Search Results (51)

Background/Objectives: Stroke is a leading cause of long-term disability, and predicting functional outcome at discharge, such as the modified Rankin Scale (mRS), is important for guiding treatment and rehabilitation. Many existing approaches depend on advanced imaging or complex corticospinal tract (CST) segmentation from multi-shell diffusion MRI, limiting clinical feasibility. Automated lesion segmentation is also challenging due to lesion heterogeneity and MRI variability. This study proposes a clinically feasible multimodal MRI pipeline based on routine imaging. Methods: Lesion segmentation models were trained and evaluated on the ISLES 2022 dataset (250 training, 150 test cases). Zero-shot external evaluation was performed on 149 cases from ISLES 2024 using standard MRI sequences only. An ensemble of deep learning models (SEALS, NVAUTO, FACTORIZER) was evaluated on ISLES 2022, while SEALS alone was used for external testing. CST segmentation was performed using TractSeg on single-shell diffusion-weighted imaging. Imaging biomarkers included lesion volume, shape, ADC-based texture features, CST integrity, and lesion–CST overlap. These features were used to train machine learning models for binary mRS prediction at discharge. Results: The ensemble achieved a Dice score of 0.82 on ISLES 2022, while zero-shot evaluation on ISLES 2024 achieved 0.57. In exploratory analysis, CatBoost achieved the highest point estimates (accuracy 0.88, F1-score 0.87, ROC-AUC 0.83). Key predictors included lesion–CST overlap, lesion volume, surface area, dissimilarity, and contrast. Conclusions: This exploratory study demonstrates the feasibility of combining automated lesion segmentation with anatomically informed biomarkers using routine clinical MRI, supporting interpretable stroke outcome modelling and motivating future large-scale validation. Full article

Accurate segmentation of ischemic stroke lesions from multimodal magnetic resonance imaging (MRI) is fundamental for quantitative assessment, treatment planning, and outcome prediction; yet, it remains challenging due to highly heterogeneous lesion morphology, low lesion–background contrast, and substantial variability across scanners and protocols. This work introduces Tri-UNetX-2D, a large-kernel and scale-aware 2D convolutional network with explicit boundary refinement for automated ischemic stroke lesion segmentation from DWI, ADC, and FLAIR MRI. The architecture is built on a compact U-shaped encoder–decoder backbone and integrates three key components: first, a Large-Kernel Inception (LKI) module that employs factorized depthwise separable convolutions and dilation to emulate very large receptive fields, enabling efficient long-range context modeling; second, a Scale-Aware Fusion (SAF) unit that learns adaptive weights to fuse encoder and decoder features, dynamically balancing coarse semantic context and fine structural detail; and third, a Boundary Refinement Head (BRH) that provides explicit contour supervision to sharpen lesion borders and reduce boundary error. Squeeze-and-Excitation (SE) attention is embedded within LKI and decoder stages to recalibrate channel responses and emphasize modality-relevant cues, such as DWI-dominant acute core and FLAIR-dominant subacute changes. On the ISLES 2022 multi-center benchmark, Tri-UNetX-2D improves Dice Similarity Coefficient from 0.78 to 0.86, reduces the 95th-percentile Hausdorff distance from 12.4 mm to 8.3 mm, and increases the lesion-wise F1-score from 0.71 to 0.81 compared with a plain 2D U-Net trained under identical conditions. These results demonstrate that the proposed framework achieves competitive performance with substantially lower complexity than typical 3D or ensemble-based models, highlighting its potential for scalable, clinically deployable stroke lesion segmentation. Full article

Deep vision foundation models such as DINOv3 offer strong visual representation capacity, but their direct deployment in medical image segmentation remains difficult due to the limited availability of annotated clinical data and the computational cost of full fine-tuning. This study proposes an adaptation framework called StrDiSeg that integrates lightweight bottleneck adapters between selected transformer layers of DINOv3, enabling task-specific learning while preserving pretrained knowledge. An attention-enhanced U-Net decoder with multi-scale feature fusion further refines the representations. Experiments were performed on two publicly available ischemic stroke lesion segmentation datasets—AISD (Non Contrast CT) and ISLES22 (DWI). The proposed method achieved Dice scores of 0.516 on AISD and 0.824 on ISLES22, outperforming baseline models and demonstrating strong robustness across different clinical imaging modalities. These results indicate that adapter-based fine-tuning provides a practical and computationally efficient strategy for leveraging large pretrained vision models in medical image segmentation. Full article

