Cervical Magnetic Resonance Imaging Research Articles

SwinUNeCCt: bidirectional hash-based agent transformer for cervical cancer MRI image multi-task learning

Cervical cancer is the fourth most common malignant tumor among women globally, posing a significant threat to women’s health. In 2022, approximately 600,000 new cases were reported, and 340,000 deaths occurred due to cervical cancer. Magnetic resonance imaging (MRI) is the preferred imaging method for diagnosing, staging, and evaluating cervical cancer. However, manual segmentation of MRI images is time-consuming and subjective. Therefore, there is an urgent need for automatic segmentation models to identify cervical cancer lesions in MRI scans accurately. All MRIs in our research are from cervical cancer patients diagnosed by pathology at Tongren City People’s Hospital. Strict data selection criteria and clearly defined inclusion and exclusion conditions were established to ensure data consistency and accuracy of research results. The dataset contains imaging data from 122 cervical cancer patients, with each patient having 100 pelvic dynamic contrast-enhanced MRI scans. Annotations were jointly completed by medical professionals from Universiti Putra Malaysia and the Radiology Department of Tongren City People’s Hospital to ensure data accuracy and reliability. Additionally, a novel computer-aided diagnosis model named SwinUNeCCt is proposed. This model incorporates (i) A bidirectional hash-based agent multi-head self-attention mechanism, which optimizes the interaction between local and global features in MRI, aiding in more accurate lesion identification. (ii) Reduced computational complexity of the self-attention mechanism. The effectiveness of the SwinUNeCCt model has been validated through comparisons with state-of-the-art 3D medical models, including nnUnet, TransBTS, nnFormer, UnetR, UnesT, SwinUNetR, and SwinUNeLCsT. In semantic segmentation tasks without a classification module, the SwinUNeCCt model demonstrates excellent performance across multiple key metrics: achieving a 95HD of 6.25, an IoU of 0.669, and a DSC of 0.802, all of which are the best results among the compared models. Simultaneously, SwinUNeCCt strikes a good balance between computational efficiency and model complexity, requiring only 442.7 GFLOPs of computational power and 71.2 M parameters. Furthermore, in semantic segmentation tasks that include a classification module, the SwinUNeCCt model also exhibits powerful recognition capabilities. Although this slightly increases computational overhead and model complexity, its performance surpasses other comparative models. The SwinUNeCCt model demonstrates excellent performance in semantic segmentation tasks, achieving the best results among state-of-the-art 3D medical models across multiple key metrics. It balances computational efficiency and model complexity well, maintaining high performance even with the inclusion of a classification module.

Delayed Pontomesencephalic and Cervical Cord Venous Drainage Followed by Contralateral Carotid-Cavernous Fistula after Craniofacial Fractures: A Case Report.

A 24-year-old male was admitted with progressive cervical hypesthesia, tetraparesis, dyspnea, and a history of craniofacial fracture. Spinal magnetic resonance imaging (MRI) showed brainstem edema extending to the thoracic spine with multiple prominent perimedullary vascular structures. Cerebral digital-substraction angiography revealed Barrow type A carotid-cavernous fistula. Total occlusion with preservation of internal carotid artery flow was achieved using 1 detachable balloon and 6 coils. Postoperatively, immediate respiratory recovery, gradual extremities strength improvement, and right abducens nerve palsy were found. One month follow-up cervical MRI showed good recovery of spinal cord edema and perimedullary veins.

Migration of cervical spine screws to the sacral canal: a case report

Cervical open door laminoplasty is widely used in multilevel decompression, which is a motion-sparing decompression treatment option for multilevel cervical myelopathy. Implant distance migration in cervical laminoplasty has not been reported. A 61-year-old woman underwent cervical laminoplasty, three months postoperatively, she experienced left shoulder pain and left upper limb pain, and underwent cervical magnetic resonance imaging, which showed no abnormalities. She gradually developed dizziness, headache, unstable walking, incomplete urinary incontinence, and fluctuating neck lumps. The X-ray showed that the screws of the C7 lateral mass had disappeared and migrated to the sacral canal. The patient underwent cerebrospinal leakage repair and removal of the screws in the spinal canal. Displacement of fixators implanted into the spinal canal after cervical laminoplasty is a rare complication that can cause permanent neurological injury.

