MRI Scans Research Articles

ObjectiveEarly speech experiences are presumed to contribute to the development of brain structures involved in processing speech. Previous research has been limited to correlational studies. Here, we conducted a randomized trial with neonates born preterm to determine whether increased exposure to maternal speech during NICU hospitalization is causally linked to structural white matter maturation.Study designWe enrolled 46 neonates born preterm (24–31 weeks gestational age). Participants were randomly assigned to receive increased (T: n = 21) or routine (C: n = 25) exposure to mother’s speech. The T-group heard 10-min audio recordings of their mothers reading a children’s story two times/hour between 10pm and 6am, increasing speech exposure by 2.67 h/day. The C-group did not hear recorded speech. At near-term-equivalent age, we obtained two high-angular resolution diffusion MRI (scan 1: b = 700, scan 2: b = 1500) and T1 relaxometry scans. We assessed mean diffusivity (MD), pre-registered primary outcome (NCT02847689), of the left and right arcuate fasciculus, tracts implicated in language processing. Secondary outcomes included fractional anisotropy (FA) and R1 (1/T1). We hypothesized that neonates randomized to the T-group would show evidence for increased maturation within the arcuate, indexed as decreased MD and increased FA and R1, compared to neonates in the C-group.ResultsGroups were equivalent on medical and demographic variables. Linear mixed models demonstrated that compared to the C-group, the T-group demonstrated significantly lower MD in the left (scan 1: β = −0.11, Marginal R2 = 0.27; scan 2: β = −0.12, Marginal R2 = 0.33) but not right arcuate (scan 1: β = −0.06, Marginal R2 = 0.09; scan 2: β = −0.03, Marginal R2 = 0.01). The T-group also demonstrated significantly higher FA (scan 1 β = 0.02, Marginal R2 = 0.20; scan 2: β = 0.03, Marginal R2 = 0.31) and R1 (β = 0.02, Marginal R2 = 0.39) in the left but not right arcuate.ConclusionPreterm neonates with increased maternal speech exposure showed more mature left arcuate microstructure, supporting a causal role of exposure to speech in brain development. Enhancing speech exposure in the NICU may benefit preterm children’s language outcomes.

Polychromatic excitation for 1H SABRE polarization transfer in weakly coupled systems at high field.

This study aimed to develop and evaluate a Transformer-CNN framework for automated segmentation of multiple sclerosis (MS) lesions on FLAIR MRI. The model was benchmarked against U-Net and DeepLabV3 and assessed for both segmentation accuracy and across-center performance under internal 5-fold cross-validation to ensure robustness across diverse clinical datasets. A dataset of 1,800 3D FLAIR MRI scans from five clinical centers was split using 5-fold cross-validation. Preprocessing included isotropic resampling, intensity normalization, and bias field correction. The Transformer-CNN combined CNN-based local feature extraction with Transformer-based global context modeling. Data augmentation strategies, including geometric transformations and noise injection, enhanced generalization. Performance was evaluated using Dice score, IoU, HD95, and pixel accuracy, along with internal cross-validation-based metrics such as Generalized Dice Similarity Coefficient (GDSC), Domain-wise IoU (DwIoU), Cross-Fold Dice Deviation (CFDD), and Volume Agreement (Intraclass Correlation Coefficient, ICC). Statistical significance was tested using Kruskal-Wallis and Dunn's post-hoc analyses to compare models. The Transformer-CNN achieved the best overall performance, with a Dice score of 92.3%, IoU of 91.4%, HD95 of 2.25mm, and pixel accuracy of 95.6%. It also excelled in internal cross-validation-based across-center metrics, achieving the highest GDSC (91.3%) and DwIoU (89.2%), the lowest CFDD (1.05%), and the highest ICC (96.5%). DeepLabV3 and U-Net scored 85.1% and 83.0% in Dice, with HD95 values of 4.15mm and 4.30mm, respectively. The worst performance was observed in U-Net, which exhibited high variability across datasets and struggled with small lesion detection. The Transformer-CNN outperformed U-Net and DeepLabV3 in segmentation accuracy and across-center performance under internal 5-fold cross-validation. Its robustness, minimal variability, and ability to generalize across diverse datasets establish it as a practical and reliable tool for clinical MS lesion segmentation and monitoring.

Patellar Lateral Facet Allograft as a Potential Graft Source in Glenoid Bone Reconstructions for Anterior Shoulder Instability: An MRI-Based Morphometric Analysis.