Background: Extracranial vertebral artery aneurysms (EVAAs) are exceptionally rare vascular lesions and an uncommon cause of posterior circulation stroke. Their diagnosis is often delayed due to nonspecific symptoms, yet prompt recognition is essential to guide management. Objective: This study aimed to report a rare case of an extracranial vertebral artery dissecting aneurysm presenting as a posterior circulation stroke in a young adult, successfully managed with flow-diverter stenting. Clinical Case: A 33-year-old woman presented with sudden-onset dysarthria, vertigo, nausea, and vomiting. Brain magnetic resonance imaging revealed infarcts in the left occipital lobe, cerebellar peduncle, and both cerebellar hemispheres. Computed tomography angiography (CTA) demonstrated a fusiform aneurysm in the V2 segment of the left vertebral artery, and digital subtraction angiography (DSA) confirmed a dissecting aneurysm. The patient was successfully treated with a flow-diverting stent and remained stable at 6 months’ follow-up with mRS 1. Results: EVAA are uncommon but can manifest as posterior circulation ischemic events in young patients. Endovascular treatment with flow-diverting stents has been reported as a feasible option in selected cases, although evidence remains limited to case reports and small series. Conclusions: This case underscores the importance of considering rare yet potentially treatable etiologies of vertebrobasilar stroke in young patients and highlights the value of a multidisciplinary approach to management. Full article

Handcrafted radiomics use predefined formulas to extract quantitative features from medical images, whereas deep neural networks learn de novo features through iterative training. We compared these approaches for predicting 3-month outcomes and hematoma expansion from admission non-contrast head CT in acute intracerebral hemorrhage (ICH). Training and cross-validation were performed using a multicenter trial cohort (n = 866), with external validation on a single-center dataset (n = 645). We trained multiscale U-shaped segmentation models for hematoma segmentation and extracted (i) radiomics from the segmented lesions and (ii) two latent deep feature sets—from the segmentation encoder and a generative autoencoder trained on dilated lesion patches. Features were reduced with unsupervised Non-Negative Matrix Factorization (NMF) to 128 per set and used—alone or in combination—for six machine-learning classifiers to predict 3-month clinical outcomes and (>3, >6, >9 mL) hematoma expansion thresholds. The addition of latent deep features to radiomics numerically increased model prediction performance for 3-month outcomes and hematoma expansion using Random Forest, XGBoost, Extra Trees, or Elastic Net classifiers; however, the improved accuracy only reached statistical significance in predicting >3 mL hematoma expansion. Clinically, these consistent but modest increases in prediction performance may improve risk stratification at the individual level. Nevertheless, the latent deep features show potential for extracting additional clinically relevant information from admission head CT for prognostication in hemorrhagic stroke. Full article

Timely identification and accurate delineation of ultra-early ischemic stroke lesions in non-contrast computed tomography (CT) scans of the human brain are of paramount importance for prompt medical intervention and improved patient outcomes. In this study, we propose a deep learning-driven methodology specifically designed for segmenting ultra-early ischemic regions, with a particular emphasis on both the ischemic core and the surrounding penumbra during the initial stages of stroke progression. We introduce a lightweight preprocessing model based on convolutional filtering techniques, which enhances image clarity while preserving the structural integrity of medical scans, a critical factor when detecting subtle signs of ultra-early ischemic strokes. Unlike conventional preprocessing methods that directly modify the image and may introduce artifacts or distortions, our approach ensures the absence of neural network-induced artifacts, which is especially crucial for accurate diagnosis and segmentation of ultra-early ischemic lesions. The model employs predefined differentiable filters with trainable parameters, allowing for artifact-free and precision-enhanced image refinement tailored to the challenges of ultra-early stroke detection. In addition, we incorporated into the combined preprocessing pipeline a newly proposed trainable linear combination of pretrained image filters, a concept first introduced in this study. For model training and evaluation, we utilize a publicly available dataset of acute ischemic stroke cases, focusing on the subset relevant to ultra-early stroke manifestations, which contains annotated non-contrast CT brain scans from 112 patients. The proposed model demonstrates high segmentation accuracy for ultra-early ischemic regions, surpassing existing methodologies across key performance metrics. The results have been rigorously validated on test subsets from the dataset, confirming the effectiveness of our approach in supporting the early-stage diagnosis and treatment planning for ultra-early ischemic strokes. Full article

