Grating-based X-ray dark-field imaging leverages the small-angle scattering from porous structures, providing enhanced sensitivity to alveoli in lung parenchyma. It shows the potential of clinical application for lung disease diagnosis, and has been implemented in human-scale dark-field computed tomography (CT). One challenge in the dark-field CT is the positional dependence of the dark-field signal, which varies with rotation during a CT scan. This rotational variance limits the accuracy of conventional reconstruction methods, particularly in large field-of-view as for humans. While calibration methods have been proposed to address this issue, they are either computationally intensive or impose constraints on the scanning trajectory. In this work, we model the dark-field CT as a weighted Radon transform. By applying the analytical inversion formula to this model, we achieve the dark-field CT reconstruction without artefacts from positional dependence. This approach eliminates the requirement for conjugate ray pairs, allowing extensions from fan-beam to cone-beam geometry through coordinate transform. Simulations and experiments were conducted to validate this method using an anthropomorphic chest phantom.

Single-cell RNA sequencing (scRNA-seq) provides the transcriptome of a single cell, allowing researchers to study cellular phenomena at a higher resolution level. Nevertheless, noise generated by technical limitations and other results seriously interferes with the downstream analysis of sequencing data such as clustering. How to minimize the impact of noise on the accuracy of clustering methods has become a focus of current research. In this case, we propose a novel cell clustering algorithm called low-rank representation constrained clustering based on noise weight fusion (LRBNW). First, we mitigate the noise interference by introducing a noise weight matrix and assigning different weights to the noise through a reliability assessment strategy. By assigning larger weights to smaller reconstruction errors, we then highlight useful features with small errors, which clean features more representative in data analysis. Finally, we impose a k-block diagonal constraint on the affinity matrix through a block strategy, grouping related features into the same block, to eliminate redundancy among them and avoid over-reliance on related features. Extensive experiments demonstrate that LRBNW achieves higher accuracy results than existing state-of-the-art clustering methods on 10 real scRNA-seq datasets. In addition, downstream analysis experiments also indicated that LRBNW can identify biologically significant groups and reduce noise interference in scRNA-seq data. The result proves LRBNW is a powerful cell type identification tool, and has potential in predicting new cell types.

Super-enhancers (SEs) are clusters of enhancers with potent regulatory capabilities. They play a crucial role in shaping cellular identity and driving the progression of various diseases, including cancer. SEs exhibit significant heterogeneity across different cell types and cancer subtypes. Analysis of SE landscapes can recapitulate existing classification systems and unveil novel SE-driven epigenetic subtypes. In this review, we summarized the latest advancements in cancer subtype identification based on SE-related characteristics, outlined the typical analytical workflows adopted in such studies, and explored the biological and clinical significance of SE-driven subtypes. Furthermore, we discussed the field's key challenges and emerging technologies to highlight future research directions. SE analysis provides a robust framework for dissecting cancer heterogeneity. This approach offers novel epigenetic perspectives and support for the realization of personalized medicine.

Automated landmark localization can help radiologists quickly determine the locations of key structures or lesion areas from medical images. However, when facing large-volume 3D medical images, existing methods have very high computational complexity due to the need to encode the global image. That is to say, it is difficult for existing methods to achieve accurate landmark localization in 3D medical images at a faster localization speed. In this paper, an accurate multi-landmark localization method for ear 3D Ultra-High Resolution CT (U-HRCT) images is proposed. This method adopts a novel localization pipeline that combines Deep Reinforcement Learning (DRL) and Transformer. Firstly, the DRL algorithm is used to quickly collect landmark-related local features. Secondly, Transformer is used to extract the spatial position relationship between anatomical structures from these discrete local features to infer the coordinate position of the landmark. Because the complex process of encoding the global image is avoided, the proposed method can achieve fast localization of ear multi-landmark in 3D U-HRCT images. Finally, we proposed a refinement module based on dual-branch hybrid Multi-Layer Perceptron, which can use the fast localization results of multi-landmark to learn the spatial position relationship between landmarks, thereby further improving the accuracy and stability of landmark localization. Experimental results on the self-built ear 3D U-HRCT dataset and the publicly available 2D cephalometric dataset demonstrate that, the proposed method can achieve Successful Detection Rate of 96.71% and 89.97% respectively within the precision range of 2.0 mm, surpassing the state-of-the-art multi-landmark localization methods and has a faster localization speed.