Hyperreflexia in outpatients with Parkinson’s disease and coexisting cervical spinal stenosis: A retrospective cohort study

Background. Degenerative cervical myelopathy (DCM) is poorly recognized and infrequently diagnosed. Objectives. To identify symptoms and signs in the lower extremities physically and radiologically in outpatients with idiopathic Parkinson’s disease (PD) and coexisting DCM. Methods. In 2023, a retrospective cohort study was performed to review the medical records from 2016 to 2020 at the outpatient clinic of the Department of Internal Medicine. As a result, 8 women with PD were diagnosed based on the presence of cardinal features, asymmetry, and a good response to levodopa. Brain and cervical magnetic resonance imaging (MRI) was conducted in 4 patients (group A): 3 with hyperreflexia of the patellar tendon, and 1 with Babinski’s sign. Results. The motor subtype of the 8 patients aged 69 to 90 was a tremor-dominant type of PD. The Hoehn and Yahr (H&Y) stages were II (1) and III (3) in group A, and III (3) and IV (1) in those without hyperreflexia of the patellar tendon. Hyperreflexia and Babinski’s sign were predominant on the tremor-dominant side in group A. Radiologically, their anteroposterior diameters at the most stenotic level (C5-6) were 6.0, 7.1, 7.1, and 10.4 mm. They developed muscular rigidity and spasticity involving the lower extremities. The gait and balance performance were particularly affected compared with the upper extremity function. Conclusion. Hyperreflexia of the patellar tendon and imbalance of gait performance due to coexisting DCM were the important factors affecting gait in older women with tremor-dominant PD.

Proposed criteria for the O'Sullivan McLeod syndrome: Case series and literature review

AbstractWe aimed to summarize the clinical characteristics of the O'Sullivan McLeod syndrome and propose the diagnostic criteria of the syndrome. We reviewed our database to identify patients with the O'Sullivan McLeod syndrome. Online databases including PubMed, EMBASE, and OVID were also searched for relevant cases. We identified a total of 24 cases, including 3 cases from our database and 21 ones from online searching. A predominance of male was observed [17 (73.9%)] with median onset age of 31 (range: 15–56) years old. The median (range) disease duration was 9 (0.5–28) years at the time of the visit. All patients showed involvement of hands and ~1/3 patients reported weakness and atrophy of right/left forearm. The upper arm was scarcely affected (8.7%). Needle electromyography suggested chronic denervation in C7‐T1 among the majority of involved cases (over 78%). Cervical magnetic resonance imaging showed longitudinal T2‐hypertenssive signals among 5/14 (35.7%) patients, which confined to the anterior horn area. No patients showed responsiveness to immunotherapy. Ten patients remained clinical stable during follow‐up, nine ones manifested chronic progressive course. The O'Sullivan and McLeod syndrome, characterized by progressive weakness and atrophy in upper limbs, might be an incurable disorder of lower motor neuron. Onset in early adulthood, the plateau period of over 12 months and years of chronic progression in clinical manifestations might be supportive indicators for the diagnosis of the syndrome. The prognosis is relatively good with no effective treatment.

