Background 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. Methods 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. Results 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. Conclusion 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.

T2DM is associated with neurodegenerative changes that can be detected through advanced magnetic resonance imaging. Brain atrophy in T2DM is linked to cognitive decline, yet the extent and pattern of structural brain changes remain underexplored. This study aims to assess volumetric differences in brain structures between diabetic and non-diabetic individuals using voxel-based morphometry (VBM). A prospective observational study was conducted with 86 participants (43 T2DM case and 43 healthy controls) who underwent high-resolution 3D MRI scans using 3D SPGR and T1-weighted Fast Spin Echo sequences. Image preprocessing and volumetric analysis were performed using Statistical Parametric Mapping (SPM-12) and the Computational Anatomy Toolbox (CAT-12). Brain volumes were analyzed for 24 regions. Statistical analyses were conducted using independent t-tests and linear regression, with p < 0.05 considered significant. T2DM subjects exhibited significant gray matter (GM) volume reductions compared to controls, particularly in the hippocampus and middle frontal gyrus, as detected in both 3DSPGR and T1 FSE sequences. However, regional differences emerged between imaging modalities: while T1 FSE imaging revealed significant bilateral hippocampal atrophy, 3DSPGR data showed no such difference. Notably, both sequences demonstrated significantly increased volumes in the anterior and posterior temporal lobes in T2DM participants, suggesting possible region-specific hypertrophy. T2DM is associated with significant brain atrophy, particularly in brain regions associated with cognition. Based on these findings, MRI-based volumetric analysis has the potential to detect and monitor T2DM-related neurodegeneration early, emphasizing the need for routine neuroimaging in diabetic populations. Research on longitudinal assessments will be necessary in the future to gain a deeper understanding of the progression of brain atrophy in diabetics.

Hepatocellular carcinoma (HCC) is among the leading causes of cancer-related deaths worldwide. The clinical utility of artificial intelligence (AI) and radiomics models based on contrast-enhanced computed tomography (CECT) for HCC detection remains underexplored. This systematic review and meta-analysis evaluated the diagnostic performance of machine learning and radiomics-based models. A comprehensive literature search (2015-2025) across four major databases identified 29 eligible studies according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The risk of bias was assessed using the QUADAS-2 tool. Of these, 17 studies provided independent performance metrics and were included in the meta-analysis. Pooled estimates of sensitivity, specificity, accuracy, and the F1 score were calculated using a random effects model. Models evaluated on independent test datasets, the pooled sensitivity and specificity were 0.562 and 0.570, respectively. A subgroup of radiomics-specific models (n=3) demonstrated comparatively higher sensitivity (0.660) and specificity (0.670), with minimal heterogeneity in sensitivity (I² = 0%, τ² ≈ 0), suggesting strong internal consistency. However, due to the limited number of studies, these results should be interpreted with caution. Combined models showed lower sensitivity (0.368) and specificity (0.297), with high heterogeneity (I² = 98.3%), likely due to the absence of independent test sets, which may have led to limited generalisability. Radiomics-based models evaluated on independent datasets exhibit more consistent diagnostic accuracy for HCC detection using CECT. However, methodological variability underscores the need for standardised reporting, robust external validation, and incorporation of explainable AI techniques to enhance clinical adoption.

Introduction Magnetic resonance imaging (MRI) is essential for brain imaging, but conventional methods rely on qualitative contrast, are time-intensive, and prone to variability. Magnetic resonance finger printing (MRF) addresses these limitations by enabling fast, simultaneous mapping of multiple tissue properties like T1, T2. Using dynamic acquisition parameters and a precomputed signal dictionary, MRF provides robust, qualitative maps, improving diagnostic precision and expanding clinical and research applications in brain imaging. Methods Database searches were performed through PubMed, Embase, Scopus, Web of science to identify relevant articles focusing on the application of MR finger printing in the adult brain. We utilized the preferred reporting items for systematic reviews and meta-analysis guidelines to extract data from the selected studies. Results Nine articles were included in the final review, with a total sample size of 332 participants. In healthy brains, notable regional, sex, age, and hemispheric variations were identified, particularly in the corpus callosum and thalamus. MRF effectively differentiated meningioma subtypes, glioma grades, and IDH mutation status, with T2 values providing particularly predictive for glioma classification. In brain metastases, significant relaxometry differences were noted between normal and lesional tissues. For multiple sclerosis, MRF values correlated with clinical and disability measures, distinguishing relapsing-remitting secondary progressive forms. In traumatic brain injury, longitudinal T1 changes strongly correlated with clinical recovery, surpassing T2 values. Conclusions The systematic review highlighted MRD as a groundbreaking technique that enhances neurological diagnosis by simultaneously quantifying T1 and T2 relaxation times. With reduced acquisition times, MRF outperforms conventional MRI in detecting subtle pathologies, distinguishing properties, and providing reliable biomarkers.

Background 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. Methods 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. Results 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. Conclusion 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.