High quality image reconstruction from undersampled k -space data is key to accelerating MR scanning. Current deep learning methods are limited by the small receptive fields in reconstruction networks, which restrict the exploitation of long-range information, and impede the mitigation of full-image artifacts, particularly in 3D reconstruction tasks. Additionally, the substantial computational demands of 3D reconstruction considerably hinder advancements in related fields. To tackle these challenges, we propose the following: 1) A novel convolution operator named Faster Fourier Convolution (FasterFC), aims at providing an adaptable broad receptive field for spatial domain reconstruction networks with fast computational speed. 2) A split-slice strategy that substantially reduces the computational load of 3D reconstruction, enabling high-resolution, multi-coil, 3D MR image reconstruction while fully utilizing inter-layer and intra-layer information. 3) A single-to-group algorithm that efficiently utilizes scan-specific and data-driven priors to enhance k -space interpolation effects. 4) A multi-stage, multi-coil, 3D fast MRI method, called the faster Fourier convolution based single-to-group network (FAS-Net), comprising a single-to-group k -space interpolation algorithm and a FasterFC-based image domain reconstruction module, significantly minimizes the computational demands of 3D reconstruction through split-slice strategy. Experimental evaluations conducted on the NYU fastMRI and Stanford MRI Data datasets reveal that the FasterFC significantly enhances the quality of both 2D and 3D reconstruction results. Moreover, FAS-Net, characterized as a method that can achieve high-resolution (320, 320, 256), multi-coil, (8 coils), 3D fast MRI, exhibits superior reconstruction performance compared to other state-of-the-art 2D and 3D methods.

Abstract Accurate vestibule segmentation for CT images is of great significance for the clinical diagnosis of congenital ear malformations and cochlear implant. However, it is still a challenging task due to extremely small size and irregular shape of vestibule. Here, a vestibule segmentation network for CT images is proposed under the basic encoder‐decoder framework. Firstly, a residual block based on channel attention mechanism, named Res‐CA block, is designed to guide the network to enhance the important features for the segmentation tasks while suppressing the irrelevant ones. And then, a global context‐aware pyramid feature extraction (GCPFE) module is proposed to capture multi‐receptive‐field global context information. Finally, active contour with elastic (ACE) loss function is adopted to guide network learning more detailed information of the boundary. Furthermore, deep supervision (DS) mechanism is employed to locate the boundaries finely, improving the robustness of the network. The experiments are conducted on the self‐established VestibuleDataset and UHRCT‐Dataset, as well as publicly available retinal dataset, namely DRIVE, to comprehensively verify the robustness and generalization capability of the proposed segmentation network. The experimental results show that the proposed network can achieve a superior performance.

Refined and automatic retinal vessel segmentation is crucial for computer-aided early diagnosis of retinopathy. However, existing methods often suffer from mis-segmentation when dealing with thin and low-contrast vessels. In this paper, a two-path retinal vessel segmentation network is proposed, namely TP-Net, which consists of three core parts, i.e., main-path, sub-path, and multi-scale feature aggregation module (MFAM). Main-path is to detect the trunk area of the retinal vessels, and the sub-path to effectively capture edge information of the retinal vessels. The prediction results of the two paths are combined by MFAM, obtaining refined segmentation of retinal vessels. In the main-path, a three-layer lightweight backbone network is elaborately designed according to the characteristics of retinal vessels, and then a global feature selection mechanism (GFSM) is proposed, which can autonomously select features that are more important for the segmentation task from the features at different layers of the network, thereby, enhancing the segmentation capability for low-contrast vessels. In the sub-path, an edge feature extraction method and an edge loss function are proposed, which can enhance the ability of the network to capture edge information and reduce the mis-segmentation of thin vessels. Finally, MFAM is proposed to fuse the prediction results of main-path and sub-path, which can remove background noises while preserving edge details, and thus, obtaining refined segmentation of retinal vessels. The proposed TP-Net has been evaluated on three public retinal vessel datasets, namely DRIVE, STARE, and CHASE DB1. The experimental results show that the TP-Net achieved a superior performance and generalization ability with fewer model parameters compared with the state-of-the-art methods.

3D medical images consist of voxels with points, edges, faces, and volumes. A fascinating question is how to compute the shortest basis of the first homology group of a 3D image. The fastest time complexity known for this question is O($n^{\omega}+n^{2}$g), where n is the size of voxels and $\omega \lt$ 2.3728639 is a quantity so that two n×n matrices can be multiplied in O($n^{\omega}$) time. But it is still slow in practical applications. We first construct a hexahedral mesh of an arbitrary domain of a 3D image and second propose an approximate algorithm with time complexity O($n^{\omega}$) to calculate the minimal homology basis for the 3D images. Experiments show that our approximate algorithm is very close to the exact algorithm. We demonstrate the effectiveness of our algorithm in segmenting the semicircular canals, the organ with complex topology.