Utilizing multimodal radiomics technology from cervical MRI for diagnosis of cervical spinal cord injury and spinal cord concussion

The primary aim of this study is to assess the viability of employing multimodal radiomics techniques for distinguishing between cervical spinal cord injury and spinal cord concussion in cervical magnetic resonance imaging. This is a multicenter study involving 288 patients from a major medical center as the training group, and 75 patients from two other medical centers as the testing group. Data regarding the presence of spinal cord injury symptoms and their recovery status within 72 h were documented. These patients underwent sagittal T1-weighted and T2-weighted imaging using cervical magnetic resonance imaging. Radiomics techniques are used to help diagnose whether these patients have cervical spinal cord injury or spinal cord concussion. 1197 radiomics features were extracted for each modality of each patient. The accuracy of T1 modal in testing group is 0.773, AUC is 0.799. The accuracy of T2 modal in testing group is 0.707, AUC is 0.813. The accuracy of T1 + T2 modal in testing group is 0.800, AUC is 0.840. Our research indicates that multimodal radiomics techniques utilizing cervical magnetic resonance imaging can effectively diagnose the presence of cervical spinal cord injury or spinal cord concussion.

Assessment of image quality and diagnostic accuracy for cervical spondylosis using T2w-STIR sequence with a deep learning-based reconstruction approach.

To investigate potential of enhancing image quality, maintaining interobserver consensus, and elevating disease diagnostic efficacy through the implementation of deep learning-based reconstruction (DLR) processing in 3.0T cervical spine fast magnetic resonance imaging (MRI) images, compared with conventional images. The 3.0T cervical spine MRI images of 71 volunteers were categorized into two groups: sagittal T2-weighted short T1 inversion recovery without DLR (Sag T2w-STIR) and with DLR (Sag T2w-STIR-DLR). The assessment covered artifacts, perceptual signal-to-noise ratio, clearness of tissue interfaces, fat suppression, overall image quality, and the delineation of spinal cord, vertebrae, discs, dopamine, and joints. Spanning canal stenosis, neural foraminal stenosis, herniated discs, annular fissures, hypertrophy of the ligamentum flavum or vertebral facet joints, and intervertebral disc degeneration were evaluated by three impartial readers. Sag T2w-STIR-DLR images exhibited markedly superior performance across quality indicators (median = 4 or 5) compared to Sag T2w-STIR sequences (median = 3 or 4) (p < 0.001). No statistically significant differences were observed between the two sequences in terms of diagnosis and grading (p > 0.05). The interobserver agreement for Sag T2w-STIR-DLR images (0.604-0.931) was higher than the other (0.545-0.853), Sag T2w-STIR-DLR (0.747-1.000) demonstrated increased concordance between reader 1 and reader 3 in comparison to Sag T2w-STIR (0.508-1.000). Acquisition time diminished from 364 to 197s through the DLR scheme. Our investigation establishes that 3.0T fast MRI images subjected to DLR processing present heightened image quality, bolstered diagnostic performance, and reduced scanning durations for cervical spine MRI compared with conventional sequences.

Exploring the Relationship Between Subcutaneous Fat Index and Neck Pain in Patients with Spinal Cervical Spondylosis: A Retrospective Cohort Study

Retrospective Cohort Study. This study measures the subcutaneous fat index (SFI) of the cervical spine in patients with spinal cervical spondylosis using cervical magnetic resonance imaging and explores its relationship with neck pain in patients with spinal cervical spondylosis. In this single-center retrospective study, 298 patients hospitalized for spinal cervical spondylosis between January and June 2021 were initially considered. After applying inclusion and exclusion criteria, 93 patients were enrolled. The cervical magnetic resonance imaging data for these patients were analyzed using A-Site software. The SFI was measured at the median sagittal plane on T2-weighted images. Patients were categorized into 2 groups based on their admission complaints: those with cervical pain and those without it. Differences between these groups were then statistically analyzed. The mean SFIs with standard deviations for the neck and non-neck pain groups were 36.4%±7.7% and 27.0%±7.9%, respectively, with a significant difference (P < 0.0001). The SFI was consistently higher across all neck segments in the neck pain group compared to the nonneck pain group (P < 0.05). The 2 groups had no statistically significant difference in the body mass index. The SFI provides a more precise assessment of muscle and fat distribution in the posterior cervical region than body mass index and is generally higher in patients with spinal cervical spondylosis who experience neck pain. These findings suggest the importance of early functional exercises postsurgery for potentially improving surgical outcomes in this patient population.