Introduction: Stroke remains a major cause of disability worldwide, and precise identification of stroke lesions is essential for prognosis and rehabilitation planning. Machine learning has emerged as a powerful tool for automating stroke lesion segmentation and outcome prediction; however, these tasks are often studied in isolation. The two strategies are inherently interdependent since segmentation provides lesion-based features that directly inform prediction models. Methods: This narrative review synthesises studies published between 2010 and 2024 on the application of machine learning in stroke lesion segmentation and recovery forecasting. A total of 23 relevant studies were reviewed, including 10 focused on lesion segmentation and 13 on recovery prediction. Results: Convolutional Neural Networks (CNNs), including architectures such as U-Net, have improved segmentation accuracy on the Anatomical Tracings of Lesions After Stroke (ATLAS) V2 dataset; however, dataset bias and inconsistent evaluation metrics limit comparability. Integrating imaging-derived lesion characteristics with clinical features improves predictive accuracy at a higher level. Furthermore, semi-supervised and self-supervised methods enhanced performance where annotated datasets are scarce. Discussion: The review highlights the interdependence between segmentation and outcome prediction. Reliable segmentation provides biologically meaningful features that underpin recovery forecasting, while prediction tasks validate the clinical relevance of segmentation outputs. This bidirectional relationship underlines the need for unified pipelines integrating lesion segmentation with outcome prediction. Future research can improve generalisability and foster clinically robust models by advancing semi-supervised and self-supervised learning, bridging the gap between automated image analysis and patient-centred prognosis. Conclusion: Accurate lesion segmentation and outcome prediction should be viewed not as separate goals but as mutually reinforcing components of a single pipeline. Progress in segmentation strengthens recovery forecasting, while predictive modelling emphasises the clinical importance of segmentation outputs. This interdependence provides a pathway for developing more effective, generalisable, and relevant AI-driven stroke care tools. Full article

Ischemic stroke remains one of the leading causes of mortality and disability, and accurate segmentation of the affected areas on CT brain images plays a crucial role in timely diagnosis and clinical decision-making. This study proposes an ensemble approach based on the combination of the transformer-based models SE-UNETR and Swin UNETR using a weighted voting strategy. Its performance was evaluated using the Dice similarity coefficient, which quantifies the overlap between the predicted lesion regions and the ground-truth annotations. In this study, three-dimensional CT scans of the brain from 98 patients with a confirmed diagnosis of acute ischemic stroke were used. The data were provided by the International Tomography Center, SB RAS. The experimental results demonstrated that the ensemble based on transformer models significantly outperforms each individual model, providing more stable and accurate predictions. The final Dice coefficient reached 0.7983, indicating the high effectiveness of the proposed approach for ischemic lesion segmentation in CT images. The analysis showed more precise delineation of ischemic lesion boundaries and a reduction in segmentation errors. The proposed method can serve as an effective tool in automated stroke diagnosis systems and other applications requiring high-accuracy medical image analysis. Full article

A stroke is a critical medical condition and one of the leading causes of death among humans. Segmentation of the lesions of the brain in which the blood flow is impeded because of blood coagulation plays a vital role in drug prescription and medical diagnosis. Computed tomography (CT) scans play a crucial role in detecting abnormal tissue. There are several methods for segmenting medical images that utilize the main images without considering the patient’s privacy information. In this paper, a deep network is proposed that utilizes compressive sensing and ensemble learning to protect patient privacy and segment the dataset efficiently. The compressed version of the input CT images from the ISLES challenge 2018 dataset is applied to the ensemble part of the proposed network, which consists of two multi-resolution modified U-shaped networks. The evaluation metrics of accuracy, specificity, and dice coefficient are 92.43%, 91.3%, and 91.83%, respectively. The comparison to the state-of-the-art methods confirms the efficiency of the proposed compressive sensing-based ensemble net (CS-Ensemble Net). The compressive sensing part provides information privacy, and the parallel ensemble learning produces better results. Full article

