Despite significant progress in medical image segmentation, clinical deployment faces challenges due to inherent uncertainties. These uncertainties primarily arise from ambiguous lesion boundaries, complex anatomical structures, and variations in imaging quality, all of which significantly affect the reliability of segmentation outcomes. To address this issue, we propose a novel Hierarchical Uncertainty-Aware Segmentation Framework (HUA-Seg), which explicitly models and utilizes uncertainty throughout the forward propagation process. HUASeg is designed to hierarchically perceive, quantify, and exploit uncertainty, enhancing segmentation robustness and generalization. Our method comprises three core components: (1) an uncertainty-modulated self-attention mechanism that adaptively emphasizes reliable features during early-stage representation learning, enabling the extraction of more robust feature embeddings; (2) an uncertainty-guided dual-strategy feature refinement module, which reallocates learning focus towards low-confidence regions-such as lesion boundaries-facilitating effective complex example mining and contour refinement; and (3) multi-scale uncertainty supervision, providing an explicit, data-dependent regularization signal that stabilizes training and enhances generalization. Extensive experiments on multiple public medical image segmentation benchmarks demonstrate that HUA-Seg consistently outperforms state-of-the-art methods, highlighting its effectiveness in handling complex and uncertain medical image segmentation scenarios.

In complex visual scenarios, people can understand occluded objects through contextual reasoning and association. However, existing video object detection (VOD) methods could not work well. They treat all frames equally during feature aggregation and ignore the interdependence of objects between adjacent frames. This results in excessive noise during long-term feature alignment. To address these issues, we propose a task-specific spatiotemporal context-aware decoupling (TSCD) network, which adapts the global semantic information and local localization information needed for classification and regression tasks, respectively. Furthermore, a spatiotemporal context-aware feature matching (CAFM) module is utilized to refine the regression features while avoiding inter-frame feature mixing. Effective object associations are used to improve the regression of occluded object locations. Extensive experimental results on the ImageNet VID dataset and the OVIS dataset show that our proposed TSCD has significant advantages in occlusion scenes. The code is available at https://github.com/KaihongLi/TSCD.

Lightweight super-resolution (SR) has garnered attention for balancing performance and efficiency in resource-constrained environments. In lightweight SR tasks, traditional CNN-based methods are constrained by limited receptive fields, leading to suboptimal SR performance. In contrast, ViT-based models achieve remarkable results but suffer from significant computational burden due to the self-attention mechanism. In this paper, we propose adaptive Pixel Classification and equivalent Large Kernels Network (PCLKN), a novel lightweight SR model that addresses the limitations of traditional CNN-based and ViT-based methods. PCLKN utilizes equivalent large kernels to expand the receptive field while relying solely on convolutional operations, significantly reducing computational overhead. Additionally, it integrates global priors with spatial and channel attention to enhance feature extraction and leverages adaptive pixel classification to utilize similar pixel information for reconstruction. Experimental results on benchmark datasets demonstrate that PCLKN achieves superior SR performance with an excellent trade-off between performance and computational complexity.

Since parathyroid glands (PG) regulate the body’s calcium levels and significantly impact human health, developing methods for their automatic detection during endoscopic thyroid surgery is of utmost clinical significance. However, existing parathyroid detection works suffer from color variations, target deformation, blur, and lighting effects in intricate surgical environments. To address the above shortcomings, in this paper, we propose a novel double-layer graph attention network for PG detection, which explicitly facilitates local augmentation via key visual features (e.g., texture and shape) identification and global interactions. It can robustly combat image blur and better differentiate the PG targets and background parts, thus improving the detection precision. Furthermore, we observe most prior works fail to deeply understand the spatial relation among targets and unavoidably suffer from false or missed detection, which is heavily due to total ignorance or insufficient utilization of depth information, especially under lighting variations and occlusions. To fill the gap, we propose a depth relation augmentation component to adaptively capture the prominent relative positional relations between targets based on depth information and incorporate it into the proposed GNN framework, significantly deepening spatial understandings and naturally enhancing generalizability. Due to lacking a thyroid endoscopy surgery benchmark for evaluating this task, we meticulously established a novel dataset from 838 actual surgeries conducted (via the fully laparoscopic thoracic-breast approach) at the Fujian Medical University Union Hospital. Extensive experiments show that our framework achieves superior PG detection accuracy compared to current state-of-the-art counterparts while keeping real-time efficiency.

Obtaining pixel-accurate and topologically complete retinal vessel segmentation is challenging due to many factors, for instance, vascular structure complexity, image contrast variations, and limitations of valuable datasets. In this paper, we introduce a novel network structure that applies dual-branch: directional reweighted branch and skeletonized branch. In the direction reweighted branch, we propose adaptive directional enhancement and connectivity consistency enhancement, which can be used to extract favorable directional channel information and model the bidirectional relationship between pixels, respectively. In the skeletonized branch, we employ morphological skeletonization to align the ground truth with the predicted segmentation map. By doing that, we effectively preserve the vessel’s topological structure from a global perspective. Extensive experiments on publicly available retinal datasets DRIVE, CHASE_DB1, and STARE show that our proposed approach has achieved significant results in preserving vessel structure and accurate segmentation.

OBJECTIVE: This study aims to explore the impact of different ROI delineation strategies on the axillary lymph nodes metastasis (ALNM) prediction model by analyzing two-dimensional ultrasound images of lymph nodes. In addition, we integrated clinical and pathological information to construct a comprehensive model, and based on this model, developed a nomogram for individualized assessment of the probability of ALNM. METHODS: A total of 146 axillary lymph nodes were randomly divided into a training set and a testing set at a ratio of 8:2. Clinical and pathological features were selected using univariate and multivariate logistic regression analyses, followed by the construction of a clinical prediction model. Radiomic features were extracted from both the internal and surrounding regions of the two-dimensional ultrasound images of the axillary lymph nodes. The least absolute shrinkage and selection operator (LASSO) algorithm was then used to select and retain the optimal features, followed by the construction of a radiomic prediction model. A combined prediction model was developed by integrating the clinical and radiomic models, and a nomogram was created for the combined prediction model. RESULTS: The clinical status of axillary lymph nodes was an independent predictor for metastasis. The clinical prediction model based on the status of axillary lymph nodes achieved an AUC of 0.728 in the testing set. The radiomic prediction model based on the LASSO logistic regression algorithm with a 1 mm extended region had the highest AUC of 0.856 in the testing set. The combined prediction model integrating the clinical and optimal radiomic models achieved an AUC of 0.841 in the testing set, with a sensitivity of 77.4% and an accuracy of 79.5%. This combined model outperformed the individual clinical and radiomic models and was more effective in predicting axillary lymph node metastasis. CONCLUSION: This study developed a predictive model for ALNM based on ultrasound images of ALNs and their peripheral extended regions. The results demonstrated that the combined model incorporating both the lymph node and a 1-mm peripheral extension yielded the best predictive performance. Furthermore, a comprehensive integrated model was established by incorporating clinical and pathological characteristics, which effectively enhanced the prediction of ALNM.