Hirayama Disease: Neutral and Flexion Magnetic Resonance Imaging Manifestations and Single Tertiary Care Center Analysis on 3T Scanner.

Hirayama disease (HD) is a rare benign type of cervical cord myelopathy occurring commonly in young males as unilateral or bilateral asymmetrical amyotrophy of the hand and forearm muscles in C8-T1 distribution. Magnetic resonance imaging (MRI) is the best technique for the evaluation and imaging of this entity. This is a retrospective review of cervical magnetic resonance images of patients that were taken for clinically suspected and diagnosed HD on 3T MRI in postcontrast neutral and flexion (30°-40°) positions from July 2019 to January 2024 at Shri Ram Murti Smarak Institute of Medical Sciences, Bareilly. Fourteen patients included in the study were males less than 34 years of age. MRI findings of cord atrophy in the lower cervical region/cervico-dorsal junction, abnormal cervical curvature, loss of attachment of the dorsal dural sac and subjacent laminae with anterior displacement, and a prominent intense enhancing posterior epidural space were observed in all 14 patients. The minimum anteroposterior cord diameters in the neutral and flexion positions were 2.9 and 2.8 mm, respectively (mean thickness of laminodural space on flexion - 5.2 mm). Other MRI findings showed variable representations. Flexion-position MRI has emerged as the gold standard for establishing and validating the diagnosis of HD in clinically suspected cases and should be an essential part of the protocol for the screening of clinically suspected cases of HD to aid in early treatment and therapeutic intervention. Complimentary newer sequences such as the Three-dimensional (3D)-Constructive interference in Steady State (CISS)/Fast Imaging Employing Steady-state Acquisition Cycled Phases (FIESTA-C) may reinforce better appreciation of epidural flow voids.

Brain and cervical spinal cord MRI correlates of sensorimotor impairment in patients with multiple sclerosis.

Cervical spinal cord (cSC) lesions and atrophy contribute to disability in multiple sclerosis (MS), but associations with specific sensorimotor dysfunction require further exploration. To investigate the associations of brain and cSC magnetic resonance imaging (MRI) measures with sensorimotor impairment in MS. One hundred fifty-one MS patients and 69 healthy controls underwent 3T MRI and clinical assessments including Expanded Disability Status Scale (EDSS), 9-hole peg test (9-HPT), finger tapping test (FTT), timed 25-foot walk test (T25FWT), and vibration detection threshold (VDT). Random forest ranked brain (T2-hyperintense lesion volume (T2-LV) and normalized deep gray matter (GM), cortical and white matter (WM) volumes) and cSC (T2-LV and total, GM, and WM cross-sectional areas (CSAs) at C2/C3 level) MRI measures relevance in explaining EDSS milestones (EDSS ⩾3.0, ⩾4.0, and ⩾6.0), VDT, pyramidal and sensory functional systems (P-FS and S-FS ⩾2), and motor tests impairment. Various combinations of brain and cSC MRI measures explained EDSS milestones (area under the curve (AUC) =0.879-0.900), VDT (R2 = 0.194), and impaired P-FS (AUC = 0.820), S-FS (AUC = 0.795), 9-HPT (AUC = 0.793), FTT (AUC = 0.740), and T25FWT (AUC = 0.825). cSC GM CSA was the most informative feature for all outcomes, except 9-HPT. cSC MRI measures, especially GM CSA, explain EDSS and sensorimotor dysfunction better than brain measures in MS.

