Search Results (238)

Coronary artery disease (CAD) remains a leading cause of mortality worldwide, and accurate coronary artery segmentation in X-ray coronary angiography (XCA) is challenged by low contrast, structural ambiguity, and anisotropic vessel trajectories, which hinder quantitative coronary angiography. We propose HR-UMamba++, a U-Mamba-based framework centered on a rotation-aligned multi-directional state-space scan for modeling long-range vessel continuity across multiple orientations. To preserve thin distal branches, the framework is equipped with (i) a persistent high-resolution bypass that injects undownsampled structural details and (ii) a UNet++-style dense decoder topology for cross-scale topological fusion. On an in-house dataset of 739 XCA images from 374 patients, HR-UMamba++ is evaluated using eight segmentation metrics, fractal-geometry descriptors, and multi-view expert scoring. Compared with U-Net, Attention U-Net, HRNet, U-Mamba, DeepLabv3+, and YOLO11-seg, HR-UMamba++ achieves the best performance (Dice 0.8706, IoU 0.7794, HD95 16.99), yielding a relative Dice improvement of 6.0% over U-Mamba and reducing the deviation in fractal dimension by up to 57% relative to U-Net. Expert evaluation across eight angiographic views yields a mean score of 4.24 ± 0.49/5 with high inter-rater agreement. These results indicate that HR-UMamba++ produces anatomically faithful coronary trees and clinically useful segmentations that can serve as robust structural priors for downstream quantitative coronary analysis. Full article

High-resolution remote sensing images are gradually playing an important role in land cover mapping, urban planning, and environmental monitoring tasks. However, current segmentation approaches frequently encounter challenges such as loss of detail and blurred boundaries when processing high-resolution remote sensing imagery, owing to their complex backgrounds and dense semantic content. In response to the aforementioned limitations, this study introduces HMA-UNet, a novel segmentation network built upon the UNet framework and enhanced through a hybrid attention strategy. The architecture’s innovation centers on a composite attention block, where a lightweight split fusion attention (LSFA) mechanism and a lightweight channel-spatial attention (LCSA) mechanism are synergistically integrated within a residual learning structure to replace the stacked convolutional structure in UNet, which can improve the utilization of important shallow features and eliminate redundant information interference. Comprehensive experiments on the WHDLD dataset and the DeepGlobe road extraction dataset show that our proposed method achieves effective segmentation in remote sensing images by fully utilizing shallow features and eliminating redundant information interference. The quantitative evaluation results demonstrate the performance of the proposed method across two benchmark datasets. On the WHDLD dataset, the model attains a mean accuracy, IoU, precision, and recall of 72.40%, 60.71%, 75.46%, and 72.41%, respectively. Correspondingly, on the DeepGlobe road extraction dataset, it achieves a mean accuracy of 57.87%, an mIoU of 49.82%, a mean precision of 78.18%, and a mean recall of 57.87%. Full article

Current state-of-the-art (SoTA) instance segmentation models often struggle to accurately segment small and densely distributed vessels. In this study, we introduce MAKSEA, a new satellite imagery dataset collected from the Makkoran Coast that contains small and overlapping vessels. We also propose an efficient and robust segmentation architecture, namely MVSegNet, to segment small and overlapping ships. MVSegNet leverages three modules on the baseline UNet++ architecture: a Multi-Scale Context Aggregation block based on Atrous Spatial Pyramid Pooling (ASPP) to detect vessels with different scales, Attention-Guided Skip Connections to focus more on ship relevant features, and a Multi-Head Self-Attention Block before the final prediction layer to model long-range spatial dependencies and refine densely packed regions. We evaluated our final model with SoTA instance segmentation architectures on two benchmark datasets including LEVIR_SHIP and DIOR_SHIP as well as our challenging MAKSEA datasets using several evaluation metrics. MVSegNet achieves the best performance in terms of F1-Score on LEVIR_SHIP (0.9028) and DIOR_SHIP (0.9607) datasets. On MAKSEA, it achieves an IoU of 0.826, improving the baseline by about 7.0%. The extensive quantitative and qualitative ablation experiments confirm that the proposed approach is effective for real-world maritime traffic monitoring applications, particularly in scenarios with dense vessel distributions. Full article