To evaluate the effectiveness of subcutaneous glucagon in reducing motion artifact during prostate MRI through intraindividual comparison. At our institution patients undergoing a clinical prostate MRI exam receive 1mg of subcutaneous glucagon before scanning. From February 15, 2024 to February 11, 2025 33 such patients were recruited to undergo an additional, research exam without glucagon. All exams were acquired at 3T. An axial T2-weighted spin-echo series (T2-WI) was acquired within both exams. Evaluation of the T2-WI series was done by three experienced radiologists using the criteria of diagnostic quality (0-3 scale), PI-QUALv2 (0-3 sum), motion artifact (significant, visible, none), and reviewer preference (five-point relative scale). Due to differences in prescribed coverage, the scan times for the two T2-WI sequences were in general different for each subject. Results were stratified using the acquisition time ratio (Trel) between the glucagon vs. non-glucagon scans. Wilcoxon tests assessed score differences. Across all 33 subjects, no significant differences were found between glucagon and non-glucagon scans. However, the observed negative correlation between glucagon preference and Trel (p = 0.026) led to stratification into low-Trel (N = 16) and high-Trel (N = 17) groups. In the low-Trel group the glucagon scans provided significantly improved diagnostic quality (p = 0.048), PI-QUALv2 sum (p = 0.049), motion scores (p = 0.047), and reader preference (p = 0.042). Subcutaneous glucagon provides improved image quality in prostate T2-WI MRI when scan duration remains within 1.25× of that of a non-glucagon T2-WI series. The benefit appears to decrease with longer scan times.

Abstract Background The auditory cortex plays a vital role in hearing acuity processing. This study aimed to evaluate the relationship between hearing acuity and the morphometry of the auditory cortex to investigate whether declines in hearing acuity correlate with changes in auditory cortex morphology. Methods Twenty-six healthy individuals participated in this study, which used a Siemens 3T Trio MRI scanner with a standard eight-channel head coil. Surface-based morphometry (SBM) was employed to evaluate the neurite architecture in the auditory cortex, encompassing cortical thickness, gyrification, sulcal depth, fractal dimension, and cortical volume. Results The findings showed a significant difference in auditory cortical thickness in the left hemisphere between males (2.41 ± 0.28 mm) and females (2.64 ± 0.27 mm). A significant positive correlation was observed between the fractal dimension of the left auditory cortex and HADS scores (r = 0.42). Significant negative correlations were also found between participants' ages and auditory cortical thickness in both the left (r = − 0.58) and right (r = − 0.71) hemispheres, as well as between the sulcal depth of the right auditory cortex and HADS (r = − 0.46), and between the cortical thickness of the right auditory cortex and hearing loss threshold (HLT) (r = − 0.42). Effect size analysis for hemispheric differences indicated a rightward lateralization of auditory cortex thickness (0.03 ± 0.08), gyrification (0.04 ± 0.13), fractal dimension (0.05 ± 0.08), and volume (0.16 ± 0.12), while non-directional asymmetry was observed in sulcal depth (0 ± 0.02). Conclusion A key finding of this research is that the cortical thickness of the auditory cortex was more significantly affected than other markers.

Background: Despite effective antiretroviral therapy, HIV-associated neurocognitive disorders (HANDs) remain prevalent, highlighting the need for sensitive biomarkers of early brain alterations. Trace-weighted diffusion spectroscopic imaging offers a non-invasive means to assess microstructural changes in brain metabolites in a single shot by measuring apparent diffusion coefficients (ADCs) of total N-acetylaspartate (tNAA), total creatine (tCr), total choline (tCho), and water. Methods: In this study, we used trace-weighted single-shot diffusion-weighted radial echo-planar spectroscopic imaging (DW-RESPI) to investigate metabolite diffusion and relative concentrations in the brains of people living with HIV (PLWH). Using a 3T MRI scanner, we studied 16 PLWH and 15 healthy controls (HCs), and we collected two sets of data with low and high b-values from which metabolite ADCs were computed. Metabolite ratios were derived from the low b-value spectra. A brief neuropsychological assessment evaluated attention, executive function, and memory in a subset of subjects. Cognitive and affective performance was quantified using domain-specific deficit scores, as well as depression and anxiety assessments, offering a comprehensive evaluation of neurobehavioral function. In the male subgroup (N = 15) of PLWH, we calculated the correlations between ADC values and neuropsychological domain scores. Results: tNAA, tCr, tCho, and water ADC values were significantly elevated in multiple gray and white matter regions in PLWH compared to HC, with the most pronounced differences observed in the superior precuneus, anterior cingulate cortex, and corona radiata. Notably, regional ADC values and metabolite ratios showed significant correlations with neuropsychological domain scores. Conclusions: These findings indicate the potential of metabolite and water diffusion metrics as biomarkers for HIV-associated microstructural brain alterations and cognitive impairment. However, the small sample size and preliminary nature of this data warrant further investigation to validate these findings.