Longitudinally extensive transverse myelitis with trident sign and positive AQP4 antibody: a case report

BackgroundLongitudinally extensive transverse myelitis (LETM) is characterized by spinal cord lesions that affect at least three spinal cord segments. It can be associated with various inflammatory conditions. While imaging characteristics can aid in diagnosis, relying solely on them may lead to misinterpretation.Case presentationWe describe a 35-year-old woman who presented with subacute myelitis. Her cervical MRI (magnetic resonance imaging) revealed an extensive lesion from the area postrema down to the second thoracic level, with a trident sign observed in axial T1-weighted post-gadolinium imaging. The presence of a trident sign in MRI of patients with myelopathy is more commonly associated with sarcoidosis than other conditions. But our patient had positive (rechecked) AQP4 antibody and negative FDG-PET (fluorodeoxyglucose positron emission tomography) scan that shows trident sign could be seen in other inflammatory disorders such as NMO (neuromyelitis optica).ConclusionTrident sign is not pathognomonic for sarcoidosis, additional investigations are necessary to identify the diagnoses related to the trident sign.

Design of a novel deep network model for spinal cord injury prediction

Degenerative cervical myelopathy must be diagnosed with magnetic resonance imaging (MRI) which predicts spinal cord injury (SCI). The growing volume of medical imaging data can be managed by deep learning models, which provide a preliminary interpretation of images taken in basic care settings. Our main goal was to create a deep-learning approach that could identify SCI using MRI data. This work concentrates on modeling a novel 2D-convolutional neural networks (2D-CNN) approach for predicting SCI. For holdouts, training, and validation, various datasets of patients were created. Two experts assigned labels to the images. The holdout dataset was used to evaluate the performance of our deep convolutional neural network (DCNN) over the image data from the available dataset. The dataset is acquired from the online resource for training and validation purpose. With the available dataset, the anticipated model attains 94% AUC, 0.1 p-value, and 92.2% accuracy. The anticipated model might make cervical spine MRI scan interpretation more accurate and reliable.

Investigation of the Relationship Between Cervical Vertebral Column Degeneration and Posterior Circulation Perfusion Area Ischemia

Aim: The primary objective of this study was to establish whether degeneration of the cervical vertebrae and paravertebral structures serves as a predisposing factor for ischemic processes by disrupting hemodynamics in the posterior system through mechanical effects on the vertebral arteries. Material and Method: We conducted a retrospective analysis of 180 patients who underwent various imaging tests between January 2017 and October 2023. These tests included cervical magnetic resonance imaging (MRI), cervical computed tomography (CT), carotid-vertebral neck CT angiography (CTA), cranial CT, and cranial MRI. Of the 180 patients, 90 had mild degeneration or no significant degeneration, with a mean age of 58 years, and 90 had significant cervical spondylosis (CS) with a mean age of 64 years. The radiological findings were statistically analyzed, and a p-value of less than 0.05 was considered statistically significant. Results: There was no significant difference between age and parenchymal density in the control group (p=0.09). There was no statistically significant difference between the age and parenchymal density in the CS group (p=0.07). As CS became more severe, there was a statistically significant increase in the incidence of atrophic enlargement of the cerebellar folia and loss of density in the posterior fossa (p=0.03) and posterior circulation infarcts (POCI) (p=0.04). Conclusion: When severe, CS can adversely affect vascular hemodynamics in the posterior system, predisposing perfused neural parenchyma to ischemia.

Dynamic Cervical Spinal Canal Stenosis: Identifying Imaging Risk Factors in Extended Positions.

