagnosis of Spinal Longitudinal Epidural Collections in a Spontaneous Spinal Dural Breach and Successful Surgical Treatment

Spontaneous intracranial hypotension is generally secondary to cerebrospinal fluid leaks. Spinal magnetic resonance imaging is an important part of the diagnostic workup, especially to display spinal longitudinal epidural collections. Other causes of leaks include nerve root sleeve tear and cerebrospinal fluid-venous fistula. We propose a standard magnetic resonance imaging protocol including sagittal T1, T2-weighted, and T2 fat-saturated sequences, with addition of high-resolution three-dimensional T2 images to improve detection of spinal longitudinal epidural collections and help locate the dural breach level. Spine computed tomography may prove useful in detecting a bony spur that may cause the dural breach. Treatment of identified dural breaches includes targeted epidural blood patch or neurosurgery in case of blood patch inefficacy. Few cases of successful surgical treatments of dural breaches have been reported with complete regression of spinal longitudinal epidural collections; thus more studies will be valuable to help establish guidelines in this pathology.

Evaluation of Brain and Spinal Cord Lesions and Cerebrospinal Fluid Analysis in Detecting Demyelinating Diseases in Patients with Optic Neuritis

ABSTRACT Optic neuritis can be an early sign of demyelinating diseases like multiple sclerosis (MS), neuromyelitis optica spectrum disorders (NMOSD), and myelin oligodendrocyte glycoprotein (MOG) antibody-associated diseases (MOGAD). We investigated the presence or absence of head and spinal cord lesions on magnetic resonance imaging (MRI) and assessed whether cerebrospinal fluid (CSF) tests are useful in detecting demyelinating disease in patients with first diagnosed optic neuritis. We conducted a retrospective study of 111 patients (47 idiopathic, 19 NMOSD, 16 MOGAD, 16 MS, 6 optic neuritis with cerebral lesions but that does not meet the McDonald’s criteria for MS (ON+)), and 7 chronic relapsing inflammatory optic neuropathy) diagnosed with optic neuritis without cerebral or spinal symptoms. Patients underwent evaluations including orbital, head, and spine MRI, along with CSF analysis. Among the 111 patients, 20 (35.1%: 4 NMOSD, 4 MOGAD, 7 MS, and 6 ON+) exhibited intracerebral or spinal cord lesions. Twelve patients showed findings on both orbital and head MRI, while six had no orbital MRI findings except for optic neuritis but exhibited lesions on head MRI. Five patients had spinal lesions without intracerebral lesions. CSF analysis revealed positive oligoclonal bands and elevated myelin basic protein levels indicate the high likelihood with systemic inflammatory demyelinating diseases. Even in the absence of concomitant encephalitis or myelitis symptoms or a history of these conditions, MRI images of patients with optic neuritis sometimes reveal lesions in the brain or spinal cord. CSF abnormalities were indicative of systemic demyelinating disease presence, extending beyond MS to NMOSD and MOGAD.

Natural language processing-based analysis of the level of adoption by expert radiologists of the ASSR, ASNR and NASS version 2.0 of lumbar disc nomenclature: an eight-year survey.

The American Society of Spine Radiology (ASSR), American Society of Neuroradiology (ASNR), and North American Spine Society (NASS) published a consensus paper with recommendations for lumbar disc nomenclature reports in 2014. We aimed to evaluate the degree of adoption in our radiology department of the ASSR, ASNR, and NASS 2.0 lumbar spine consensus paper using natural language processing (NLP). In March 2015 we gave in our radiology department, at HT Medica in Jaén (Spain) a lecture detailing the changes proposed in the ASSR, ASNR, and NASS consensus about lumbar disc nomenclature, version 2.0. We analyzed 34,064 lumbar spine magnetic resonance imaging (MRI) reports from three different expert radiologists (A, B, and C) performed from May 2010 to February 2015 (15,813 studies) and from March 2015 to February 2022 (18,251 studies). Using an NLP algorithm, we evaluated 29 old and new terms related to 4 different categories: disc with fissures of the annulus, degenerated disc, herniated disc, and location of the disc. A relevant decrease in the percentage of use of old terms was found for degenerated disc category (44.63% for radiologist B and 18.95% for radiologist C) and disc localization (18.86% for radiologist A and 27.73% for radiologist C). Relevant increments in the percentage of use of new lexicon were depicted for terms related to degenerated disc (32.48% for radiologist C), herniated disc (7.27% for radiologist A) and disc localization (36.53% for radiologist C). NLP algorithms may help to manage large radiological report datasets to evaluate the impact and degree of adherence of radiologists to recommendations for the use of ASSR, ASNR and NASS lumbar disc nomenclature version 2.0.

