Medical imaging modalities are inherently susceptible to noise contamination that degrades diagnostic utility and clinical assessment accuracy. This paper presents a comprehensive comparative evaluation of three state-of-the-art deep learning architectures for MRI brain image denoising: CNN-DAE, CADTra, and DCMIEDNet. We systematically evaluate these models across multiple Gaussian noise intensities ($\sigma = 10, 15, 25$) using the Figshare MRI Brain Dataset. Our experimental results demonstrate that DCMIEDNet achieves superior performance at lower noise levels, with PSNR values of $32.921 \pm 2.350$ dB and $30.943 \pm 2.339$ dB for $\sigma = 10$ and $15$ respectively. However, CADTra exhibits greater robustness under severe noise conditions ($\sigma = 25$), achieving the highest PSNR of $27.671 \pm 2.091$ dB. All deep learning approaches significantly outperform traditional wavelet-based methods, with improvements ranging from 5-8 dB across tested conditions. This study establishes quantitative benchmarks for medical image denoising and provides insights into architecture-specific strengths for varying noise intensities.

Magnetic Resonance Imaging (MRI) is indispensable in clinical practice but remains constrained by fragmented, multi-stage workflows encompassing acquisition, reconstruction, segmentation, detection, diagnosis, and reporting. While deep learning has achieved progress in individual tasks, existing approaches are often anatomy- or application-specific and lack generalizability across diverse clinical settings. Moreover, current pipelines rarely integrate imaging data with complementary language information that radiologists rely on in routine practice. Here, we introduce OmniMRI, a unified vision-language foundation model designed to generalize across the entire MRI workflow. OmniMRI is trained on a large-scale, heterogeneous corpus curated from 60 public datasets, over 220,000 MRI volumes and 19 million MRI slices, incorporating image-only data, paired vision-text data, and instruction-response data. Its multi-stage training paradigm, comprising self-supervised vision pretraining, vision-language alignment, multimodal pretraining, and multi-task instruction tuning, progressively equips the model with transferable visual representations, cross-modal reasoning, and robust instruction-following capabilities. Qualitative results demonstrate OmniMRI's ability to perform diverse tasks within a single architecture, including MRI reconstruction, anatomical and pathological segmentation, abnormality detection, diagnostic suggestion, and radiology report generation. These findings highlight OmniMRI's potential to consolidate fragmented pipelines into a scalable, generalist framework, paving the way toward foundation models that unify imaging and clinical language for comprehensive, end-to-end MRI interpretation.

To explore the efficacy of a deep learning (DL) model in predicting perineural invasion (PNI) in prostate cancer (PCa) by conducting multiparametric MRI (mpMRI)-based tumor heterogeneity analysis. This retrospective study included 397 patients with PCa from two medical centers. The patients were divided into training, internal validation (in-vad), and independent external validation (ex-vad) cohorts (n = 173, 74, and 150, respectively). mpMRI-based habitat analysis, comprising T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient sequences, was performed followed by DL, deep feature selection, and filtration to compute a radscore. Subsequently, six models were constructed: one clinical model, four habitat models (habitats 1, 2, 3, and whole-tumor), and one combined model. Receiver operating characteristic curve analysis was performed to evaluate the models' ability to predict PNI. The four habitat models exhibited robust performance in predicting PNI, with area under the curve (AUC) values of 0.862-0.935, 0.802-0.957, and 0.859-0.939 in the training, in-vad, and ex-vad cohorts, respectively. The clinical model had AUC values of 0.832, 0.818, and 0.789 in the training, in-vad, and ex-vad cohorts, respectively. The combined model outperformed the clinical and habitat models, with AUC, sensitivity, and specificity values of 0.999, 1, and 0.955 for the training cohort. Decision curve analysis and clinical impact curve analysis indicated favorable clinical applicability and utility of the combined model. DL models constructed through mpMRI-based habitat analysis accurately predict the PNI status of PCa.

Early and accurate brain tumor classification is vital for clinical diagnosis and treatment. Although Convolutional Neural Networks (CNNs) are widely used in medical image analysis, they often struggle to focus on critical information adequately and have limited feature extraction capabilities. To address these challenges, this study proposes a novel Residual Network based on Multi-dimensional Attention and Pinwheel Convolution (Res-MAPNet) for Magnetic Resonance Imaging (MRI) based brain tumor classification. Res-MAPNet is developed on two key modules: the Coordinated Local Importance Enhancement Attention (CLIA) module and the Pinwheel-Shaped Attention Convolution (PSAConv) module. CLIA combines channel attention, spatial attention, and direction-aware positional encoding to focus on lesion areas. PSAConv enhances spatial feature perception through asymmetric padding and grouped convolution, expanding the receptive field for better feature extraction. The proposed model classifies two publicly brain tumor datasets into glioma, meningioma, pituitary tumor, and no tumor. The experimental results show that the proposed model achieves 99.51% accuracy in the three-classification task and 98.01% accuracy in the four-classification task, better than the existing mainstream models. Ablation studies validate the effectiveness of CLIA and PSAConv, which are 4.41% and 4.45% higher than the ConvNeXt baseline, respectively. This study provides an efficient and robust solution for brain tumor computer-aided diagnosis systems with potential for clinical applications.