A retrospective study at a single academic institution. This study aimed to identify imaging risk factors for stenosis in extended neck positions undetectable in preoperative neutral magnetic resonance imaging (MRI) and improving decompression strategies for cervical spine disorders. Cervical disorders are influenced by various dynamic factors, with spinal stenosis appearing during neck extension. Despite the diagnostic value of dynamic cervical MRI, standard practice often uses neutral-position MRI, potentially influencing surgical outcomes. This study analyzed 143 patients who underwent decompression surgery between 2012 and 2014, who had symptomatic cervical disorders and MRI evidence of spinal cord or nerve compression but had no history of cervical spine surgery. Patient demographics, disease type, Japanese Orthopedic Association score, and follow-up periods were recorded. Spinal surgeons conducted radiological evaluations to determine stenosis levels using computed tomography myelography or MRI in neutral and extended positions. Measurements such as dural tube and spinal cord diameters, cervical alignment, range of motion, and various angles and distances were also analyzed. The residual space available for the spinal cord (SAC) was also calculated. During extension, new stenosis frequently appeared caudal to the stenosis site in a neutral position, particularly at C5/C6 and C6/C7. A low SAC was identified as a significant risk factor for the development of new stenosis in both the upper and lower adjacent disc levels. Each 1-mm decrease in SAC resulted in an 8.9- and 2.7-fold increased risk of new stenosis development in the upper and lower adjacent disc levels, respectively. A practical SAC cutoff of 1.0 mm was established as the threshold for new stenosis development. The study identified SAC narrowing as the primary risk factor for new stenosis, with a clinically relevant cutoff of 1 mm. This study highlights the importance of local factors in stenosis development, advocating for further research to improve outcomes in patient with cervical spine disorders.

Association Between Severity of Cervical Central Spinal Stenosis and Paraspinal Muscle Parameters in Patients Undergoing Anterior Cervical Discectomy and Fusion.

Retrospective study. The aim of this study was to evaluate the association between severity and level of cervical central stenosis (CCS) and the fat infiltration (FI) of the cervical multifidus/rotatores (MR) at each subaxial levels. The relationship between cervical musculature morphology and the severity of CCS is poorly understood. Patients with preoperative cervical magnetic resonance imaging (MRI) who underwent anterior cervical discectomy and fusion (ACDF) were reviewed. The cervical MR were segmented from C3 to C7 and the percent FI was measured using a custom-written Matlab software. The severity of the CCS at each subaxial level was assessed using a previously published classification. Grade 3, representing a loss of cerebrospinal fluid space and deformation of the spinal cord > 25%, was set as the reference and compared to the other gradings. Multivariable linear regression analyses were conducted and adjusted for age, sex, and body mass index. 156 consecutive patients were recruited. A spinal cord compression at a certain level was significantly associated with a greater FI of the MR below that level. After adjustment for the above-mentioned confounders, our results showed that spinal cord compression at C3/4 and C4/5 was significantly associated with greater FI of the MR from C3 to C6 and C5 to C7, respectively. A spinal cord compression at C5/6 or C6/7 was significantly associated with greater FI of the MR at C7. Our results demonstrated significant correlations between the severity of CCS and a greater FI of the MR. Moreover, significant level-specific correlations were found. A significant increase in FI of the MR at the levels below the stenosis was observed in patients presenting with spinal cord compression. Given the segmental innervation of the MR, the increased FI might be attributed to neurogenic atrophy. 3.

Vertebral Artery Injury in Cervical Spine Fracture Dislocation: An Observational Study in a Tertiary Care Center.

