Single-cell multi-omics sequencing represents an advanced technology capable of simultaneously measuring multiple omics data from the same cell. The joint clustering of single-cell multi-omics sequencing data enables a comprehensive depiction of cell states and uncovers intricate molecular mechanisms, holding immense significance in fields such as oncology, neurology, and developmental biology. However, the disparities in feature spaces across different omics layers and data noise present substantial challenges for achieving accurate clustering. To tackle these challenges, we introduce a novel clustering method for single-cell multi-omics data, termed scMSAC, which is grounded in a denoising subgraph attention autoencoder. The proposed method employs a weighted nearest neighbor graph strategy to ascertain the weights of multi-omics data, subsequently generating a similarity graph that holistically encapsulates intercellular connections through the weighted amalgamation of diverse omics perspectives. The scMSAC model captures the topological features of cells through the subgraph attention autoencoder, constructing relationships among cells. For the omics features extracted by the subgraph attention autoencoder, scMSAC incorporates an SCA (Spatial Channel Attention) mechanism for feature fusion to reduce the differences in feature spaces of different omics and achieve better clustering performance. Comparative experiments with various existing methods demonstrate that scMSAC has excellent clustering performance and performs well in detecting rare cell types and differential expression analysis.

Accurate cross-modality cardiac image segmentation is essential for effectively diagnosing and treating heart disease. Different imaging modalities help to determine suitable pre-procedure planning. However, most methods face the difficulty of spatial-temporal confounding, where the anatomy element and modality element of cardiac images are intertwined across both spatial and temporal dimensions. It is derived from the imaging diversity and structure diversity of cardiac images. The spatial-temporal confounding hinders knowledge transfer between cardiac images on different modalities. In this paper, we propose a novel dynamic causal learning (DCL) to solve spatial-temporal confounding. The DCL explores multi-dimensional causal intervention to consider not only the causal relationship between images and labels, but also the causality in time dimension and space dimension. It integrates historical optimal interventions and facilitates the transfer of this knowledge across temporal contexts. In addition, the DCL utilizes the diffusion mechanism to further ensure that the extracted anatomy element remains causal invariant, improving model performance across multiple imaging modalities. Extensive experiments on cross-modality cardiac images (MR, CT, and US) demonstrate the effectiveness of the DCL (mean Dice = 0.951), outperforming other advanced segmentation methods. DCL is freely accessible at https://github.com/asdww0721ww/DCL.

We introduce MorphMamba, a new deep learning architecture for 3D medical image segmentation that successfully adapts the efficiency of state space models to volumetric data. While standard Mamba models excel at long-sequence modeling, they fail to preserve the rich 3D spatial context of medical images due to a required data-flattening step. MorphMamba overcomes this critical limitation with a novel Mamba-based encoder designed for volumetric inputs. Our architecture integrates two key innovations: a Channel-Spatial Attention Guided module, which refines feature maps to emphasize salient anatomical information before sequential processing, and a Context Refining Block in the skip-connections to ensure optimal multi-scale feature fusion. We demonstrate the state-of-the-art performance of MorphMamba through extensive experiments on four diverse benchmarks, including BraTS 2023, LiTS 2017, a private cardiac dataset and a private prostate tumor dataset. Our model consistently achieves superior results in terms of both accuracy and boundary delineation, establishing a new and efficient baseline for 3D segmentation. Our code is available at https://github.com/haoranGeng/MorphMamba.

In a wireless device-to-device (D2D) network, mobile edge caching can reduce transmission cost for network traffic, but it may also cause outdated caching information. How to reduce the transmission cost and improve the freshness of information becomes an important issue. A dedicated caching device called helper which has a large cache can be used in a wireless D2D network, which can significantly improve the performance of network. In this paper, to better model the file-centric data transmission, we proposed a concept called age of file (AoF), which is defined as the duration from the latest updating of the file. We analyzed the AoF, energy cost and updating cost of the files in the network level. We comprehensively consider the AoF and energy cost through the maximum and minimum normalization methods, and proposed an AoF-based accessing strategy. In the strategy, users can adjust the access of files according to their demand for file freshness and improve the quality of service. The results indicate that this strategy can reduce the energy cost for file transmission and reduce the total cost of the entire network while satisfying the freshness of files.

The USGS and NASA, in conjunction with Colorado State University, George Mason University and other partners, have developed the Invasive Species Forecasting System (ISFS), a flexible tool that capitalizes on NASA's remote sensing resource to produce dynamic habitat maps of invasive terrestrial plant species across the United States. In 2006 ISFS was adopted to generate predictive invasive habitat maps to benefit noxious plant and fire management teams in three major National Park systems: The Greater Yellowstone Area (Yellowstone / Grand Tetons National Parks), Sequoia and Kings Canyon National Park, and interior Alaskan (between Denali, Gates of The Arctic and Yukon-Charley). One of the objectives of this study is to explore how the ISFS enhances decision support apparatus in use by National Park management teams. The first step with each park system was to work closely with park managers to select top-priority invasive species. Specific species were chosen for each study area based on management priorities, availability of observational data, and their potential for invasion after fire disturbances. Once focal species were selected, sources of presence/absence data were collected from previous surveys for each species in and around the Parks. Using logistic regression to couple presence/absence points with environmental data layers, the first round of ISFS habitat suitability maps were generated for each National Park system and presented during park visits over the summer of 2006. This first engagement provided a demonstration of what the park service can expect from ISFS and initiated the ongoing dialog on how the parks can best utilized the system to enhance their decisions related to invasive species control. During the park visits it was discovered that separate "expert opinion" maps would provide a valuable baseline to compare against the ISFS model output. Opinion maps are a means of spatially representing qualitative knowledge into a quantitative two-dimensional map. Furthermore, our approach combines the qualitative expert opinion habitat maps with the quantitative ISFS habitat maps in a difference map that shows where the two maps agree and disagree. The objective of the difference map is to help focus future field sampling and improve model results. This paper presents a demonstration of the habitat, expert opinion, and difference map for Yellowstone National Park.