MFFE CT-like MRI Sequences for the Assessment of Vertebral Fractures.

The aim of this study was to evaluate the diagnostic performance, image quality, and inter- and intra-observer agreement of the 3D T1 multi-echo fast field echo (mFFE) sequence in cervico-thoraco-lumbar vertebral fractures compared with conventional computed tomography (CT) as the gold standard. We conducted a prospective single-centre study including 29 patients who underwent spinal magnetic resonance imaging (MRI) at the surgeon's request, in addition to CT for vertebral fracture assessment and classification. A 3D T1 mFFE sequence was added to the standard MRI protocol. Consecutively, two readers analyzed the 3D mFFE sequence alone, the 3D mFFE sequence with the entire MRI protocol, including the STIR and T1 sequences, and, finally, the CT images in random order and 1 month apart. A standardized assessment was performed to determine the presence or absence of a fracture, its location, its classification according to the Genant and AO classifications for traumatic and osteoporotic fractures, respectively, the loss of height of the anterior and posterior walls of the vertebral body, and the presence of concomitant disco-ligamentous lesions. Contingency tables, intraclass correlation coefficients, and Cohen's kappa tests were used for statistical analysis. A total of 25 fractures were recorded (48% cervical, 20% thoracic, and 32% lumbar), of which 52% were classified A, according to the AO classification system. The quality of the 3D mFFE image was good or excellent in 72% of cases. Inter-observer agreement was near perfect (0.81-1) for vertebral body height and for AO and Genant classifications for all modalities. Intra-observer agreement was strong-to-near perfect between CT and the 3D mFFE sequence. Regarding the diagnostic performance of the 3D mFFE sequence, the sensitivity was 0.9200 and 0.9600, the specificity was 0.9843 and 0.9895, and the accuracy was 0.9861 and 0.9769 for Readers 1 and 2, respectively. In addition, up to 40% of intervertebral disc lesions and 33% of ligamentous lesions were detected by the 3D mFFE sequence compared to CT, allowing four AO type A fractures to be reclassified as type B. The 3D mFFE sequence allows accurate diagnosis of vertebral fractures, with superiority over CT in detecting disco-ligamentous lesions and a more precise classification of fractures, which can prompt clinicians to adapt their management despite an image quality that still requires improvement in some cases. Vertebral fractures and disco-ligamentous lesions can be assessed using CT-like MRI sequences, with 3D T1 mFFE being superior to CT for the detection of disco-ligamentous lesions. CT-like images using the 3D T1 mFFE sequence improve the diagnostic accuracy of bone structures in MRI.

Does combination of urodynamic reduced bladder capacity and detrusor overactivity warrant spinal cord magnetic resonance imaging in children with persistan enuresis: a prospective study.