Background: Vascular risk factors (VRFs) are known to influence cerebral small vessel disease (cSVD) burden and progression. However, their specific impact on the presence and distribution of each cSVD imaging marker (white matter hyperintensity [WMH], perivascular spaces [PVSs], lacunes, and cerebral microbleeds [CMBs]) and their spatial distribution remains unclear. Methods: We conducted a retrospective analysis of 93 patients with lacunar stroke with a standardized investigational magnetic resonance imaging protocol using a 3T scanner. WMH and PVSs were segmented semi-automatically, and lacunes and CMBs were manually segmented. We assessed the univariable associations of four common VRFs (hypertension, hyperlipidemia, diabetes, and smoking) with the load of each cSVD marker. Then, we assessed the independent associations of these VRFs in multivariable regression models adjusted for age and sex. Spatial lesion patterns were explored with regional volumetric comparisons using Pearson’s coefficient analysis, which was adjusted for multiple comparisons, and by visually examining heatmap lesion distributions. Results: Hypertension was the VRF that exhibited stronger associations with the cSVD markers in the univariable analysis. In the multivariable analysis, only lacunes (p = 0.009) and PVSs in the basal ganglia (p = 0.014) and white matter (p = 0.016) were still associated with hypertension. In the regional analysis, hypertension showed a higher WMH load in deep structures and white matter, particularly in the posterior periventricular regions. In patients with hyperlipidemia, WMH was preferentially found in hippocampal regions. Conclusions: Hypertension was confirmed to be the VRF with the most impact on cSVD load, especially for lacunes and PVSs, while the lesion topography was variable for each VRF. These findings shed light on the complexity of cSVD expression in relation to factors detrimental to vascular health. Full article

Background/Objectives: Accurate segmentation of brain stroke lesions from MRI images is a critical task in medical image analysis that is essential for timely diagnosis and treatment planning. Methods: This paper presents a novel approach for segmenting brain stroke lesions using a deep learning model based on the U-Net neural network architecture. We enhanced the traditional U-Net by integrating a transformer-based backbone, specifically the Mix Vision Transformer (MiT), and compared its performance against other commonly used backbones such as ResNet and EfficientNet. Additionally, we implemented a 2.5D method, which leverages 2D networks to process three-dimensional data slices, effectively balancing the rich spatial context of 3D methods and the simplicity of 2D methods. The 2.5D approach captures inter-slice dependencies, leading to improved lesion delineation without the computational complexity of full 3D models. Utilizing the 2015 ISLES dataset, which includes MRI images and corresponding lesion masks for 20 patients, we conducted our experiments with 4-fold cross-validation to ensure robustness and reliability. To evaluate the effectiveness of our method, we conducted comparative experiments with several state-of-the-art (SOTA) segmentation models, including CNN-based UNet, nnU-Net, TransUNet, and SwinUNet. Results: Our proposed model outperformed all competing methods in terms of Dice Coefficient and Intersection over Union (IoU), demonstrating its robustness and superiority. Our extensive experiments demonstrate that the proposed U-Net with the MiT Backbone, combined with 2.5D data preparation, achieves superior performance metrics, specifically achieving DICE and IoU scores of 0.8153 ± 0.0101 and 0.7835 ± 0.0079, respectively, outperforming other backbone configurations. Conclusions: These results indicate that the integration of transformer-based backbones and 2.5D techniques offers a significant advancement in the accurate segmentation of brain stroke lesions, paving the way for more reliable and efficient diagnostic tools in clinical settings. Full article

According to the World Health Organization (WHO), peripheral and central neurological disorders affect approximately one billion people worldwide. Ischemic stroke and Alzheimer’s Disease and other dementias are the second and fifth leading causes of death, respectively. In this context, detecting and classifying brain lesions constitute a critical area of research in medical image processing, significantly impacting clinical practice. Traditional lesion detection, segmentation, and feature extraction methods are time-consuming and observer-dependent. In this sense, research in the machine and deep learning methods applied to medical image processing constitute one of the crucial tools for automatically learning hierarchical features to get better accuracy, quick diagnosis, treatment, and prognosis of diseases. This project aims to develop and implement deep learning models for detecting and classifying small brain White Matter hyperintensities (WMH) lesions in magnetic resonance images (MRI), specifically lesions concerning ischemic and demyelination diseases. The methods applied were the UNet and Segmenting Anything model (SAM) for segmentation, while YOLOV8 and Detectron2 (based on MaskRCNN) were also applied to detect and classify the lesions. Experimental results show a Dice coefficient (DSC) of 0.94, 0.50, 0.241, and 0.88 for segmentation of WMH lesions using the UNet, SAM, YOLOv8, and Detectron2, respectively. The Detectron2 model demonstrated an accuracy of 0.94 in detecting and 0.98 in classifying lesions, including small lesions where other models often fail. The methods developed give an outline for the detection, segmentation, and classification of small and irregular morphology brain lesions and could significantly aid clinical diagnostics, providing reliable support for physicians and improving patient outcomes. Full article