Accurate segmentation of multiple sclerosis (MS) lesions from 3D MRI scans is essential for diagnosis, disease monitoring, and treatment planning. However, this task remains challenging due to the sparsity, heterogeneity, and subtle appearance of lesions, as well as the difficulty in obtaining high-quality annotations. In this study, we propose Efficient-Net3D-UNet, a deep learning framework that combines compound-scaled MBConv3D blocks with a lesion-aware patch sampling strategy to improve volumetric segmentation performance across multi-modal MRI sequences (FLAIR, T1, and T2). The model was evaluated against a conventional 3D U-Net baseline using standard metrics including Dice similarity coefficient, precision, recall, accuracy, and specificity. On a held-out test set, EfficientNet3D-UNet achieved a Dice score of 48.39%, precision of 49.76%, and recall of 55.41%, outperforming the baseline 3D U-Net, which obtained a Dice score of 31.28%, precision of 32.48%, and recall of 43.04%. Both models reached an overall accuracy of 99.14%. Notably, EfficientNet3D-UNet also demonstrated faster convergence and reduced overfitting during training. These results highlight the potential of EfficientNet3D-UNet as a robust and computationally efficient solution for automated MS lesion segmentation, offering promising applicability in real-world clinical settings.

The accurate and timely identification of brain tumors is crucial for effective diagnosis and treatment planning; however, the manual interpretation of MRI scans continues to be difficult and susceptible to errors. Although convolutional neural networks (CNNs) have made strides in automated classification, their dependence on local feature processing can restrict overall effectiveness. As an initial exploration, this pilot study introduces a Vision Transformer (ViT) model that utilizes self-attention mechanisms to capture both long-range global contexts and detailed local dependencies within image data, facilitating a more thorough feature representation that is vital for detecting subtle pathological patterns. Trained and assessed on a pilot dataset comprising 3,000 MRI images with significant augmentation, the proposed ViT model attained a promising preliminary accuracy of 99.73%, surpassing established CNN-based architectures such as ResNet-50, VGG-16, and EfficientNet-B0 across all evaluation metrics within the constraints of this binary classification task. These feasibility results not only highlight the potential of ViTs for brain tumor classification but also effectively validate the fundamental data processing and model fine-tuning pipeline. The study points out critical limitations, including dataset scale and model explainability, which directly influence the design of a forthcoming large-scale, multi-institutional research initiative. This pilot research lays a foundational framework for the integration of transformer-based models into medical imaging workflows to enhance diagnostic accuracy.

Hypertension is characterised by both enlarged perivascular spaces (ePVS) and chronically elevated resting sympathetic outflow. ePVS is associated with heart rate variability, suggesting links to autonomic outflow; however, heart rate variability offers limited information on sympathetic nerve activity. Here, we assessed whether ePVS are associated with muscle sympathetic nerve activity (MSNA) in 25hypertensive patients and 50healthy normotensive adults. T1-weighted MRI anatomical brain images were analysed for ePVS using a deep learning-based segmentation algorithm (nnU-Net). Spontaneous bursts of MSNA were recorded from the right common peroneal nerve via a tungsten microelectrode immediately before the MRI scan in a supine position. A backward regression analysis was conducted to test the relationship between ePVS and MSNA. Significant associations were found between MSNA and ePVS in the white matter (β=1.02, p=0.007), basal ganglia (β=0.43, p=0.001), and hippocampus (β=0.24, p=0.010) in healthy normotensive adults. Similar associations were observed in individuals with hypertension. Notably, the association between MSNA and midbrain ePVS cluster was only observed in the hypertensive group (β=0.41, p=0.005). ePVS were associated with MSNA in both normotensive and hypertensive patients. These findings warrant further research into the causal relationship between MSNA and ePVS and highlight the potential for ePVS as a neuroimaging biomarker for sympathetic nerve activity.