This study aims to evaluate the necessity of spinal cord magnetic resonance imaging (MRI) in children with persistent enuresis, specifically those presenting with urodynamically reduced bladder capacity (RBC) and detrusor overactivity (DO), in comparison to children with normal urodynamic findings. We evaluated 586 children admitted for bedwetting, all of whom received urotherapy and/or pharmacotherapy. Persistent enuresis, lasting for over one year, was identified in 134 patients who were subsequently re-evaluated for occult neurological conditions and recommended for urodynamic studies (UDS). In total, 92 patients provided informed consent and underwent UDS. Of these, 40 patients were divided into two cohorts based on UDS findings. All patients were over 6 years of age and had normal physical examinations. The first cohort consisted of 23 children RBC and DO, while the second cohort included 17 children with normal UDS findings. All participants underwent spinal cord MRI with a 3 Tesla scanner. Urodynamic and MRI results were compared using Fisher's chi-square test. The median age of the cohort was 11 years, with 26 (65%) of the patients being female. Spinal disorders were identified in 10 patients (25%), with 8 cases of spina bifida without neurological compression and 2 cases of tethered cord. In the RBC + DO cohort, 7 out of 23 patients (30.4%) were found to have spinal disorders, compared to 3 out of 17 patients (17.6%) in the normal UDS cohort, with no statistically significant difference between the groups (p > 0.05). When evaluating persistent enuresis nocturna, a combination of RBC and DO in children with nocturnal enuresis and daytime symptoms may warrant spinal cord MRI, though with limited cost-effectiveness.

Enhancing spinal MRI segmentation with an asymmetric U-Net architecture

Spinal diseases are among the most prevalent health issues in modern society, significantly impacting patients’ quality of life. Diagnosing conditions such as disc herniation and spinal deformity requires advanced medical imaging techniques, including X-rays, magnetic resonance imaging (MRI), computed tomography, and nuclear magnetic resonance. Spine MRI is particularly crucial due to its ability to provide high-resolution images of soft tissues, essential for accurate diagnosis. However, the manual segmentation of spine MRI images is labor-intensive and inadequate for large-scale quantitative analysis. Thus, developing automated spinal MRI segmentation methods is critical to alleviating doctors’ workload and enhancing diagnostic efficiency. In this study, we propose a novel asymmetric U-Net architecture designed to improve the precision of reconstructing complex structures and details by increasing the depth of the upsampling side. The model incorporates adjacent-scale skip connections to control parameters while maintaining high segmentation accuracy. In addition, residual connections on the upsampling side prevent gradient vanishing, thereby enhancing the network’s feature learning and representation capabilities. Experimental results indicate that this method significantly reduces training time and increases model accuracy compared to traditional approaches, marking a substantial advancement in automated spinal MRI segmentation. This innovative approach holds promise for improving clinical outcomes and optimizing the workflow in medical imaging departments.

Phenotypic, Electrophysiologic, and Imaging Spectrum of Hirayama Disease from Northern India.

Cervical flexion-induced myelopathy, also known as Hirayama disease (HD), is a lower motor neuron disorder seen mainly in adolescents and young adults, affecting the C7-T1 myotomes, presenting as asymmetric weakness with wasting of one or both the distal upper limbs. We aimed to describe the clinical features, electrophysiology, and radiologic features of HD in a tertiary care institute in northern India. One hundred and forty patients between 2017 and 2022 with clinical and imaging features consistent with HD were retrospectively reviewed from the All India Institute of Medical Sciences-Comprehensive Neuromuscular Diseases center database. Majority were males with the mean age of onset of illness being 17.8 years. The median duration of the symptoms was 3 (1.5-4) years. Sixty-nine (49%) patients had unilateral involvement, and the disease was actively progressing in 88 (63%) patients at presentation. Two families had history of HD in two (1.4%) siblings. Electromyography showed abnormal findings in the clinically involved limb in all the patients and in the clinically uninvolved limb in 17/50 (34%) patients. Flexion magnetic resonance imaging (MRI) demonstrated forward dural displacement in 134 (96%) patients and asymmetric cord flattening in 124 (88.5%) patients. Disability was graded as mild, moderate, and severe; 12 (13%) had severe disability. The majority were managed conservatively, and four underwent surgery for HD. A high index of suspicion of HD needs to be kept in a young male presenting with distal upper limb weakness and atrophy. Dynamic MRI of the cervical spine in young adults presenting with hand wasting is inevitable. This disease needs to be managed aggressively and early to prevent serious dysfunction and loss of productivity.

