Magnetic resonance imaging (MRI) serves as the clinical gold standard for diagnosing lumbar disc herniation (LDH). This multicenter study was to develop and clinically validate a deep learning (DL) model utilizing axial T2-weighted lumbar MRI sequences to automate LDH detection, following the Michigan State University (MSU) morphological classification criteria. A total of 8428 patients (100000 axial lumbar MRIs) with spinal surgeons annotating the datasets per MSU criteria, which classifies LDH into 11 subtypes based on morphology and neural compression severity, were analyzed. A DL architecture integrating adaptive multi-scale feature fusion titled as AFFM-YOLOv8 was developed. Model performance was validated against radiologists' annotations using accuracy, precision, recall, F1-score, and Cohen's κ (95% confidence intervals). The proposed model demonstrated superior diagnostic performance with a 91.01% F1-score (3.05% improvement over baseline) and 3% recall enhancement across all evaluation metrics. For surgical indication prediction, strong inter-rater agreement was achieved with senior surgeons (κ = 0.91, 95% CI 90.6-91.4) and residents (κ = 0.89, 95% CI 88.5-89.4), reaching consensus levels comparable to expert-to-expert agreement (senior surgeons: κ = 0.89; residents: κ = 0.87). This study establishes a DL framework for automated LDH diagnosis using large-scale axial MRI datasets. The model achieves clinician-level accuracy in MUS-compliant classification, addressing key limitations of prior binary classification systems. By providing granular spatial and morphological insights, this tool holds promise for standardizing LDH assessment and reducing diagnostic delays in resource-constrained settings.

This study aimed to validate the utility of commercially available vendor-neutral deep learning (DL) image enhancement software for improving the image quality of multiparametric MRI for gliomas in a multinational setting. A total of 294 patients from three institutions (NYU, Severance, and SNUH) who underwent glioma MRI protocols were included in this retrospective study. DL image enhancement was performed on T2-weighted (T2W), T2 FLAIR, and postcontrast T1-weighted (T1W) imaging using commercially available DL image enhancement software. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated for both conventional and DL-enhanced images. Three neuroradiologists, one from each institution, independently evaluated the following image quality parameters in both images using a 5-point scale: overall image quality, noise, gray-white matter differentiation, truncation artifact, motion artifact, pulsation artifact, and main lesion conspicuity. The quantitative and qualitative image parameters were compared between conventional and DL-enhanced images. Compared with conventional images, DL-enhanced images showed significantly higher SNRs and CNRs in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). The average scores of radiologist assessments in overall image quality, noise, gray-white matter differentiation, and main lesion conspicuity were significantly higher for DL-enhanced images than conventional images in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). Regarding artifacts, truncation artifacts decreased (all P < 0.001), while pre-existing motion and pulsation artifacts were not further exaggerated in most structural MRI sequences. In conclusion, DL image enhancement using commercially available vendor-neutral software improved image quality and reduced truncation artifacts in multiparametric glioma MRI.

Brain metastases (BMs) are the most common intracranial tumors and stereotactic radiotherapy improved the life quality of patient with BMs, while it requires more time and experience to delineate BMs precisely by oncologists. Deep Learning techniques showed promising applications in radiation oncology. Therefore, we proposed a deep learning-based automatic segmentation of primary tumor volumes for BMs in this work. Magnetic resonance imaging (MRI) of 158 eligible patients with BMs was retrospectively collected in the study. An automatic segmentation model called BUC-Net based on U-Net with cascade strategy and bottleneck module was proposed for auto-segmentation of BMs. The proposed model was evaluated using geometric metrics (Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and Average surface distance (ASD)) for the performance of automatic segmentation, and Precision recall (PR) and Receiver operating characteristic (ROC) curve for the performance of automatic detection, and relative volume difference (RVD) for evaluation. Compared with U-Net and U-Net Cascade, the BUC-Net achieved the average DSC of 0.912 and 0.797, HD95 of 0.901 mm and 0.922 mm, ASD of 0.332 mm and 0.210 mm for the evaluation of automatic segmentation in binary classification and multiple classification, respectively. The average Area Under Curve (AUC) of 0.934 and 0.835 for (Precision-Recall) PR and Receiver Operating Characteristic (ROC) curve for the tumor detection. It also performed the minimum RVD with various diameter ranges in the clinical evaluation. The BUC-Net can achieve the segmentation and modification of BMs for one patient within 10 min, instead of 3-6 h by the conventional manual modification, which is conspicuous to improve the efficiency and accuracy of radiation therapy.