ABSTRACTAlthough substantial progress has been made in mapping the connectivity of cortical networks responsible for conscious awareness, neuroimaging analysis of subcortical networks that modulate arousal (i.e., wakefulness) has been limited by a lack of robust segmentation procedures for ascending arousal network (AAN) nuclei in the brainstem. Automated segmentation of brainstem AAN nuclei is an essential step toward elucidating the physiology of human consciousness and the pathophysiology of disorders of consciousness. We created a probabilistic atlas of 10 AAN nuclei built on diffusion MRI scans of 5 ex vivo human brain specimens imaged at 750 μm isotropic resolution. The neuroanatomic boundaries of AAN nuclei were manually annotated with reference to 200 μm 7 Tesla MRI scans in all five specimens and nucleus‐specific immunostains in two of the scanned specimens. We then developed a Bayesian segmentation algorithm that utilizes the probabilistic atlas as a generative model and automatically identifies AAN nuclei in a resolution‐ and contrast‐adaptive manner. The segmentation method displayed high accuracy when applied to in vivo T1 MRI scans of healthy individuals and patients with traumatic brain injury, as well as high test–retest reliability across T1 and T2 MRI contrasts. Finally, we show through classification and correlation assessments that the algorithm can detect volumetric changes and differences in magnetic susceptibility within AAN nuclei in patients with Alzheimer's disease and traumatic coma, respectively. We release the probabilistic atlas and Bayesian segmentation tool to advance the study of human consciousness and its disorders.Trial Registration:ClinicalTrials.gov: NCT03504709

This study aims to investigate microstructural changes in the corpus callosum (CC) of multiple sclerosis (MS) patients using texture analysis (TA), even in the absence of visible lesions on conventional MRI, and to assess its diagnostic value in distinguishing patients from healthy controls. A retrospective analysis was conducted on midsagittal T2-weighted MRI scans of 54 MS patients without CC lesions and 50 healthy controls. Histogram-based texture analysis was performed using MATLAB software, and statistical evaluations were conducted with SPSS version 25. Texture parameters were compared between groups, and a logistic regression model was developed to predict MS diagnosis. Given that our study involves a retrospective radiology analysis, obtaining consent forms is not necessary. Statistically significant differences were found between MS patients and controls in most histogram-derived texture features, including mean, median, standard deviation, and multiple percentiles (p < 0.001). The logistic regression model incorporating selected parameters achieved a diagnostic accuracy of 94.23%, successfully identifying patients with MS despite the absence of radiologically visible lesions. Texture analysis of the CC can detect subtle tissue changes in MS patients, offering a promising, non-invasive method for early diagnosis. These findings highlight the potential of TA as a complementary imaging tool in MS diagnostics and warrant further research in larger populations.

ABSTRACTObjective:This study aimed to assess the brain functional connectivity and its association with cognitive function in patients with chronic kidney disease (CKD) using resting‐state functional magnetic resonance imaging (rs‐fMRI).MethodsA total of 64 CKD patients were enrolled and divided into two groups based on their dependence on dialysis: dialysis‐dependent CKD (DD‐CKD) group (n = 38) and non‐dialysis‐dependent CKD (NDD‐CKD) group (n = 26). A total of 43 healthy controls (NC) were also recruited and matched for age and sex. Cognitive function was evaluated using the Mini‐Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA). MRI scans were conducted on a 3.0T Magnetom Skyra scanner equipped with a 32‐channel phased array head coil. Data analysis was performed using the Data Processing Assistant for Resting‐State fMRI (DPARSF) and Statistical Parametric Mapping (SPM) software.ResultsCognitive scores (MMSE and MoCA) were significantly lower in both CKD groups compared to healthy controls (p < 0.001), with DD‐CKD patients exhibiting worse cognitive performance than NDD‐CKD patients (p < 0.05). Laboratory parameters also differed: compared with DD‐CKD, NDD‐CKD patients had significantly lower levels of protein, creatinine, calcium, and phosphate (all p < 0.05). Network‐based statistical analysis revealed reduced functional connectivity in both CKD groups relative to controls (p < 0.05). NDD‐CKD patients showed disruptions mainly in the frontal‐insular and occipital networks, whereas DD‐CKD patients exhibited more extensive alterations involving frontoparietal, cingulate, and visual regions. Correlation analysis further showed that connectivity reductions in key regions—including the dorsolateral prefrontal cortex and parietal association areas—were negatively associated with renal function indicators such as serum creatinine and urea nitrogen (p < 0.05).ConclusionResting‐state fMRI effectively reflects alterations in brain functional connectivity in CKD patients and is associated with cognitive performance. Notably, DD‐CKD patients showed more extensive network disruptions and more severe cognitive impairment.