Timely and accurate urban change detection is vital for sustainable urban development, infrastructure management, and disaster response. Traditional two-dimensional approaches often overlook vertical and structural variations in dense urban areas. This study proposes a three-dimensional (3D) change detection framework that integrates high-resolution optical imagery and Digital Surface Models (DSMs) from two time points to capture both horizontal and vertical transformations. The method is based on a deep learning architecture combining a ResNet34 encoder with a UNet++ decoder, enabling the joint learning of spectral and elevation features. The research was carried out in two stages. First, a binary classification model was trained to detect areas of change and no-change, allowing direct comparison with conventional methods such as Principal Component Analysis (PCA), Change Vector Analysis (CVA) with thresholding, K-Means clustering, and Random Forest classification. In the second stage, a multi-class model was developed to categorize the types of structural changes, including new building construction, complete destruction, building height increase, and height decrease. Experiments conducted on a high-resolution urban dataset demonstrated that the proposed CNN-based framework significantly outperformed traditional methods, achieving an overall accuracy of 96.58%, an F1-score of 96.58%, and a recall of 96.7%. Incorporating DSM data notably improved sensitivity to elevation-related changes. Overall, the ResNet34–UNet++ architecture offers a robust and accurate solution for 3D urban change detection, supporting more effective urban monitoring and planning. Full article

Early detection of breast cancer commonly relies on imaging technologies such as ultrasound, mammography and MRI. Among these, breast ultrasound is widely used by radiologists to identify and assess lesions. In this study, we developed image segmentation techniques and multiclass classification artificial intelligence (AI) tools based on pretrained models to segment lesions and detect breast cancer. The proposed workflow includes both the development of segmentation models and development of a series of classification models to classify ultrasound images as normal, benign or malignant. The pretrained models were trained and evaluated on the Breast Ultrasound Images (BUSI) dataset, a publicly available collection of grayscale breast ultrasound images with corresponding expert-annotated masks. For segmentation, images and ground-truth masks were used to pretrained encoder (ResNet18, EfficientNet-B0 and MobileNetV2)–decoder (U-Net, U-Net++ and DeepLabV3) models, including the DeepLabV3 architecture integrated with a Frequency-Domain Feature Enhancement Module (FEM). The proposed FEM improves spatial and spectral feature representations using Discrete Fourier Transform (DFT), GroupNorm, dropout regularization and adaptive fusion. For classification, each image was assigned a label (normal, benign or malignant). Optuna, an open-source software framework, was used for hyperparameter optimization and for the testing of various pretrained models to determine the best encoder–decoder segmentation architecture. Five different pretrained models (ResNet18, DenseNet121, InceptionV3, MobielNetV3 and GoogleNet) were optimized for multiclass classification. DeepLabV3 outperformed other segmentation architectures, with consistent performance across training, validation and test images, with Dice Similarity Coefficient (DSC, a metric describing the overlap between predicted and true lesion regions) values of 0.87, 0.80 and 0.83 on training, validation and test sets, respectively. ResNet18:DeepLabV3 achieved an Intersection over Union (IoU) score of 0.78 during training, while ResNet18:U-Net++ achieved the best Dice coefficient (0.83) and IoU (0.71) and area under the curve (AUC, 0.91) scores on the test (unseen) dataset when compared to other models. However, the proposed Resnet18: FrequencyAwareDeepLabV3 (FADeepLabV3) achieved a DSC of 0.85 and an IoU of 0.72 on the test dataset, demonstrating improvements over standard DeepLabV3. Notably, the frequency-domain enhancement substantially improved the AUC from 0.90 to 0.98, indicating enhanced prediction confidence and clinical reliability. For classification, ResNet18 produced an F1 score—a measure combining precision and recall—of 0.95 and an accuracy of 0.90 on the training dataset, while InceptionV3 performed best on the test dataset, with an F1 score of 0.75 and accuracy of 0.83. We demonstrate a comprehensive approach to automate the segmentation and multiclass classification of breast cancer ultrasound images into benign, malignant or normal transfer learning models on an imbalanced ultrasound image dataset. Full article

