Magnetic Resonance Imaging (MRI) and its automatic segmentation are pivotal in assisting physicians with clinical diagnosis. In recent years, with the scarcity of labeled data, significant advancements have been made in semi-supervised segmentation. However, the prediction of many current methods is affected by the presence of false positive regions, which limits their reliability in clinical applications. To tackle this issue, we propose a pseudo-label optimization method based on polar coordinate modeling and prior constraints (PMPC), which refines false positive regions in pseudo-labels by leveraging prior knowledge within the polar coordinate system. Firstly, to improve the efficiency and rationality during polar coordinate modeling, the Adaptive Pole Selection (APS) algorithm is presented to ensure that the pole is located within the foreground region. Secondly, to mitigate false positive regions in pseudo-labels that violate medical anatomical priors, we propose the Prior Knowledge Constraint in Polar Coordinate System (KCP) module to reassign pixel categories in these regions. Finally, the Shape-aware Weighting (SaW) strategy is presented to evaluate the quality of the optimized pseudo-labels based on their shape and then determine their weight in guiding network parameter updates. Experiments on three MRI datasets demonstrate that the proposed method can be effectively integrated with existing pelvic MRI segmentation approaches, significantly reducing false positive rates and further improving segmentation quality.

Neural Radiance Fields (NeRF) have demonstrated impressive novel view synthesis capabilities but suffer from slow training and limitations in representational capacity, leading to artifacts and blurring. Consequently, balancing quality and efficiency remains a significant challenge. In this paper, we present DB-NeRF, a novel dual-branch representation for neural radiance fields, which achieves high-fidelity rendering results with detailed textures while enabling fast training. The key of the proposed method is to utilize effective encoding to represent the density and color fields separately. Specifically, we propose a multi-dimensional spatial perception encoding (MSPE) to fuse the multi-dimensional spatial information, enabling the model to quickly and accurately reconstruct scene geometry. Concurrently, a multi-level spherical harmonics prediction head (MSH) is designed to explicitly embed direction information, reducing directional ambiguity and improving rendering quality. Extensive experiments on three datasets demonstrate that our method achieves better rendering quality within the same training time compared to previous state-of-the-art methods.

Semi-Supervised medical image segmentation is crucial for clinical applications. Recent methods tend to adopt the weak-to-strong consistency strategy to boost model performance. However, these approaches predominantly emphasize spatial domain perturbations, restricting the expansion of the perturbation space. Additionally, reliance on the confidence threshold for pseudo-label selection frequently neglects noisy pixels with high confidence, leading to their accumulation and degradation of model performance. To address these challenges, we propose the Adaptive Wavelet and Uncertainty Refinement (AWUR) framework, incorporating two modules: (1) Adaptive Wavelet Perturbation (AWP), which employs wavelet transform and adaptive noise to introduce gentle frequency perturbations, effectively broadening the original perturbation space and enhancing model performance; (2) Uncertainty Weight Refinement (UWR), which refines high-uncertainty pixels and adjusts pseudo-label weights based on confidence and uncertainty, effectively improving pseudo-label reliability and guiding model training. Extensive experiments show that AWUR surpasses state-of-the-art methods across various medical image segmentation tasks.

In many image-guided clinical approaches, tumor segmentation is a fundamental and critical step for locating tumor involvement. However, the scarcity of annotated data and the low contrast of medical imaging techniques make it challenging to accurately segment tumors from surrounding tissues using supervised learning methods. To address these issues, we propose a patch-based contrastive semi-supervised learning framework with wavelet guidance and adaptive data augmentation (PaCaS-WAA). Specifically, we apply patch-based contrast to maintain high-quality segmentation results with limited labels. Moreover, to exploit the discriminative information about subtle boundaries, we use the wavelet domain guides UNet for more edge details. Besides, to increase the diversity of unlabelled data, we propose an adaptive data augmentation strategy to augment the unlabelled data according to its Challenging Grade. Experimental results on two publicly available datasets of different modalities demonstrate that our method consistently outperform the state-of-the-art semi-supervised segmentation methods.