Multiple sclerosis (MS) is a chronic neurological condition that affects approximately 150 000 people in the UK and presents a significant healthcare burden, including the high costs of disease-modifying treatments (DMTs). DMTs have substantially reduced the risk of relapse and moderately reduced disability progression. Patients exhibit a wide range of responses to available DMTs. The Predicting Optimal INdividualised Treatment response in MS (POINT-MS) cohort was established to predict the individual treatment response by integrating comprehensive clinical phenotyping with imaging, serum and genetic biomarkers of disease activity and progression. Here, we present the baseline characteristics of the cohort and provide an overview of the study design, laying the groundwork for future analyses. POINT-MS is a prospective, observational research cohort and biobank of 781 adult participants with a diagnosis of MS who consented to study enrolment on initiation of a DMT at the Queen Square MS Centre (National Hospital of Neurology and Neurosurgery, University College London Hospital NHS Trust, London) between 01/07/2019 and 31/07/2024. All patients were invited for clinical assessments, including the expanded disability status scale (EDSS) score, brief international cognitive assessment for MS and various patient-reported outcome measures (PROMs). They additionally underwent MRI at 3T, optical coherence tomography and blood tests (for genotyping and serum biomarkers quantification), at baseline (i.e., within 3 months from commencing a DMT), and between 6-12 (re-baseline), 18-24, 30-36, 42-48 and 54-60 months after DMT initiation. 748 participants provided baseline data. They were mostly female (68%) and White (75%) participants, with relapsing-remitting MS (94.3%), and with an average age of 40.8 (±10.9) years and a mean disease duration of 7.9 (±7.4) years since symptom onset. Despite low disability (median EDSS 2.0), cognitive impairment was observed in 40% of participants. Most patients (98.4%) had at least one comorbidity. At study entry, 59.2% were treatment naïve, and 83.2% initiated a high-efficacy DMT. Most patients (76.4%) were in either full- or part-time employment. PROMs indicated heterogeneous impairments in physical and mental health, with a greater psychological than physical impact and with low levels of fatigue. When baseline MRI scans were compared with previous scans (available in 668 (89%) patients; mean time since last scan 9±8 months), 26% and 8.5% of patients had at least one new brain or spinal cord lesion at study entry, respectively. Patients showed a median volume of brain lesions of 6.14 cm³, with significant variability among patients (CI 1.1 to 34.1). When brain tissue volumes z-scores were obtained using healthy subjects (N=113, (mean age 42.3 (± 11.8) years, 61.9% female)) from a local MRI database, patients showed a slight reduction in the volumes of the whole grey matter (-0.16 (-0.22 to -0.09)), driven by the deep grey matter (-0.47 (-0.55 to -0.40)), and of the whole white matter (-0.18 (-0.28 to -0.09)), but normal cortical grey matter volumes (0.10 (0.05 to 0.15)). The mean upper cervical spinal cord cross-sectional area (CSA), as measured from volumetric brain scans, was 62.3 (SD 7.5) mm². When CSA z-scores were obtained from the same healthy subjects used for brain measures, patients showed a slight reduction in CSA (-0.15 (-0.24 to -0.10)). Modelling with both standard statistics and machine learning approaches is currently planned to predict individualised treatment response by integrating all the demographic, socioeconomic, clinical data with imaging, genetic and serum biomarkers. The long-term output of this research is a stratification tool that will guide the selection of DMTs in clinical practice on the basis of the individual prognostic profile. We will complete long-term follow-up data in 4 years (January 2029). The biobank and MRI repository will be used for collaborative research on the mechanisms of disability in MS.

Magnetic resonance imaging (MRI) requires long acquisition times, raising costs, reducing accessibility, and making scans more susceptible to motion artifacts. Diffusion probabilistic models that learn data-driven priors can potentially assist in reducing acquisition time. However, they typically require large training datasets that can be prohibitively expensive to collect. Patch-based diffusion models have shown promise in learning effective data-driven priors over small real-valued datasets, but have not yet demonstrated clinical value in MRI. We extend the Patch-based Diffusion Inverse Solver (PaDIS) to complex-valued, multi-coil MRI reconstruction, and compare it against a state-of-the-art whole-image diffusion baseline (FastMRI-EDM) for 7x undersampled MRI reconstruction on the FastMRI brain dataset. We show that PaDIS-MRI models trained on small datasets of as few as 25 k-space images outperform FastMRI-EDM on image quality metrics (PSNR, SSIM, NRMSE), pixel-level uncertainty, cross-contrast generalization, and robustness to severe k-space undersampling. In a blinded study with three radiologists, PaDIS-MRI reconstructions were chosen as diagnostically superior in 91.7% of cases, compared to baselines (i) FastMRI-EDM and (ii) classical convex reconstruction with wavelet sparsity. These findings highlight the potential of patch-based diffusion priors for high-fidelity MRI reconstruction in data-scarce clinical settings where diagnostic confidence matters.

