The 3D human pose estimation algorithm has significant potential for use in the medical sector. Current research in this area primarily utilizes Vision Transformer architectures, which are generally organized into two phases: the extraction of spatial structural features from human keypoints and the analysis of temporal changes. In the past, researchers have used Graph Convolutional Networks (GCNs) to identify the relationships between various keypoints that make up the human skeletal structure or the same keypoint over time. However, a new challenge has arisen in integrating GCNs with the multi-head self-attention (MHSA) mechanism found in Vision Transformers to enhance the extraction of spatial and temporal dependency features. Additionally, existing research indicates that adding frequency domain information to Vision Transformers—particularly in time-related contexts—can lead to the extraction of more robust and comprehensive features that are less affected by noise. In light of this, we introduce the GFreFormer model, which utilizes a GCN-MHSA hybrid transformer block for the extraction of spatial and temporal features. It also incorporates traditional spatial transformer block and an enhanced Temporal-Fre Transformer block to better capture temporal features, ultimately achieving precise 3D human pose estimation results. Comprehensive experiments conducted on the Human3.6M dataset show that the GFreFormer model surpasses other existing methods.

Object detection across diverse real-world environments poses significant challenges when labeled data is scarce, particularly in privacy-sensitive scenarios such as healthcare, where data annotation is costly and access to labeled data is often restricted. In healthcare settings, robust human detection systems can enable critical applications such as patient monitoring, rehabilitation assessment, and clinical workflow optimization, yet their deployment is hindered by domain shift when models are applied to new environments. To address these challenges, this paper presents a novel unsupervised domain adaptation approach for object detection that effectively bridges the domain gap between source and target domains. Our method introduces a multi-scale sample mixing strategy guided by region-level detection confidence estimation, with the core innovation lying in our selective region mixing mechanism and multi-scale uncertainty estimation. This approach enables accurate detection of objects of varying sizes without requiring target domain annotations. Extensive experiments demonstrate that our method adapts robustly across diverse environments, offering a practical solution for deploying AI systems in scenarios where privacy concerns and annotation costs limit the availability of labeled data.

Segmenting prostate organ areas and lesion areas based on multi-modal magnetic resonance images is an important task in the medical field, and has important reference value for doctors’ subsequent diagnosis and treatment plan formulation. However, existing segmentation methods still have some shortcomings. The most important thing is that many existing methods are mostly limited to the segmentation stage of a single task, which not only wastes computing resources, but also fails to make full use of shared features between different tasks and effectively utilize the spatial and texture structures of organs and lesions. Correlation can enhance the model’s understanding of anatomical structures and improve the accuracy and consistency of segmentation results. In this paper, we propose a multi-task learning model for multi-scale feature interaction and fusion (MFAS-Net), drawing on the insights of Progressive layered extraction model(PLE). The fusion module (MMFF) realizes cross-task feature interaction and fusion, thereby making better use of shared features between organs and lesions. The multi-scale attention supervision (MAS) module is used to supervise the lesions using feature maps of organ segmentation, and finally achieves joint segmentation of prostate organs and lesions. Through comparative experiments and ablation experiments on the PI-CAI data set, our model showed significant superiority in the joint segmentation task of prostate organs and lesions, verifying its effectiveness and practicability in medical image segmentation.

Motion retargeting technology plays a vital role in fields such as computer animation, virtual reality, and gaming industries. Users can save a lot of costs in art design and animation production. However, the current motion retargeting methods still has many strict requirements. For example, some methods require the source and target skeletons need to have the same number of joints or share the same topology. In addition, we find many methods currently use the Mixamo dataset as the training set and test set, and use joint position errors optimize retargeting results, but ignore the source-target differences at the shape geometry level. This may result in interpenetration or loss of contact. Therefore, we introduce a novel framework and use evaluation metrics such as position error related to skeleton and interpenetration ratio related to shape, which makes the retargeting result more realistic.