Monitoring the progress of diabetic macular ischemia (DMI) is essential for providing timely and effective treatment plans and prognostic evaluations. Many approaches have recently been proposed for quantifying DMI based on optical coherence tomography angiography (OCTA) images. However, none of the existing methods can effectively segment the damaged foveal avascular zone (FAZ) and blood vessels (BV) of DMI patients. To avoid this disadvantage, this study proposes a DMI grading framework, i.e. FAZ-BV, combining accurate FAZ and vessel segmentation designed for DMI. For FAZ segmentation, we propose a FAZ attention network, namely FA-Net, coupled with residual fusion attention block (RFAB). For vessel segmentation, Frangi filter and multi-scale line detector can effectively highlight vessel pixels without annotations. The selection of FAZ and BV features follows the doctors’ logic of diagnosing DMI. Hybrid features are fused to build a FAZ-BV grading model for DMI. We evaluate our proposed method on a newly collected dataset with 107 eyes. Experimental results show that FA-Net surpasses state-of-the-art segmentation methods with a 95.81% Dice score, an increase of 1.61% compared with U-Net. Our framework achieves encouraging grading performance with a 0.92 AUC, which indicates that the proposed framework is of potential clinical value in DMI grading.

Color fundus (CF) image registration is crucial for accurate information fusion; it could obtain more details of retinal structure to assist clinical diagnosis. Existing methods suf-fer from costing time or dataset size, making CF image reg-istration still a challenging task. In this paper, we propose a novel pair-metamorphosis-decouple synthetic data scheme for learning-based CF image registration and ameliorate the registration model for retinal image. Specifically, we take ad-vantage of the pairing information of the registration task to decouple the differences between the pairing data and expand the representative ability of the dataset by synthesizing data. Furthermore, the registration framework is ameliorated ac-cording to the characteristics of the blood vessels in the retinal image. Experiments on the public dataset (FIRE) show that our synthetic data scheme could bring general performance promotion to registration models, and our registration method is superior to other state-of-the-art unsupervised algorithms.

Age‐related macular degeneration (AMD) is a common eye disease that causes progressive degeneration of the central vision. The presence of abundant drusen is a common early feature of AMD. Optical coherence tomography (OCT) can provide detailed structure information on drusen. The physiological structure of the retinal epithelium and drusen complex (RPEDC) and the Bruch's membrane (BM) layer boundaries will be influenced by the presence of drusen with AMD. Therefore, drusen quantification is important to diagnose and cure AMD. The authors proposed an automatic method to segment the inner limiting membrane, the retinal pigment epithelium and drusen complex (RPEDC) and BM layer boundaries from OCT images with AMD (termed as deep forest for layer segmentation (DF‐LS)). In their method, image patches are extracted and used to train a deep‐forest model to predict three boundary probability maps. In addition, they modify grapy theory and dynamic programming method to find the layer boundary. Finally, the layer boundary is smoothed by using a smoothing operation. The proposed DF‐LS method is evaluated on three publicly available datasets (one healthy dataset and two AMD dataset). The proposed DF‐LS method can yield superior mean unsigned error with an average error of 0.81 pixel on Tian et al .'s dataset, and 1.35, 1.23 pixel on Chiu et al .'s and Farisu et al .'s dataset, respectively.

In wireless sensor networks (WSNs), many applications require a high reliability for the sensing data forwarding to sink. Due to the lossy nature of wireless channels, achieving reliable communication through multihop forwarding can be very challenging. Broadcast technology is an effective way to improve the communication reliability so that the data can be received by multiple receiver nodes. As long as the data of any one of the receiver nodes is transmitted to the sink, the data can be transmitted successfully. In this paper, a cross‐layer optimization protocol named Adaptive transmission Power control based Reliable data Forwarding (APRF) scheme by using broadcast technology is proposed to improve the reliability of network and reduce communication delay. The main contributions of this paper are as follows: (1) for general data aggregation sensor networks, through the theoretical analysis, the energy consumption characteristics of the network are obtained. (2) According to the case that the energy consumption of near‐sink area is high and that in far‐sink area is low, a cross‐layer optimization method is adopted, which can effectively improve the data communication by increasing the transmission power of the remaining energy nodes. (3) Since the reliability of communication is improved by increasing the transmission power of the node, the number of retransmissions of the data packet is reduced, so that the delay of the packet reaching the sink node is reduced. The theoretical and experimental results show that, applying APRF scheme under initial transmission power of 0 dBm, although the lifetime dropped by 13.77%, delay could be reduced by 40.37%, network reliability could be reduced by 10.08%, and volume of data arriving at sink increased by 10.08% compared with retransmission‐only mechanism.