This study aimed to evaluate the effectiveness of intelligent quick magnetic resonance (IQMR) for accelerating brain MRI scanning and improving image quality in patients with acute ischemic stroke. In this prospective study, 58 patients with acute ischemic stroke underwent head MRI examinations between July 2023 and January 2024, including diffusion-weighted imaging and both conventional and accelerated T1-weighted, T2-weighted, and T2 fluid-attenuated inversion recovery fat-saturated (T2-FLAIR) sequences. Accelerated sequences were processed using IQMR, producing IQMR-T1WI, IQMR-T2WI, and IQMR-T2-FLAIR images. Image quality was assessed qualitatively by two readers using a five-point Likert scale (1 = non-diagnostic to 5 = excellent). Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of lesions and surrounding tissues were quantitatively measured. The Alberta Stroke Program Early CT Score (ASPECTS) was used to evaluate ischemia severity. Total scan time was reduced from 5 minutes 9 seconds to 2 minutes 40 seconds, accounting for a reduction of 48.22%. IQMR significantly improved SNR/CNR in accelerated sequences (P < .05), achieving parity with routine sequences (P > .05). Qualitative scores for lesion conspicuity and internal display improved post-IQMR (P < .05).. ASPECTS showed no significant difference between IQMR and routine images (P = 0.79; ICC = 0.91-0.93). IQMR addressed MRI's slow scanning limitation without hardware modifications, enhancing diagnostic efficiency. The results have been found to align with advancements in deep learning. Limitations included the small sample size and the exclusion of functional sequences. IQMR could significantly reduce brain MRI scanning time and enhance image quality in patients with acute ischemic stroke.

To assess the appropriateness of emergency department (ED) on-call medical imaging requests and the corresponding radiology reports. Two researchers reviewed all CT, MRI, and ultrasound scans ordered from January 1 to December 31, 2022 by ED physicians during on-call hours at a major Canadian hospital network (estimated 2.5million catchment population). Scan indications were evaluated for: (1) containing any clinical history and (2) providing a clinical question and/or specific differential diagnosis. Radiology report impressions were categorized as either: (1) normal (including chronic and/or stable findings); (2) positive for the clinical question and/or differential diagnosis provided; (3) positive for a condition that could reasonably explain the provided clinical history/question; or (4) only containing incidental findings unrelated to the indication. Inter-rater reliability for the scoring was assessed with the κ statistic. Among 85,066 scans ordered during ED encounters in 2022, 18,201 met inclusion criteria including 248 (1.4%) MRI, 3587 (19.7%) US, and 14,366 (78.9%) CT scans. Most requests (74.2%) provided clinical history and a differential diagnosis; a minority provided only clinical history (15.0%) or only a clinical question/differential diagnosis (10.7%). Most imaging studies contained only normal or chronic findings (62.0%). Approximately 12.5% of studies were positive for the specified differential diagnosis, 4.1% were positive for a condition that could reasonably explain the provided clinical history/question, and 21.3% identified unrelated incidental findings. The high percentage of negative scans may be an unavoidable consequence of modern medicine's growing dependence on imaging. However, ensuring that imaging tests are appropriately ordered and automating routine steps of the image acquisition workflow may mitigate strains on radiology departments.

Spatially fractionated radiotherapy (SFRT) is emerging as a powerful tool in cancer therapy for patients who are ineligible for treatment with clinically established irradiation techniques. Microbeam radiotherapy (MRT) is characterized by spatial dose fractionation in the micrometre range. This presents challenges in both treatment planning and dosimetry. While a dosimetry system with a spatial resolution of 10 µm and an option for real-time readout already exists, this system can only record dose in a very small volume. Thus, we are exploring dosimetry in an N-isopropylacrylamide (NIPAM) gel as an option for 3D dose visualization and, potentially, also three-dimensional dosimetry in larger volumes. In the current study, we have recorded the geometric patterns of single- and multiport irradiation with microbeam arrays in NIPAM gel. Data for 3D dose distribution was acquired in a 7T small animal MRI scanner. We found that the resolution of the gel is well suited for a detailed 3D visualization of microbeam patterns even in complex multiport geometries, similar to that of radiochromic film, which is well established for recording 2D dose distribution in MRT. The results suggest that a dose–response calibration is required for reliable quantitative dosimetry.