Comprehensive assessment of imaging quality of artificial intelligence-assisted compressed sensing-based MR images in routine clinical settings

BackgroundConventional MR acceleration techniques, such as compressed sensing, parallel imaging, and half Fourier often face limitations, including noise amplification, reduced signal-to-noise ratio (SNR) and increased susceptibility to artifacts, which can compromise image quality, especially in high-speed acquisitions. Artificial intelligence (AI)-assisted compressed sensing (ACS) has emerged as a novel approach that combines the conventional techniques with advanced AI algorithms. The objective of this study was to examine the imaging quality of the ACS approach by qualitative and quantitative analysis for brain, spine, kidney, liver, and knee MR imaging, as well as compare the performance of this method with conventional (non-ACS) MR imaging.MethodsThis study included 50 subjects. Three radiologists independently assessed the quality of MR images based on artefacts, image sharpness, overall image quality and diagnostic efficacy. SNR, contrast-to-noise ratio (CNR), edge content (EC), enhancement measure (EME), scanning time were used for quantitative evaluation. The Cohen’s kappa correlation coefficient (k) was employed to measure radiologists’ inter-observer agreement, and the Mann Whitney U-test used for comparison between non-ACS and ACS.ResultsThe qualitative analysis of three radiologists demonstrated that ACS images showed superior clinical information than non-ACS images with a mean k of ~ 0.70. The images acquired with ACS approach showed statistically higher values (p < 0.05) for SNR, CNR, EC, and EME compared to the non-ACS images. Furthermore, the study’s findings indicated that ACS-enabled images reduced scan time by more than 50% while maintaining high imaging quality.ConclusionIntegrating ACS technology into routine clinical settings has the potential to speed up image acquisition, improve image quality, and enhance diagnostic procedures and patient throughput.

An open-access lumbosacral spine MRI dataset with enhanced spinal nerve root structure resolution

Spinal cord injury (SCI) profoundly affects an individual’s ability to move. Fortunately, recent advancements in neuromodulation, particularly the spatio-temporal epidural electrical stimulation (EES) targeting the spinal nerve roots, promoted rapid rehabilitation of SCI patients. Such neuromodulation techniques require precise anatomical modelling of spinal cord. However, the lack of spine imaging datasets, especially high-quality magnetic resonance imaging (MRI) datasets highlighting nerve roots, hinders the translation of EES into medical practice. To address this problem, we introduce an open-access lumbosacral spine MRI dataset acquired in 14 healthy adults, using constructive interference in steady state (CISS) sequence, double echo steady state (DESS) sequence, and T2-weight turbo spin echo (T2-TSE) sequence, with enhanced nerve root resolution. The dataset also includes the corresponding anatomical annotations of nerve roots and the final reconstructed 3D spinal cord models. The quality of our dataset is assessed using image quality metrics implemented in MRI quality control tool (MRIQC). Our dataset provides a valuable platform to promote a wide range of spinal cord neuromodulation research and collaboration among neurorehabilitation engineers.

Steroid response in a rare case of vertebrae butterfly with spinal cord compression caused by chronic subdural hematoma

IntroductionSpinal subdural hematoma (SSH) is a rare entity. Clinical symptoms include motor, sensory and/or autonomic dysfunction due to compression of the spinal cord. There is no standard consensus in the management of SSH. Here, we report a rare case of SSH of sudden onset following trauma, successfully treated with conservative therapy.AimThis case highlights butterfly vertebrae as an incidental imaging finding before SSH diagnosis.Case studyA 30-year-old female presented with weakness in the lower extremities after trauma, accompanied by paresthesia, urinary retention, and impaired defecating function. The thermoregulatory sweat exam revealed sudomotor dysfunction. Multiple slice computed tomography (MSCT) examination of the whole spine revealed wedge deformity of vertebral corpus (VC) L4 on the right lateral side, and VC L5 butterfly vertebrae. Spine magnetic resonance imaging (MRI) revealed an extramedullary intradural lesion at the T7 to T10 level suggestive of subdural hematoma.Results and discussionThe administration of methylprednisolone pulse therapy, combined with physical rehabilitation, led to a rapid and significant improvement in the patient's motor function. The absence of the spinal pain possibly indicated that there was no more extension of the hematoma; motor recovery, even if slight, should be a predictor of successful conservative therapy, and physical rehabilitation.ConclusionsSSH is an uncommon condition, with varying clinical presentation, and progression. This case report highlights significant improvement following conservative steroid treatment of a SSH. It also highlights a unique incidental finding of butterfly vertebra in a patient with paraparesis following trauma.