This paper provides an overview of artificial intelligence (AI) applications in ophthalmology, with a focus on diagnosing dry eye disease (DED). We aim to synthesize studies that explicitly compare AI-based diagnostic models with clinical tests employed by ophthalmologists, examine results obtained using similar imaging modalities, and identify recurring limitations to propose recommendations for future work. We conducted a systematic literature search following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines across four databases: Google Scholar, PubMed, ScienceDirect, and the Cochrane Library. We targeted studies published between 2020 and 2025 and applied predefined inclusion criteria to select 30 original peer-reviewed articles. We then analyzed each study based on the AI models used, development strategies, diagnostic performance, correlation with clinical parameters, and reported limitations. The imaging modalities covered include videokeratography, smartphone-based imaging, tear film interferometry, anterior segment optical coherence tomography, infrared meibography, in vivo confocal microscopy, and slit-lamp photography. Across modalities, deep learning models (e.g., U-shaped Convolutional Network (U-Net), Residual Network (ResNet), Densely Connected Convolutional Network (DenseNet), Generative Adversarial Networks (GANs), transformers) demonstrated promising performance, often matching or surpassing clinical assessments, with reported accuracies ranging from 82% to 99%. However, few studies performed external validations or addressed inter-expert variability. The findings confirm AI’s potential in DED diagnosis, but emphasize gaps in data diversity, clinical use, and reproducibility. It offers practical recommendations for future research to bridge these gaps and support AI deployment in routine eye care. Full article

Accurate evaluation of the Temporomandibular joint (TMJ) components is essential for proper diagnosis and treatment. However, the current diagnostic process relies heavily on manual measurements, which are time-consuming and prone to human error. Here, the fundamental task is performed using imaging techniques and locating regions of interest in the TMJ. Nowadays, such image segmentation has been automated using a number of deep learning models. Nonetheless, developed models for TMJ segmentation are primarily built on symmetric convolutional kernels, which may limit their ability to capture the inherently asymmetric structures of the joint. To address this gap, this work proposes a novel approach that integrates an asymmetric kernel into a DenseUNet architecture and squeeze-and-excitation blocks for the automatic segmentation of three key morphological components of the TMJ. A metaheuristic iterated local search algorithm was used to identify the most effective kernel configuration within a search space of ${15}^2$ asymmetric kernel combinations. The resulting optimized architecture was trained and evaluated on a TMJ imaging dataset and compared against nine state-of-the-art segmentation architectures. The proposed method achieved the highest Dice coefficient of 0.78, outperforming all baseline architectures, and demonstrated efficient processing with an average inference time of 0.16 s per image. These results highlight the potential of the proposed system to enhance the accuracy and efficiency of TMJ diagnostics in clinical settings. Full article

In this paper, we present a water mist dehazing network to improve the accuracy of radiation temperature measurements of the billet surface in the secondary cooling zone of continuous casting. First, we develop a billet radiation attenuation model that accounts for the wavelength-dependent attenuation coefficient of water mist in the secondary cooling zone. Using this model and the corresponding dataset, the water mist transmittance is calculated. Furthermore, the water mist dehazing network—which is distinct from conventional dehazing networks designed for natural environments—comprises three key components: water mist feature extraction based on a combined Unet and Transformer structure; fusion of prior water mist transmittance data using an attention mechanism; and composite transmittance estimation via a multi-path dense network. The experimental results demonstrate that the proposed network effectively reduces water mist’s interference with billet surface temperature measurements in both the spatial and temporal dimensions. Compared with the standalone Unet and Unet + Transformer network architectures, the proposed network achieves a significantly improved dehazing performance, thus verifying its practical value and reliability for billet surface temperature measurement tasks. Full article

Background/Objectives: Accurate volumetry of the remnant pancreas after pancreatectomy is crucial for assessing postoperative endocrine and exocrine function but remains challenging due to anatomical variability and complex postoperative morphology. This study aimed to develop and validate a deep learning (DL)-based model for automatic segmentation and volumetry of the remnant pancreas using abdominal CT images. Methods: A total of 1067 CT scans from 341 patients who underwent pancreaticoduodenectomy and 512 scans from 184 patients who underwent distal pancreatectomy were analyzed. Ground truth masks were manually delineated and verified through multi-expert consensus. Six 3D segmentation models were trained and compared, including four convolution-based U-Net variants (basic, dense, residual, and residual dense) and two transformer-based models (Trans U-Net and Swin U-Net). Model performance was evaluated using five-fold cross-validation with sensitivity, specificity, precision, accuracy, and Dice similarity coefficient. Results: The Residual Dense U-Net achieved the best performance among convolutional models, with dice similarity coefficient (DSC) values of 0.7655 ± 0.0052 for pancreaticoduodenectomy and 0.8086 ± 0.0091 for distal pancreatectomy. Transformer-based models showed slightly higher DSCs (Swin U-Net: 0.7787 ± 0.0062 and 0.8132 ± 0.0101), with statistically significant but numerically small improvements (p < 0.01). Conclusions: The proposed DL-based approach enables accurate and reproducible postoperative pancreas segmentation and volumetry. Automated volumetric assessment may support objective evaluation of remnant pancreatic function and provide a foundation for predictive modeling in long-term clinical management after pancreatectomy. Full article