Brain tumors remain among the most lethal human diseases, where early detection and accurate classification are critical for effective diagnosis and treatment planning. Although deep learning-based computer-aided diagnostic (CADx) systems have shown remarkable progress. However, conventional convolutional neural networks (CNNs) and Transformers face persistent challenges, including high computational cost, sensitivity to minor contrast variations, structural heterogeneity, and texture inconsistencies in MRI data. Therefore, a novel hybrid framework, CE-RS-SBCIT, is introduced, integrating residual and spatial learning-based CNNs with transformer-driven modules. The proposed framework exploits local fine-grained and global contextual cues through four core innovations: (i) a smoothing and boundary-based CNN-integrated Transformer (SBCIT), (ii) tailored residual and spatial learning CNNs, (iii) a channel enhancement (CE) strategy, and (iv) a novel spatial attention mechanism. The developed SBCIT employs stem convolution and contextual interaction transformer blocks with systematic smoothing and boundary operations, enabling efficient global feature modeling. Moreover, Residual and spatial CNNs, enhanced by auxiliary transfer-learned feature maps, enrich the representation space, while the CE module amplifies discriminative channels and mitigates redundancy. Furthermore, the spatial attention mechanism selectively emphasizes subtle contrast and textural variations across tumor classes. Extensive evaluation on challenging MRI datasets from Kaggle and Figshare, encompassing glioma, meningioma, pituitary tumors, and healthy controls, demonstrates superior performance, achieving 98.30% accuracy, 98.08% sensitivity, 98.25% F1-score, and 98.43% precision.

To evaluate deep-learning (DL) based real-time cardiac cine sequences acquired in free breathing (FB) vs breath hold (BH). In this prospective single-centre cohort study, 56 healthy adult volunteers were investigated on a 1.5-T MRI scanner. A set of real-time cine sequences, including a short-axis stack, 2-, 3-, and 4-chamber views, was acquired in FB and with BH. A validated DL-based cine sequence acquired over three cardiac cycles served as the reference standard for volumetric results. Subjective image quality (sIQ) was rated by two blinded readers. Volumetric analysis of both ventricles was performed. sIQ was rated as good to excellent for FB real-time cine images, slightly inferior to BH real-time cine images (p < 0.0001). Overall acquisition time for one set of cine sequences was 50% shorter with FB (median 90 vs 180 s, p < 0.0001). There were significant differences between the real-time sequences and the reference in left ventricular (LV) end-diastolic volume, LV end-systolic volume, LV stroke volume and LV mass. Nevertheless, BH cine imaging showed excellent correlation with the reference standard, with an intra-class correlation coefficient (ICC) > 0.90 for all parameters except right ventricular ejection fraction (RV EF, ICC = 0.887). With FB cine imaging, correlation with the reference standard was good for LV ejection fraction (LV EF, ICC = 0.825) and RV EF (ICC = 0.824) and excellent (ICC > 0.90) for all other parameters. DL-based real-time cine imaging is feasible even in FB with good to excellent image quality and acceptable volumetric results in healthy volunteers. Question Conventional cardiac MR (CMR) cine imaging is challenged by arrhythmias and patients unable to hold their breath, since data is acquired over several heartbeats. Findings DL-based real-time cine imaging is feasible in FB with acceptable volumetric results and reduced acquisition time by 50% compared to real-time breath-hold sequences. Clinical relevance This study fits into the wider goal of increasing the availability of CMR by reducing the complexity, duration of the examination and improving patient comfort and making CMR available even for patients who are unable to hold their breath.

Accurately predicting pseudoprogression (PsP) from tumor progression (TuP) in patients with glioblastoma (GBM) is crucial for treatment and prognosis. This study develops a deep learning (DL) prognostic model using pre- and post-operative contrast-enhanced T1-weighted (CET1) magnetic resonance imaging (MRI) to forecast the likelihood of PsP or TuP following standard GBM treatment. Brain MRI data and clinical characteristics from 110 GBM patients were divided into a training set (n = 68) and a validation set (n = 42). Pre-operative and post-operative CET1 images were used individually and combined. A Vision Transformer (ViT) model was built using expert-segmented tumor images to extract DL features. Several mainstream convolutional neural network (CNN) models (DenseNet121, Inception_v3, MobileNet_v2, ResNet18, ResNet50, and VGG16) were built for comparative evaluation. Principal Component Analysis (PCA) and Least Absolute Shrinkage and Selection Operator (LASSO) regression selected the significant features, classified using a Multi-Layer Perceptron (MLP). Model performance was evaluated with Receiver Operating Characteristic (ROC) curves. A multimodal model also incorporated DL features and clinical characteristics. The optimal input for predicting TuP versus PsP was the combination of pre- and post-operative CET1 tumor regions. The CET1-ViT model achieved an area under the curve (AUC) of 95.5% and accuracy of 90.7% on the training set, and an AUC of 95.2% and accuracy of 96.7% on the validation set. This model outperformed the mainstream CNN models. The multimodal model showed superior performance, with AUCs of 98.6% and 99.3% on the training and validation sets, respectively. We developed a DL model based on pre- and post-operative CET1 imaging that can effectively forecast PsP versus TuP in GBM patients, offering potential for evaluating treatment responses and early indications of tumor progression.