Role of Artificial intelligence model in prediction of low back pain using T2 weighted MRI of Lumbar spine.

Low back pain (LBP), the primary cause of disability, is the most common musculoskeletal disorder globally and the primary cause of disability. Magnetic resonance imaging (MRI) studies are inconclusive and less sensitive for identifying and classifying patients with LBP. Hence, this study aimed to investigate the role of artificial intelligence (AI) models in the prediction of LBP using T2 weighted MRI image of the lumbar spine. This was a prospective case-control study. A total of 200 MRI patients (100 cases and controls each) referred for lumbar spine and whole spine screening were included. The scans were performed using 3.0 Tesla MRI (United Imaging Healthcare). T2 weighted images of the lumbar spine were segmented to extract radiomic features. Machine learning (ML) models, such as random forest, decision tree, logistic regression, K-nearest neighbors, adaboost, and deep learning methods (DL), such as ResNet and GoogleNet, were used, and performance measures were calculated. Our study showed that Random forest and AdaBoost are the most reliable ML models for predicting LBP. Random forest showed high performance with area under curve (AUC) values from 0.83 to 0.88 across all lumbar vertebrae and L2-L3, L3-L4, and L4-L5 intervertebral discs (IVDs), with AUCs of 0.88 the highest at L5-S1 IVD (0.92). Adaboost demonstrated high performance at the L2-L5 vertebrae with AUC values of 0.82 to 0.90, with the highest AUC (0.97) at the L5-S1 IVD. Among the DL models, GoogleNet outperformed the other models at 30 epochs with an accuracy of 0.85, followed by ResNet 18 (30 epochs) with an accuracy of 0.84. The study demonstrated that ML and DL models can effectively predict LBP from MRI T2 weighted image of the lumbar spine. ML and DL models could also enhance the diagnostic accuracy of LBP, potentially leading to better patient management and outcomes.

Spiral volumetric optoacoustic tomography of reduced oxygen saturation in the spinal cord of M83 mouse model of Parkinson's disease.

Metabolism and bioenergetics in the central nervous system play important roles in the pathophysiology of Parkinson's disease (PD). Here, we employed a multimodal imaging approach to assess oxygenation changes in the spinal cord of the transgenic M83 murine model of PD overexpressing the mutated A53T alpha-synuclein form in comparison with non-transgenic littermates. In vivo spiral volumetric optoacoustic tomography (SVOT) was performed to assess oxygen saturation (sO2) in the spinal cords of M83 mice and non-transgenic littermates. Ex vivo high-field T1-weighted (T1w) magnetic resonance imaging (MRI) at 9.4T was used to assess volumetric alterations in the spinal cord. 3D SVOT analysis and deep learning-based automatic segmentation of T1w MRI data for the mouse spinal cord were developed for quantification. Immunostaining for phosphorylated alpha-synuclein (pS129 α-syn), as well as vascular organization (CD31 and GLUT1), was performed after MRI scan. In vivo SVOT imaging revealed a lower sO2SVOT in the spinal cord of M83 mice compared to non-transgenic littermates at sub-100μm spatial resolution. Ex vivo MRI-assisted by in-house developed deep learning-based automatic segmentation (validated by manual analysis) revealed no volumetric atrophy in the spinal cord of M83 mice compared to non-transgenic littermates at 50μm spatial resolution. The vascular network was not impaired in the spinal cord of M83 mice in the presence of pS129 α-syn accumulation. We developed tools for deep-learning-based analysis for the segmentation of mouse spinal cord structural MRI data, and volumetric analysis of sO2SVOT data. We demonstrated non-invasive high-resolution imaging of reduced sO2SVOT in the absence of volumetric structural changes in the spinal cord of PD M83 mouse model.