Background/Objectives: Sarcopenia and muscle composition have emerged as significant indicators in the fields of musculoskeletal and metabolic research. The objective of this study was to develop and validate a fully automated, deep learning-based method for segmenting thigh muscles into three functional groups (extensor, flexor, and adductor) using non-contrast computed tomography (CT) images and to quantitatively evaluate the thigh muscles. Methods: In order to ascertain the most efficacious architecture for automated thigh muscle segmentation, three deep learning models (Dense U-Net, MANet, and SegFormer) were implemented and subsequently compared. Each model was trained using 136 manually labeled non-contrast thigh CT scans and externally validated with 40 scans from another institution. The performance of the segmentation was evaluated using the Dice similarity coefficient (DSC), sensitivity, specificity, and accuracy. Quantitative indices, including total muscle volume, lean muscle volume, and intra-/intermuscular fat volumes, were automatically calculated and compared with manual measurements. Results: All three models exhibited high segmentation accuracy, with the mean DSC exceeding 96%. The MANet model demonstrated optimal performance in internal validation, while the SegFormer model exhibited superior volumetric agreement in external validation, as indicated by an intraclass correlation coefficient (ICC) of at least 0.995 and a p-value less than 0.01. Conclusions: A CT-based deep learning framework enables accurate and reproducible segmentation of functional thigh muscle groups. A comparative evaluation of convolutional attention- and transformer-based architectures supports the feasibility of CT-based quantitative muscle assessment for sarcopenia and musculoskeletal research. Full article

The Yellow River Delta (YRD) is a vital agricultural and ecologically fragile zone in China. Understanding the spatial pattern and evolutionary characteristics of Rural Settlements Area (RSA) in this region is crucial for both ecological protection and sustainable development. This study focuses on Dongying, a key YRD city, and compares four advanced deep learning models—U-Net, DeepLabv3+, TransUNet, and TransDeepLab—using fused Sentinel-1 radar and Landsat optical imagery to identify the optimal method for RSA mapping. Results show that TransUNet, integrating polarization and optical features, achieves the highest accuracy, with Precision, Recall, F1 score, and mIoU of 89.27%, 80.70%, 84.77%, and 85.39%, respectively. Accordingly, TransUNet was applied for the spatiotemporal extraction of RSA in 2002, 2008, 2015, 2019, and 2023. The results indicate that medium-sized settlements dominate, showing a “dense in the west/south, sparse in the east/north” pattern with clustered distribution. Settlement patches are generally regular but grow more complex over time while maintaining strong connectivity. In summary, the proposed method offers technical support for RSA identification in the YRD, and the extracted multi-temporal settlement data can serve as a valuable reference for optimizing settlement layout in the region. Full article

We propose a local–global attention fusion network for benign–malignant discrimination of ovarian tumors in color Doppler ultrasound (CDFI). The framework integrates three complementary modules: a local enhancement module (LEM) to capture fine-grained texture and boundary cues, a Global Attention Module (GAM) to model long-range dependencies with flow-aware priors, and a Fusion Discriminator (FD) to align and adaptively reweight heterogeneous evidence for robust decision-making. The method was evaluated on a multi-center clinical dataset comprising 820 patient cases (482 benign and 338 malignant), ensuring a realistic and moderately imbalanced distribution. Compared with classical baselines including ResNet-50, DenseNet-121, ViT, Hybrid CNN–Transformer, U-Net, and SegNet, our approach achieved an accuracy of 0.923, sensitivity of 0.911, specificity of 0.934, AUC of 0.962, and F1-score of 0.918, yielding improvements of about three percentage points in the AUC and F1-score over the strongest baseline. Ablation experiments confirmed the necessity of each module, with the performance degrading notably when the GAM or the LEM was removed, while the complete design provided the best results, highlighting the benefit of local–global synergy. Five-fold cross-validation further demonstrated stable generalization (accuracy: 0.922; AUC: 0.961). These findings indicate that the proposed system offers accurate and robust assistance for preoperative triage, surgical decision support, and follow-up management of ovarian tumors. Full article