Epicardial and paracardial adipose tissues (EAT and PAT) are two types of fat depots around the heart and they have important roles in cardiac physiology. Manual quantification of EAT and PAT from cardiac MR (CMR) is time-consuming and prone to human bias. Leveraging the cardiac motion, we aimed to develop deep learning neural networks for automated segmentation and quantification of EAT and PAT in short-axis cine CMR. A modified U-Net equipped with modules of multi-resolution convolution, motion information extraction, feature fusion, and dual attention mechanisms, was developed. Multiple steps of ablation studies were performed to verify the efficacy of each module. The performance of different networks was also compared. The final network incorporating all modules achieved segmentation Dice indices of 77.72% ± 2.53% and 77.18% ± 3.54% for EAT and PAT, respectively, which were significantly higher than the baseline U-Net. It also achieved the highest performance compared to other networks. With our model, the determination coefficients of EAT and PAT volumes to the reference were 0.8550 and 0.8025, respectively. Our proposed network can provide accurate and quick quantification of EAT and PAT on routine short-axis cine CMR, which can potentially aid cardiologists in clinical settings.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with increasing prevalence among the ageing population, necessitating early and accurate diagnosis for effective disease management. In this study, we present a novel hybrid deep learning framework, AlzhiNet, that integrates both 2D convolutional neural networks (2D-CNNs) and 3D convolutional neural networks (3D-CNNs), along with a custom loss function and volumetric data augmentation, to enhance feature extraction and improve classification performance in AD diagnosis. According to extensive experiments, AlzhiNet outperforms standalone 2D and 3D models, highlighting the importance of combining these complementary representations of data. The depth and quality of 3D volumes derived from the augmented 2D slices also significantly influence the model's performance. The results indicate that carefully selecting weighting factors in hybrid predictions is imperative for achieving optimal results. Our framework has been validated on the magnetic resonance imaging (MRI) from Kaggle and MIRIAD datasets, obtaining accuracies of 98.9% and 99.99%, respectively, with an AUC of 100%. Furthermore, AlzhiNet was studied under a variety of perturbation scenarios on the Alzheimer's Kaggle dataset, including Gaussian noise, brightness, contrast, salt and pepper noise, color jitter, and occlusion. The results obtained show that AlzhiNet is more robust to perturbations than ResNet-18, making it an excellent choice for real-world applications. This approach represents a promising advancement in the early diagnosis and treatment planning for AD.

Placenta accreta spectrum (PAS) is a serious perinatal complication. Accurate preoperative identification of patients at high risk for adverse clinical outcomes is essential for developing personalized treatment strategies. This study aimed to develop and validate a high-performance, interpretable machine learning model that integrates MRI morphological indicators and clinical features to predict adverse outcomes in PAS, and to build an online prediction tool to enhance its clinical applicability. This retrospective study included 125 clinically confirmed PAS patients from two centers, categorized into high-risk (intraoperative blood loss over 1500 mL or requiring hysterectomy) and low-risk groups. Data from Center 1 were used for model development, and data from Center 2 served as the external validation set. Five MRI morphological indicators and six clinical features were extracted as model inputs. Three machine learning classifiers-AdaBoost, TabPFN, and CatBoost-were trained and evaluated on both internal testing and external validation cohorts. SHAP analysis was used to interpret model decision-making, and the optimal model was deployed via a Streamlit-based web platform. The CatBoost model achieved the best performance, with AUROCs of 0.90 (95% CI: 0.73-0.99) and 0.84 (95% CI: 0.70-0.97) in the internal testing and external validation sets, respectively. Calibration curves indicated strong agreement between predicted and actual risks. SHAP analysis revealed that "Cervical canal length" and "Gestational age" contributed negatively to high-risk predictions, while "Prior C-sections number", "Placental abnormal vasculature area", and Parturition were positively associated. The final online tool allows real-time risk prediction and visualization of individualized force plots and is freely accessible to clinicians and patients. This study successfully developed an interpretable and practical machine learning model for predicting adverse clinical outcomes in PAS. The accompanying online tool may support clinical decision-making and improve individualized management for PAS patients.