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.

It is challenging to detect 3D objects from noise point clouds by Graph Neural Networks (GNNs), though graph-based methods have shown promising results in 3D classifications. Since strong robustness against noise is offered by hypergraph, a relative paradigm named HyperGraph Construction-Compression-Conversion (HG3C) is proposed for detecting 3D objects from noise point clouds. Our method presents the capacity of reducing graph redundancy and capturing the variances from multiple features, by pre-encoding the graph, to improve the graph representations in point clouds. A fused graph neural network is further designed to predict the shape and category of the target in converted graphs. The experiments, on both the KITTI and Nuscene, show that the proposed approach achieves leading accuracy. Our results demonstrate the potential of using the hypergraph transformation to extract and compress point cloud information from noisy point clouds.

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.

Abstract Retinal vessel segmentation is fundamental for the automatic retinal image analysis and ocular disease screening. This paper aims to learn a ground truth free feature aggregation strategy for the vessel segmentation. Five vesselness maps modelling the vessels'profile, appearance, and shape are first generated. Together, the histogram of the local binary pattern and the green colour are extracted. In each vesselness map, the pixels with large vesselness values are regarded as simple positive samples. The pixels with small vesselness values are regarded as simple negative samples, and the pixels with mediocre values are treated as difficult pixels. The simple positive samples and simple negative samples near the difficult pixels consist of the training dataset while the rest vesselness maps together with the local binary pattern histogram, and green colour channel are used as the features to learn a strong classifier. Then, without leveraging any ground truth, multiple kernel boosting is used to combine four support vector machine kernels to learn a strong vessel model for each image. Applying this learnt model to the pixels with mediocre values in the single vesselness map, their label will be determined. Totally, five strong vessel models are learnt. Finally, pixels with the majority supports from the strong vessel models are labelled as vessel pixels. The proposed method achieves accuracy of 94.83%, sensitivity of 72.59%, and specificity of 98.11% on DRIVE dataset, and accuracy of 95.51%, sensitivity of 78.09%, and specificity of 97.56% on STARE. It outperforms the state‐of‐the‐art unsupervised methods and achieves comparable performances to the supervised methods.

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The Cup-to-Disc Ratio (CDR) serves as the most important indicator for glaucoma screening and plays a significant role in clinical screening and early diagnosis of glaucoma. In general, obtaining CDR is subjected to measuring on manually or automatically segmented optic disc and cup. Despite great efforts have been devoted, obtaining CDR values automatically with high accuracy and robustness is still a great challenge due to the heavy overlap between optic cup and neuroretinal rim regions. In this paper, a direct CDR estimation method is proposed based on the well-designed semi-supervised learning scheme, in which CDR estimation is formulated as a general regression problem while optic disc/cup segmentation is cancelled. The method directly regresses CDR value based on the feature representation of optic nerve head via deep learning technique while bypassing intermediate segmentation. The scheme is a two-stage cascaded approach comprised of two phases: unsupervised feature representation of fundus image with a convolutional neural networks (MFPPNet) and CDR value regression by random forest regressor. The proposed scheme is validated on the challenging glaucoma dataset Direct-CSU and public ORIGA, and the experimental results demonstrate that our method can achieve a lower average CDR error of 0.0563 and a higher correlation of around 0.726 with measurement before manual segmentation of optic disc/cup by human experts. Our estimated CDR values are also tested for glaucoma screening, which achieves the areas under curve of 0.905 on dataset of 421 fundus images. The experiments show that the proposed method is capable of state-of-the-art CDR estimation and satisfactory glaucoma screening with calculated CDR value.

Evidence identification, optic disc segmentation and automated glaucoma diagnosis are the most clinically significant tasks for clinicians to assess fundus images. However, delivering the three tasks simultaneously is extremely challenging due to the high variability of fundus structure and lack of datasets with complete annotations. In this paper, we propose an innovative Weakly-Supervised Multi-Task Learning method (WSMTL) for accurate evidence identification, optic disc segmentation and automated glaucoma diagnosis. The WSMTL method only uses weak-label data with binary diagnostic labels (normal/glaucoma) for training, while obtains pixel-level segmentation mask and diagnosis for testing. The WSMTL is constituted by a skip and densely connected CNN to capture multi-scale discriminative representation of fundus structure; a well-designed pyramid integration structure to generate high-resolution evidence map for evidence identification, in which the pixels with higher value represent higher confidence to highlight the abnormalities; a constrained clustering branch for optic disc segmentation; and a fully-connected discriminator for automated glaucoma diagnosis. Experimental results show that our proposed WSMTL effectively and simultaneously delivers evidence identification, optic disc segmentation (89.6% TP Dice), and accurate glaucoma diagnosis (92.4% AUC). This endows our WSMTL a great potential for the effective clinical assessment of glaucoma.

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.

Changes of retinal blood vessel are precursors of many serious diseases such as diabetic retinopathy, hypertension and cardiovascular diseases. Automatic segmentation of retinal blood vessels in the fundus image can better assist in the diagnosis of these diseases and has been studied by many researchers. However, the segmentation of pale vessel pixels remains a problem because of their low contrasts with surrounding pixels. This study proposes an improved multi‐scale line detector to segment retinal vessels. It computes the line responses of vessels in multi‐scale windows and takes the maximum as the response value, which can enhance the responses of pale vessel pixels near strong vessels or dark background pixels. Experimental results on the publicly available database DRIVE demonstrate that the proposed method can detect pale vessel pixels better. It achieves 75.28% in sensitivity and 94.47% in accuracy, which outperforms the state‐of‐the‐art unsupervised methods. Compared with the supervised methods it also gets better sensitivity and comparable accuracy.

Most existing salient object detection methods compute the saliency for pixels, patches, or superpixels by contrast. Such fine-grained contrast-based salient object detection methods are stuck with saliency attenuation of the salient object and saliency overestimation of the background when the image is complicated. To better compute the saliency for complicated images, we propose a hierarchical contour closure-based holistic salient object detection method, in which two saliency cues, i.e., closure completeness and closure reliability, are thoroughly exploited. The former pops out the holistic homogeneous regions bounded by completely closed outer contours, and the latter highlights the holistic homogeneous regions bounded by averagely highly reliable outer contours. Accordingly, we propose two computational schemes to compute the corresponding saliency maps in a hierarchical segmentation space. Finally, we propose a framework to combine the two saliency maps, obtaining the final saliency map. Experimental results on three publicly available datasets show that even each single saliency map is able to reach the state-of-the-art performance. Furthermore, our framework, which combines two saliency maps, outperforms the state of the arts. Additionally, we show that the proposed framework can be easily used to extend existing methods and further improve their performances substantially.