Background: Unilateral basal ganglia calcinosis (BGC) is a rare radiological finding that can be diagnosed on computed tomography (CT) and magnetic resonance imaging (MRI) but often presents challenges for clinicians and radiologists in determining its underlying cause. So far, only a few potential causes that could explain unilateral BGC have been described in the literature. Case Report: A 54-year-old Caucasian male was admitted to a tertiary university hospital due to the sudden onset of speech impairment and right-sided weakness. The patient had no significant medical history prior to this event. Non-enhanced computed tomography (NECT) of the brain revealed no evidence of acute ischemia; CT angiography (CTA) showed acute left middle cerebral artery (MCA) M2 segment occlusion. CT perfusion (CTP) maps revealed an extensive penumbra-like lesion, which is potentially reversible upon achieving successful recanalization. However, a primary neoplastic tumor with calcifications in the basal ganglia was initially interpreted as the potential cause; therefore, acute stroke treatment with intravenous thrombolysis was contraindicated. A follow-up CT examination at 24 h revealed an ischemic lesion localized to the left insula, predominantly involving the left parietal lobe and the superior gyrus of the left temporal lobe. Subsequent gadolinium-enhanced brain MRI revealed small blood vessels draining into the subependymal periventricular veins on the left basal ganglia. Digital subtraction angiography was conducted, confirming the diagnosis of venous angioma. Conclusions: Unilateral BGC caused by venous angioma is a rare entity with unclear pathophysiological mechanisms and heterogeneous clinical presentation. It may mimic conditions such as intracerebral hemorrhage or hemorrhagic brain tumors, complicating acute stroke management, as demonstrated in this case. Surrounding tissue calcification may provide a valuable radiological clue in diagnosing venous angiomas DVAs and vascular malformations. Full article

Background/Objectives: Kissing aneurysms, a rare and intriguing cerebrovascular anomaly, challenge even the most advanced neurosurgical techniques. These lesions, characterized by two intimately apposed aneurysms with shared arterial walls, often masquerade as single, irregular aneurysms. This report documents a case of ruptured kissing aneurysms in the M1 segment of the right middle cerebral artery (MCA), complicated by ischemic stroke and pulmonary thromboembolism (PTE)—a convergence of severe complications rarely encountered. The case underscores the importance of precise diagnostics, innovative surgical strategies, and multidisciplinary care. Methods: A 55-year-old female presented with subarachnoid hemorrhage, confirmed by advanced imaging to arise from ruptured kissing aneurysms in the M1 segment of the right MCA. Surgical intervention via a right frontotemporal craniotomy and microsurgical clipping achieved definitive aneurysmal exclusion. Postoperatively, the patient experienced ischemic stroke and PTE, necessitating dynamic adjustments in anticoagulation therapy, intensive care, and rehabilitation protocols. Results: The dual aneurysms were successfully clipped, as confirmed by intraoperative and postoperative imaging. Despite developing significant complications, including left-sided motor deficits and PTE, a carefully orchestrated treatment strategy enabled the patient’s full recovery, with marked neurological and systemic improvement by her three-month follow-up. This favorable outcome highlights the resilience of a multidisciplinary approach in navigating such high-risk scenarios. Conclusions: This case showcases the formidable challenges of managing kissing aneurysms, particularly when compounded by stroke and PTE. It emphasizes the transformative role of cutting-edge imaging and surgical techniques in achieving successful outcomes. By illustrating how precision medicine and collaborative care can overcome rare and complex cases, this report contributes valuable insights to the evolving field of cerebrovascular surgery and postoperative management. Full article

Background: Accurate delineation of lesions in acute ischemic stroke is important for determining the extent of tissue damage and the identification of potentially salvageable brain tissues. Automatic segmentation on CT images is challenging due to the poor contrast-to-noise ratio. Quantitative CT perfusion images improve the estimation of the perfusion deficit regions; however, they are limited by a poor signal-to-noise ratio. The study aims to investigate the potential of deep learning (DL) algorithms for the improved segmentation of ischemic lesions. Methods: This study proposes a novel DL architecture, DenseResU-NetCTPSS, for stroke segmentation using multiparametric CT perfusion images. The proposed network is benchmarked against state-of-the-art DL models. Its performance is assessed using the ISLES-2018 challenge dataset, a widely recognized dataset for stroke segmentation in CT images. The proposed network was evaluated on both training and test datasets. Results: The final optimized network takes three image sequences, namely CT, cerebral blood volume (CBV), and time to max (Tmax), as input to perform segmentation. The network achieved a dice score of 0.65 ± 0.19 and 0.45 ± 0.32 on the training and testing datasets. The model demonstrated a notable improvement over existing state-of-the-art DL models. Conclusions: The optimized model combines CT, CBV, and T_max images, enabling automatic lesion identification with reasonable accuracy and aiding radiologists in faster, more objective assessments. Full article