The incidence of traumatic vertebral artery injury (VAI) associated with cervical spine trauma varies widely in published trauma series. The primary aim of this study was to determine the incidence of traumatic VAIin patients who suffered cervical spine injuries by means of routine magnetic resonance imaging, and the secondary objective was to identify any associations with injury mechanism, level ofinjury, and neurologic injury severity. Materials and methods: A retrospective review was conducted on 96 patients who suffered cervical spine fracture dislocation with or without an associated spinal cord injury (SCI) in Indian Spinal Injuries Center (ISIC), New Delhi, Indiafrom January 2013 to April 2023. Cervical magnetic resonance imaging (MRI) was used to diagnose VAI. Patient's age, sex, cervical injury level, mechanism of injury, neurologic level of injury, association with foraminal fracture, facet dislocation,and clinical sequelae of vertebral artery injury were analyzed. In this study, of 96 patients who met the inclusion criteria, 18 patients (18.75%) had VAI on the MRI study. Thirteen (72.22%) of the eighteen patients had right-sided injuries, four (22.22%) had left-sided injuries, and one (5.55%) had bilateral injuries. There was an associated SCI in every VAI patient. VAI was significantly more common in patients who had ASIA A (61%, n = 11) and ASIA B (22%, n = 4)injuries, and no VAI was noted in neurologically intact patients (p<0.001). The incidence of VAI was higher in the flexion distraction type of injury (n = 12, 66%).The most commonly involved cervical spine injury level was C5-C6 (27%, n = 5), followed by 22% (n = 4) at C4-C5 and C6-C7 levels. About 27.8% (n = 5) of VAI was associated with foraminal fractures, and 72% (n = 13) of VAI was associated with facet dislocations, of which 44% (n = 8) were bifacetal and 28% (n = 5) were unifacetal dislocations. On clinical symptoms, only one (5.56%) patient had a headache, and 17 (94.4%) had no clinical features due to VAI. The incidence of traumatic vertebral artery disease is not very uncommon and requires careful and meticulous screening and management. Otherwise, complications like pseudoaneurysm, neurologic deficit, late-onset hemorrhage, infarction, and death can happen. Mostly, it is associated with high-velocity injuries and neurological injuries. MRI can be used as a good screening tool, which can be aided by a CT angiogram or digital subtraction angiographyfor confirmation. Proper pre-operative evaluation of vascular injury in cervical spine fracture dislocation is very important for patient counseling, patient management, and surgical planning.

Advanced MRI metrics improve the prediction of baseline disease severity for individuals with degenerative cervical myelopathy

BACKGROUND CONTEXTDegenerative cervical myelopathy (DCM) is the most common form of atraumatic spinal cord injury globally. Degeneration of spinal discs, bony osteophyte growth and ligament pathology results in physical compression of the spinal cord contributing to damage of white matter tracts and grey matter cellular populations. This results in an insidious neurological and functional decline in patients which can lead to paralysis. Magnetic resonance imaging (MRI) confirms the diagnosis of DCM and is a prerequisite to surgical intervention, the only known treatment for this disorder. Unfortunately, there is a weak correlation between features of current commonly acquired MRI scans (“community MRI, cMRI”) and the degree of disability experienced by a patient. PURPOSEThis study examines the predictive ability of current MRI sequences relative to “advanced MRI” (aMRI) metrics designed to detect evidence of spinal cord injury secondary to degenerative myelopathy. We hypothesize that the utilization of higher fidelity aMRI scans will increase the effectiveness of machine learning models predicting DCM severity and may ultimately lead to a more efficient protocol for identifying patients in need of surgical intervention. STUDY DESIGN/SETTINGSingle institution analysis of imaging registry of patients with DCM. PATIENT SAMPLEA total of 296 patients in the cMRI group and 228 patients in the aMRI group. OUTCOME MEASURESPhysiologic measures: accuracy of machine learning algorithms to detect severity of DCM assessed clinically based on the modified Japanese Orthopedic Association (mJOA) scale. METHODSPatients enrolled in the Canadian Spine Outcomes Research Network registry with DCM were screened and 296 cervical spine MRIs acquired in cMRI were compared with 228 aMRI acquisitions. aMRI acquisitions consisted of diffusion tensor imaging, magnetization transfer, T2-weighted, and T2*-weighted images. The cMRI group consisted of only T2-weighted MRI scans. Various machine learning models were applied to both MRI groups to assess accuracy of prediction of baseline disease severity assessed clinically using the mJOA scale for cervical myelopathy. RESULTSThrough the utilization of Random Forest Classifiers, disease severity was predicted with 41.8% accuracy in cMRI scans and 73.3% in the aMRI scans. Across different predictive model variations tested, the aMRI scans consistently produced higher prediction accuracies compared to the cMRI counterparts. CONCLUSIONSaMRI metrics perform better in machine learning models at predicting disease severity of patients with DCM. Continued work is needed to refine these models and address DCM severity class imbalance concerns, ultimately improving model confidence for clinical implementation.