Each heartbeat generates a cardiac pressure wave that propagates through the brain and travels from large arteries through cerebrospinal fluid and brain tissue, compressing the venous sinuses and producing venous blood pulsatility. The delay between arterial and venous pulsation (A-V delay) is an insightful marker of intracranial compliance and the intracranial mechanical environment. We developed a novel approach to extract A-V delay from conventional resting-state functional MRI (fMRI) scans, leveraging fMRI’s sensitivity to vessel pulsations in large cerebral arteries and the superior sagittal sinus (SSS). This fully automated method was applied to the Human Connectome Project – Aging dataset to analyze 578 participants aged 35 to 90 years. The mean A-V delay was 78 ± 32 msec; it shortened by 4 msec for every decade of aging and was 12 msec faster in men than women, highlighting age-related and sex-specific differences. We also identified a within-SSS pattern of pulsations, characterized by an earlier posterior pulsation and a later anterior pulsation. This pattern opposes the direction of blood flow, supporting that the SSS is passively compressed and tied to a distinct intracranial pulse transmission. Overall, this work demonstrates the feasibility of extracting an fMRI-based A-V delay, uncovering a previously unexplored capability of fMRI. This approach broadens the potential applications of fMRI by adding a biomechanical dimension to fMRI’s established roles in evaluating neuronal and hemodynamic function. Given the widespread availability of fMRI, this approach can be applied in future studies to investigate biomechanical changes in various disease conditions.

Degenerative changes in the neurovascular unit (NVU) in the human spiral ganglia (SG) in patients with Meniere's disease (MD) compared with normal patients underlie the clinical manifestations of MD. Endolymphatic hydrops (EH) is the pathologic correlate of MD, yet the etiology of MD is poorly understood. EH alone does not adequately explain the changes in permeability of the cochlear blood-labyrinthine barrier seen with delayed contrast MRI or fluctuations in symptoms. Hematoxylin and eosin sections of the cochlea were obtained from temporal bones of normal patients (n=5, age: 47 to 63y, 1 male/4 female) and patients diagnosed with MD (n=8, age 51 to 88, 4 male/4 female). The number of spiral ganglia neurons (SGNs) in each cochlea was estimated. SGNs and blood vessels in the cochlea from normal and MD patients (archival celloidin sections from the same patients) were reliably identified with antibodies against acetylated-3-tubulin and glucose transporter-1, respectively, and visualized by immunofluorescence and laser confocal microscopy. There was a significant decrease (50% loss) of SGNs among patients diagnosed with MD compared with age-matched controls (P<0.05) and contralateral unaffected cochlea (35% decrease). Immunofluorescence-stained sections showed a marked decrease of blood vessels and a corresponding loss of SGNs in MD cochlea compared with controls. The decrease of spiral ganglia neurons and associated blood vessels showed regional damage of the cochlea. These results suggest that the NVU interaction may be critical to preserve the SGNs in MD and establish a framework for understanding the etiology and treatment of MD beyond EH. Not applicable.

Introduction: Osteosarcomas (OS) and Ewing’s sarcomas (ES) are third most common cancer in young adult group, lymphomas and brain tumors being more prevalent. Aim: The study aims to give appropriate measurements for making prosthesis with the use of Bone scan, MRI scan and Digital radiographs to lead better quality of remaining part of their life. Materials &amp; Methods: Patients with malignant bone tumor of Osteosarcoma and Ewing’s sarcoma of lower/upper limbs enrolled from July 2019 to August 2023 at the Institute were taken up for the prospective study. From 122 patients we have divided into two groups, Pre chemo studies and Pre and post chemo studies and each group consists of 122 and 83 patients. Totally, around 205 patients were eligible for this study and Tc99m MDP bone scan, MRI scan and Digital Radiography were taken for all these patients. Statistical Analysis: Measures of central tendency and deviation were employed to describe the data as tables (Mean, SD, median, range, %difference, etc.) and graphs (boxplots, etc.) Results: In Pre chemo study, was carried out involving 122 patients, which included 77 males and 45 females and p value &lt; 0.001 and 90% cut off percent change value is 18.3% for pre chemo bone scan and HPE values. Pre chemo &amp; Post chemo study, was carried out involving 84 patients, which included 51 males and 33 females and p value &lt; 0.087 and 90% cut off percent change value is almost equal for pre chemo MRI scan and HPE values Conclusion: Pre chemo study concluded that pre chemo bone scan, MRI scan and Digital radiography measurements are comparable and statistically analyzed using paired t test. Post chemo Bone scan tumor length variation only 8.2% and MRI scan measurements are almost equal when compare to post-operative tumor measurements. Keywords: LSS, MRI, DR, OS, ES, NAC &amp; AC

Automated Brain Tumor Detection in MRI Scans Using Deep Learning Approaches