International Clinical Neuroscience Journal

Background: Cervical spondylotic myelopathy (CSM) stems from either chronic degenerative changes or traumatic mechanisms. Distinguishing between these etiologies is crucial, yet identifying which patients benefit most from surgery remains challenging. This study aims to evaluate how trauma history, spinal alignment, and patient profiling influence clinical outcomes.

Methods: A retrospective cohort study was conducted on 153 patients treated at the “Ospedale dell’Angelo” (Venice, Italy). Patients were assessed using the modified Japanese Orthopedic Association (mJOA) score. Variables included trauma history, spinal alignment (Cervical Lordosis, SVA, T1 Slope), and ASA score. Statistical analysis employed linear regression and K-means cluster analysis to identify homogeneous patient profiles.

Results: Patients with a history of mild trauma showed a trend toward greater improvement compared to non-traumatic cases (mJOA improvement: +1.61 vs +0.33, p=0.074). Surprisingly, patients with straight spinal alignment achieved higher recovery (+1.29 points) than those in the kyphotic (-0.08) or lordotic (+0.15) groups. Cluster analysis identified a specific subgroup of non-surgical trauma patients who achieved remarkable recovery (+5.00 points) without intervention.

Conclusion: Trauma history acts as a potential catalyst for neurological recovery. While surgery remains the standard for unstable cases, our data suggest that a neutral (straight) alignment is associated with favorable outcomes, and that a subset of trauma patients can recover significantly with conservative management.

Background: Glioblastoma is the most common malignant primary brain tumor in adults. It has been classified into mutant and wild-type subtypes of isocitrate dehydrogenase (IDH). Patient therapeutic options in Glioblastoma vary across subtypes. Therefore, preoperative classification of IDH mutation status is important for therapeutic decision-making. This study aimed to develop and evaluate a metric-meta learning approach based on a Siamese Neural Network model for noninvasive classification of IDH mutation status in patients from magnetic resonance imaging (MRI) scans, based on their similarity.

Methods: MRI scans from 93 patients (2018-2024) with glioblastoma tumors were collected and subdivided into IDH-mutant and IDH-wildtype scans. After preprocessing MRI scans, a Siamese Convolutional Neural Network was combined with two pre-trained models, InceptionResNetV2 and ResNet152V2, as an embedding function to differentiate between classes using a small dataset. The network extracts relevant features to classify patients' IDH-mutation status. We propose a self-attention mechanism combined with a Siamese neural network to improve model accuracy.

Results: We evaluate a Siamese Neural Network on MRI scans of brain tumors. After adding an attention mechanism to the Siamese Neural network, we obtain classification accuracy (73.33% - 70%), precision (68.42% - 68%), recall (86%- 73.33%), and F1-score (76.20%- 70.96%) on our dataset.

Conclusion: Our proposed model demonstrated promising results after combined with an attention mechanism to perform classification of IDH-mutation status using a limited number of brain tumor images and accuracy of this model has improved.

Background: Accurate and timely segmentation of brain tumors in MRI images is essential for optimal treatment planning. While convolutional neural networks (CNNs) have achieved extensive success in medical image segmentation, they have limited ability to capture long-range spatial dependencies and often require high computational resources to achieve reasonable accuracy. Vision Transformers (ViTs), which utilize global self-attention, offer a promising alternative but are computationally expensive for high-resolution 3D medical images. In this study, we propose SegViTBT, a lightweight hybrid architecture combining a vision transformer encoder with a convolutional decoder for efficient brain tumor segmentation. The model integrates sparse attention to reduce computational load and learnable 2D positional embeddings to enhance spatial representation, delivering high accuracy with reduced resource demands.

Methods: The model is trained on MRI images from the BraTS benchmark dataset. Key performance metrics, including dice coefficient, accuracy, and loss, are evaluated over 25 epochs during training and validation. A comparison is made against conventional CNN and ViT models.

Results: The proposed SegViTBT model demonstrates a stable learning curve with rapid convergence. It achieves a dice score of 78.06% on the BraTS dataset, outperforming baseline CNNs and standard ViT implementations while using less than 60% of the computational resources. Visual results confirm the model’s ability to delineate tumor boundaries with high precision, even for irregularly shaped lesions.

Conclusion: SegViTBT successfully closes the performance gap between CNNs and ViTs in medical imaging by introducing a computationally efficient, pixel-accurate architecture. The model is suitable for deployment in low-resource clinical settings, enabling real-time, practical diagnostic support for brain tumor assessment.

FOXG1 syndrome is a rare neurodevelopmental disorder caused by mutations in the FOXG1 gene, leading to severe developmental delay, microcephaly, movement disorders, epilepsy, and autistic features. Though it shares some phenotypic similarities with Rett syndrome, it has a distinct genetic etiology and clinical course. We report a 1-year-old 3-month-old boy, the second-born child of a non-consanguineous couple, who presented with recurrent seizures from 4 months of age, characterized by infantile spasms. The child exhibited global developmental delay, poor social interaction, irritability, and sleep disturbances. Clinical examination revealed microcephaly, hypotonia, exaggerated deep tendon reflexes, and extensor plantar responses. Neuroimaging showed benign enlargement of the subarachnoid space, and genetic testing confirmed a pathogenic FOXG1 mutation. Despite multiple anti-seizure medications, the child’s epilepsy remained refractory. He is currently being managed on a ketogenic diet, anti-epileptic medication, and intensive multidisciplinary therapy sessions. This case highlights the diagnostic challenges of FOXG1 syndrome and its overlapping but distinct features from Rett syndrome. The patient’s refractory epilepsy, severe developmental delay, and poor response to conventional therapies align with existing literature. Neuroimaging findings in these patients are varied. This syndrome has a poor prognosis, with no definitive treatment available at present. FOXG1 syndrome is a distinct entity requiring early diagnosis and multidisciplinary management. Further research into gene-targeted therapies is crucial for improving outcomes.

Wilson’s disease is an autosomal recessive disorder that disrupts copper metabolism, leading to serious consequences in the liver and brain, including cirrhosis and the characteristic Kayser-Fleischer (KF) ring in the cornea. Our study focuses on children who presented with neurological symptoms, with or without hepatic involvement. While there have been a few reports from northern India, data on pediatric cases in southern India are sparse, highlighting the need for more comprehensive research in this region. In this series, we report on nine adolescent children diagnosed with neurological manifestations of Wilson’s disease who presented to a tertiary care center. We collected relevant clinical histories, along with details from physical and neurological examinations, from the medical record system. This comprehensive data collection aimed to provide a clearer understanding of the clinical presentation and progression of neurological Wilson's disease in our patient cohort. Wilson’s disease should be considered as one of the initial differential diagnoses even when there is only one neurological manifestation and without hepatic involvement in adolescents as well.