Assessment of chemical-shift and diffusion-weighted magnetic resonance imaging in differentiating malignant and benign vertebral lesions in oncologic patients. A single institution experience.

To analyze the contribution of two non-standard magnetic resonance imaging (MRI) techniques the chemical-shift image (CSI), and diffusion-weighted imaging (DWI) in distinguishing malignant and benign vertebral bone marrow lesions (VBMLs). Conventional spine MRI protocol, followed by CSI and DWI was performed with a 1.5 T system on 102 oncologic patients between January 2020 and December 2023. From the identified 325 VBMLs, 102 representative lesions (one per patient) were selected. VBMLs were divided into malignant (n = 74) and benign (n = 28) based on histopathology, or imaging follow-up. The quantitative parameters for VBMLs assessment were signal intensity ratio (SIR) derived from CSI and apparent diffusion coefficient (ADC) derived from DWI. The malignant VBMLs had significantly higher SIR values (p < 0.05) and lower ADC values compared to benign VBMLs (p < 0.05). The area under the curve (AUC) was 0.953 (p < 0.001) for SIR, and 0.894 for ADC (p < 0.001) (cut-off at > 0.82, and ≤ 1.57x10-3 mm2/s, respectively). The sensitivity and specificity for SIR were 93.6%, and 88.5%, while for ADC were 88.2% and 92.3% (respectively). The combined use of SIR and ADC improved the diagnostic accuracy to AUC of 0.988 (p < 0.001, cut-off at > 0.19), sensitivity, and specificity of 100.0% and 90.9% (respectively). Quantitative parameters, SIR and ADC, derived from two non-standard MRI techniques, CSI, and DWI, showed diagnostic strength in differentiating malignant and benign VBMLs. Combining both methods can further enhance the diagnostic performance and accuracy of spine MRI in clinical practice.

A Case of the Anti-aquaporine-4 Antibody-negative Neuromyelitis Optica Spectrum Disorders Associated with Atopic Disease with High Concentration of Anti-IgE Autoantibody and HyperIgEemia

We report a 70-year-old male patient with the sero-negative neuromyelitis optica spectrum disorders (NMOSD) associated with atopic disease (AD). He was diagnosed with allergic rhinitis at the age of 20. When he was 61 years old, he subacutely developed orthostatic hypotension, bilateral optic neuritis, quadriparesis, urinary retention, and constipation. The laboratory results revealed allergen-specific IgE positivity for cryptomeria japonica and hinoki, hyperIgEemia, and Th (helper T cell) 1 dominance. The serological tests for autoantibodies revealed negative anti-aquaporine 4 antibody, and high concentration of anti-IgE autoantibody (anti-IgE AAb). Cerebrospinal fluid was negative for anti-myelin-oligodendrocyte glycoprotein antibody and glial fibrillary acidic protein antibody. Fluid-attenuated inversion recovery on brain magnetic resonance imaging (MRI) showed high signal intensities in bilateral cerebral deep white matter. T2 weighted image on spine MRI showed longitudinally extensive high signal intensities in the spinal cord, specifically involving C1 vertebral level to conus medullaris. Intravenous methylprednisolone (IVMP) and plasma exchange resulted in partial improvement. Following the onset of NMOSD, he had relapse of NMOSD four times. In each episode, IVMP was to be partially effective with anti-IgE AAb reduction. Anti-IgE AAb may be a reasonable clinical indicator of increased disease activity in the sero-negative NMOSD associated with AD.