Important Morphometric Values and Anatomical Ratios Obtained from Cervical Magnetic Resonance Imaging Images and their Differences from the Literature in Terms of Evaluation of Myelopathy

Objective: A Torg ratio of 0.80 or less is considered positive support for the diagnosis of cervical spinal canal stenosis. In our study, it was aimed to determine the morphometric values of the spinal cord, spinal canal, and vertebral body, to calculate the subarachnoid distance, and to examine the differences in Torg ratio according to cervical vertebra levels and between genders in young adult individuals belonging to our community. Materials and Methods: The study was performed on magnetic resonance imaging (MRI) images (28–35 years, 50 men and 50 women, retrospectively). Results: The Torg ratio was found to be &lt;0.80 in 194 of 350 measurements made at 7 levels (55.4%) in men and in 83 of 350 measurements in women (23.7%). The Torg ratio value was found to be higher in women than men at C3–T1 levels (P &lt; 0.01). There is a positive and highly significant relationship between the Torg ratio and “canal-cord distance” (P &lt; 0.01). Spinal canal diameter was found to be &lt;14 mm in 235 vertebrae (67.1%) in men and 282 vertebrae (80.6%) in women. In addition, it was found below 12 mm in 12.6% of men and 16% of women. Conclusion: In our study, the Torg ratio was found below 0.80 in a significant part of our cases. Therefore, it would be appropriate to revise the Torg ratio separately for different populations in MRI measurements. It is clear that there is a need for planning epidemiological studies consisting of control–patient groups in the future, especially for many societies.

The significance of cervical discopathy diagnosis in patients with mastalgia.

The primary aim of this study was to explore the involvement of cervical discopathy in the development of non-cyclic mastalgia by employing cervical magnetic resonance imaging (MRI). A total of 407 patients were included in the study. Individualized management plans were developed for each patient. Pathological findings in MRI results were assessed by specialists in physical therapy and neurosurgery, and appropriate treatment was administered. Visual assessments of patients were conducted. The Analog Scale (VAS) scoring system was used at the initial presentation, and patients were evaluated at 1 and 3 months following the treatment. In the MRI examinations of the patients included in the study, simultaneous cervical disc protrusion was observed in 29% (n: 124) of those with annular bulging. Comparing the VAS scores of patients before treatment, at the 1st and at the 3rd month showed a significant decrease in mastalgia pain (p < 0.001). The diagnosis of cervical discopathy holds significant importance in the treatment of mastalgia patients. Therefore, clinicians should keep the cervical spine in mind as a potential contributing factor to mastalgia.

Incidental findings of cervical magnetic resonance imaging: A retrospective reinterpretation of a large adult population.

Magnetic resonance imaging (MRI) of the cervical spine is one of the routine MRI scans of the cervical region in investigating spinal disc pathologies, spinal stenosis, and the detection of spinal lesions, which are the major parameters to be evaluated in this examination. The authors of this study are focused on a different aspect of cervical MRI, revealing the incidences and reporting rates of extraspinal incidental findings. A total of 1000 patients (324 males, 676 females, mean age 47 ± 14) who had undergone an MRI of the cervical spine were enrolled in this study. The magnetic resonance (MR) images of these patients were re-interpreted with respect to the incidental extraspinal imaging findings. The incidence and reporting rate of each incidental finding encountered during the evaluation were presented in percentages. 726 patients in this study had at least one incidental lesion. The results of this study revealed that the most common incidental lesions encountered during the reinterpretation of cervical MRI were nasopharyngeal mucosal thickening (n = 442) and thyroid hypertrophy (n = 231). The total reporting rate of incidental findings was 5.29%. There are many data to be reported and evaluated by MR imaging of the cervical spine, not only the main parameters of MRI scanning in the routine daily practice of radiologists. All our colleagues should be aware and careful of these incidental findings, which may be the initial medical data of the patients' diagnoses, or to avoid undesirable medicolegal problems.