Segmentation of brain tumors from multi-modal magnetic resonance (MR) images is a crucial task in medical imaging, with significant clinical implications for the diagnosis and treatment planning of relevant brain disorders. In this paper, we present a 3D framework, that utilizes multi-modal MR images, including T1-weighted, T1ce-weighted, T2-weighted, and FLAIR images, to capture comprehensive information about the tumor for precise and automated brain tumor segmentation. The proposed framework leverages a multi-modal MRI fusion task to facilitate the optimization and training of brain tumor segmentation. Comparative experiments have indicated the effectiveness and superiority of the proposed framework for brain tumor segmentation tasks.

High-performance deep learning models require large amounts of data with high quality annotations for model training, while the labeling work usually takes a lot of time for the experts. Meanwhile, the inter-observer variability al-ways exist between annotations from different experts and the distribution shift between the data acquired from different medical institutions. To address these challenges, we propose an end-to-end domain adaptive collaborative learning network for multi-institutional prostate MRI segmentation. Specifically, we introduce an unpaired image translation module to match the image domains between different institutions, which can alleviate the heterogeneity between 1.5T and 3T prostate MR images during model training. Moreover, we design a self-taught strategy to transfer domain-aware knowledge to jointly learn generic and unique representations. Furthermore, we evaluate our approach in scenarios with limited or without annotations, experimental results show that our approach has better adaptation performance than traditional supervised learning approaches, and has the potential to extend to unsupervised domain adaptation scenario. We also evaluate our approach with prostate MRI segmentation benchmark datasets, experimental results show that our approach outperforms several state-of-the-art methods.

Limited by the size of the dataset, deep learning models for medical image analysis are usually difficult to train well, and the complex deep learning model with large amount of trainable parameters can not achieve good results. At the same time, due to the lack of clear boundaries, especially in the root tips and roots, as well as the huge differences in shape and texture between images from different patients, an overly simple model cannot accurately segment organs. In order to improve the accuracy of organ segmentation for prostate region detection, in this paper we propose an attention based U-Net framework, which includes an attention mechanism and residual feature extraction network. In addition, we also design an improved loss function to improve the training effect for organ segmentation. We conduct several batches of experiments with the prostate dataset PROMISE12 and the pneumothorax dataset SIIM, the experimental results show that significant segmentation accuracy improvement has been achieved by our proposed method compared to other reported approaches.

Contouring prostate tumor in magnetic resonance images is a prerequisite for diagnosis. Automatically segmenting blurred lesion regions is challenging and requires fully leveraging multi-parameter MR images. This paper proposes MFSL-Net, an end-to-end network that cascades two novel sub-networks: 1) a modality fusion network that selectively fuses information of two MRI modalities by expanding a dual-stream CNN with spatial and channel attention modules; 2) a shape learning network that integrates shape learning and context learning to recognize the shape and edge information while preserving high-resolution semantic information. We justify MFSL-Net’s design by ablation experiments and compare its performance with the state-of-the-art approaches. Experimental results show a 3.6% improvement in Dice Similarity Coefficient, which confirms the effectiveness of MFSL-Net.

Participatory sensing systems can be used for concurrent event monitoring applications, like noise levels, fire, and pollutant concentrations. However, they are facing new challenges as to how to accurately detect the exact boundaries of these events, and further, to select the most appropriate participants to collect the sensing data. On the one hand, participants’ handheld smart devices are constrained with different energy conditions and sensing capabilities, and they move around with uncontrollable mobility patterns in their daily life. On the other hand, these sensing tasks are within time-varying quality-of-information (QoI) requirements and budget to afford the users’ incentive expectations. Toward this end, this article proposes an event-driven QoI-aware participatory sensing framework with energy and budget constraints. The main method of this framework is event boundary detection. For the former, a two-step heuristic solution is proposed where the coarse-grained detection step finds its approximation and the fine-grained detection step identifies the exact location. Participants are selected by explicitly considering their mobility pattern, required QoI of multiple tasks, and users’ incentive requirements, under the constraint of an aggregated task budget. Extensive experimental results, based on a real trace in Beijing, show the effectiveness and robustness of our approach, while comparing with existing schemes.