Diffusion models have found extensive use in solving numerous inverse problems. Such diffusion inverse problem solvers aim to sample from the posterior distribution of data given the measurements, using a combination of the unconditional score function and an approximation of the posterior related to the forward process. Recently, consistency models (CMs) have been proposed to directly predict the final output from any point on the diffusion ODE trajectory, enabling high-quality sampling in just a few NFEs. CMs have also been utilized for inverse problems, but existing CM-based solvers either require additional task-specific training or utilize data fidelity operations with slow convergence, not amenable to large-scale problems. In this work, we reinterpret CMs as proximal operators of a prior, enabling their integration into plug-and-play (PnP) frameworks. We propose a solver based on PnP-ADMM, which enables us to leverage the fast convergence of conjugate gradient method. We further accelerate this with noise injection and momentum, dubbed PnP-CM, and show it maintains the convergence properties of the baseline PnP-ADMM. We evaluate our approach on a variety of inverse problems, including inpainting, super-resolution, Gaussian deblurring, and magnetic resonance imaging (MRI) reconstruction. To the best of our knowledge, this is the first CM trained for MRI datasets. Our results show that PnP-CM achieves high-quality reconstructions in as few as 4 NFEs, and can produce meaningful results in 2 steps, highlighting its effectiveness in real-world inverse problems while outperforming comparable CM-based approaches.

To compare overall image quality, lesion conspicuity and detectability on 3D-T1w-GRE arterial phase high-resolution MR images with deep learning reconstruction (3D-DLR) against standard-of-care reconstruction (SOC-Recon) in patients with suspected pancreatic disease. Patients who underwent a pancreatic MR exam with a high-resolution 3D-T1w-GRE arterial phase acquisition on a 3.0-T MR system between December 2021 and June 2022 in our center were retrospectively included. A new deep learning-based reconstruction algorithm (3D-DLR) was used to additionally reconstruct arterial phase images. Two radiologists blinded to the reconstruction type assessed images for image quality, artifacts and lesion conspicuity using a Likert scale and counted the lesions. Signal-to-noise ratio and lesion contrast-to-noise ratio were calculated for each reconstruction. Quantitative data were evaluated using paired t-tests. Ordinal data such as image quality, artifacts and lesions conspicuity were analyzed using paired-Wilcoxon tests. Interobserver agreement for image quality and artifact assessment was evaluated using Cohen's kappa. Thirty-two patients (mean age 62 years ± 12, 16 female) were included. 3D-DLR significantly improved SNR for each pancreatic segment and lesion CNR compared to SOC-Recon (p < 0.01), and demonstrated significantly higher average image quality score (3.34 vs 2.68, p < 0.01). 3D DLR also significantly reduced artifacts compared to SOC-Recon (p < 0.01) for one radiologist. 3D-DLR exhibited significantly higher average lesion conspicuity (2.30 vs 1.85, p < 0.01). The sensitivity was increased with 3D-DLR compared to SOC-Recon for both reader 1 and reader 2 (1 vs 0.88 and 0.88 vs 0.83, p = 0.62 for both results). 3D-DLR images demonstrated higher overall image quality, leading to better lesion conspicuity. 3D deep learning reconstruction can be applied to gadolinium-enhanced pancreatic 3D-T1w arterial phase high-resolution images without additional acquisition time to further improve image quality and lesion conspicuity. 3D DLR has not yet been applied to pancreatic MRI high-resolution sequences. This method improves SNR, CNR, and overall 3D T1w arterial pancreatic image quality. Enhanced lesion conspicuity may improve pancreatic lesion detectability.