Remote sensing images, which obtain surface information from aerial or satellite platforms, are of great significance in fields such as environmental monitoring, urban planning, agricultural management, and disaster response. However, due to the complex and diverse types of ground coverage and significant differences in spectral characteristics in remote sensing images, achieving high-quality semantic segmentation still faces many challenges, such as blurred target boundaries and difficulty in recognizing small-scale objects. To address these issues, this study proposes a novel deep learning model, MKF-NET. The fusion of KAN convolution and Vision Transformer (ViT), combined with the multi-scale feature extraction and dense connection mechanism, significantly improves the semantic segmentation performance of remote sensing images. Experiments were conducted on the LoveDA dataset to systematically evaluate the segmentation performance of MKF-NET and several existing traditional deep learning models (U-net, Unet++, Deeplabv3+, Transunet, and U-KAN). Experimental results show that MKF-NET performs best in many indicators: it achieved a pixel precision of 78.53%, a pixel accuracy of 79.19%, an average class accuracy of 76.50%, and an average intersection-over-union ratio of 64.31%; it provides efficient technical support for remote sensing image analysis. Full article

Background/Objectives: Diagnosis of abdominal aortic aneurysm and abdominal aortic dissection (AAA and AAD) is of strategic importance as cardiovascular disease has fatal implications worldwide. This study presents a novel deep learning-based approach for the accurate and efficient diagnosis of abdominal aortic aneurysms (AAAs) and aortic dissections (AADs) from CT images. Methods: Our proposed convolutional neural network (CNN) architecture effectively extracts relevant features from CT scans and classifies regions as normal or diseased. Additionally, the model accurately delineates the boundaries of detected aneurysms and dissections, aiding in clinical decision-making. A pyramid scene parsing network has been built in a hybrid method. The layer block after the classification layer is divided into two groups: whether there is an AAA or AAD region in the abdominal CT image, and determination of the borders of the detected diseased region in the medical image. Results: In this sense, both detection and segmentation are performed in AAA and AAD diseases. Python programming has been used to assess the accuracy and performance results of the proposed strategy. From the results, average accuracy rates of 83.48%, 86.9%, 88.25%, and 89.64% were achieved using ResDenseUNet, INet, C-Net, and the proposed strategy, respectively. Also, intersection over union (IoU) of 79.24%, 81.63%, 82.48%, and 83.76% have been achieved using ResDenseUNet, INet, C-Net, and the proposed method. Conclusions: The proposed strategy is a promising technique for automatically diagnosing AAA and AAD, thereby reducing the workload of cardiovascular surgeons. Full article

Background/Objectives: GK plan quality is strongly affected by lesion size and shape, and the same evaluation metrics may not be directly comparable across patients with different anatomies. This study proposes a deep learning-based method to predict achievable, clinically acceptable plan quality from patient-specific geometry. Methods: A hierarchically densely connected U-Net (HD-U-Net) was trained at the lesion level to predict 3D dose distributions for the estimation of plan quality metrics, including coverage, selectivity, gradient index (GI), and conformity index at a 50% prescription dose (CI50). To improve the prediction accuracy of plan quality metrics, Dice similarity coefficient losses for the 100% and 50% isodose lines were incorporated with conventional mean squared error (MSE) loss. Results: Ten-fold cross-validation on 463 brain metastases (BMs) from 175 patients showed that our method achieved smaller mean absolute errors across all four metrics than the HD-U-Net baseline trained with MSE loss. Improvements were pronounced in all metrics for small metastases, and were observed primarily in GI and CI50 for medium and large lesions. Paired Wilcoxon signed-rank tests confirmed the statistical significance of these improvements (p < 0.05). Conclusions: The proposed method outperformed the baseline model in capturing overall trends, improving per-lesion accuracy, and enhancing robustness to dataset variability. It can serve as a pre-planning tool to guide planners in constraint setting and priority tuning, a post-planning quality control tool to identify subpar plans that could be substantially improved, and as a foundation for developing deep reinforcement learning-based automated planning of GK treatments for brain metastases. Full article