Alzheimer's disease (AD) is a progressive illness that can cause behavioural abnormalities, personality changes, and memory loss. Early detection helps with future planning for both the affected person and caregivers. Thus, an innovative hybrid Deep Learning (DL) method is introduced for the segmentation and classification of AD. The classification is performed by a Fuzzy Res-LeNet model. At first, an input Magnetic Resonance Imaging (MRI) image is attained from the database. Image preprocessing is then performed by a Bilateral Filter (BF) to enhance the quality of image by denoising. Then segmentation is carried out by the proposed O-SegUNet. This method integrates the O-SegNet and U-Net model using Pearson correlation coefficient-based fusion. After the segmentation, augmentation is carried out by utilizing Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. After that, feature extraction is carried out. Finally, AD classification is performed by the Fuzzy Res-LeNet. The stages are classified as Mild Cognitive Impairment (MCI), AD, Cognitive Normal (CN), Early Mild Cognitive Impairment (EMCI), and Late Mild Cognitive Impairment (LMCI). Here, Fuzzy Res-LeNet is devised by integrating Fuzzy logic, ResNeXt, and LeNet. Furthermore, the proposed Fuzzy Res-LeNet obtained the maximum performance with an accuracy of 93.887%, sensitivity of 94.587%, and specificity of 94.008%.

Osteoarthritis (OA) pain often does not correlate with magnetic resonance imaging (MRI)-detected structural abnormalities, limiting the clinical utility of traditional volume-based lesion assessments. To address this mismatch, we present a novel explainable artificial intelligence (XAI) framework that localizes pain-driving abnormalities in knee MR images via counterfactual image synthesis and Shapley-based feature attribution. Our method combines a Bayesian generative network-which is trained to synthesize asymptomatic versions of symptomatic knees-with a black-box pain classifier to generate counterfactual MRI scans. These counterfactuals, which are constrained by multimodal segmentation and uncertainty-aware inference, isolate lesion regions that are likely responsible for symptoms. Applying Shapley additive explanations (SHAP) to the output of the classifier enables the contribution of each lesion to pain to be precisely quantified. We trained and validated this framework on 2148 knee pairs obtained from a multicenter study of the Osteoarthritis Initiative (OAI), achieving high anatomical specificity in terms of identifying pain-relevant features such as patellar effusions and bone marrow lesions. An odds ratio (OR) analysis revealed that SHAP-derived lesion scores were significantly more strongly associated with pain than raw lesion volumes were (OR 6.75 vs. 3.73 in patellar regions), supporting the interpretability and clinical relevance of the model. Compared with conventional saliency methods and volumetric measures, our approach demonstrates superior lesion-level resolution and highlights the spatial heterogeneity of OA pain mechanisms. These results establish a new direction for conducting interpretable, lesion-specific MRI analyses that could guide personalized treatment strategies for musculoskeletal disorders.

This study aimed to identify key image parameters from the traditional and advanced MR sequences within the peritumoral edema in glioblastoma, which could predict the sub-volume with high risk of tumor recurrence. The retrospective cohort involved 32 cases with recurrent glioblastoma, while the retrospective validation cohort consisted of 5 cases. The volume of interest (VOI) including tumor and edema were manually contoured on each MR sequence. Rigid registration was performed between sequences before and after tumor recurrence. The edema before tumor recurrence was divided into the subedema-rec and subedema-no-rec depending on whether tumors occurred after registration. The histogram parameters of VOI on each sequence were collected and statistically analyzed. Beside Spearman's rank correlation analysis, Wilcoxon's paired test, least absolute shrinkage and selection operator (LASSO) analysis, and a forward stepwise logistic regression model(FSLRM) comparing with two machine learning models was developed to distinguish the subedema-rec and subedema-no-rec. The efficiency and applicability of the model was evaluated using receiver operating characteristic (ROC) curve analysis, image prediction and pathological detection. Differences of the characteristics from the ADC map between the subedema-rec and subedema-no-rec were identified, which included the standard deviation of the mean ADC value (stdmeanADC), the maximum ADC value (maxiADC), the minimum ADC value (miniADC), the Ratio-maxiADC/meanADC (maxiADC divided by the meanADC), and the kurtosis coefficient of the ADC value (all P < 0.05). FSLRM showed that the area under the ROC curve (AUC) of a single-parameter model based on Ratio-maxiADC/meanADC (0.823) was higher than that of the support vector machine (0.813) and random forest models (0.592), compared to the retrospective validation cohort's AUC of 0.776. The location prediction in image revealed that tumor recurrent mostly in the area with Ratio-maxiADC/meanADC less than 2.408. Pathological detection in 10 patients confirmed that the tumor cell dotted within the subedema-rec while not in the subedema-no-rec. The Ratio-maxiADC/meanADC is useful in predicting location of the subedema-rec.