Wen Zheng

Traditional methods for measuring body composition in CT scans rely on labor-intensive manual delineation, which is time-consuming and imprecise. This study proposes a deep learning-driven framework, MCAUnet, for accurate and automated quantification of body composition and comprehensive survival analysis in cirrhotic patients. A total of 11,362 L3-level lumbar CT slices were collected to train and validate the segmentation model. The proposed model incorporates an attention mechanism from the channel perspective, enabling adaptive fusion of critical channel features. Experimental results demonstrate that our approach achieves an average Dice coefficient of 0.952 for visceral fat segmentation, significantly outperforming existing segmentation models. Based on the quantified body composition, sarcopenic visceral obesity (SVO) was defined, and an association model was developed to analyze the relationship between SVO and survival rates in cirrhotic patients. The study revealed that 3-year and 5-year survival rates of SVO patients were significantly lower than those of non-SVO patients. Regression analysis further validated the strong correlation between SVO and mortality in cirrhotic patients. In summary, the MCAUnet framework provides a novel, precise, and automated tool for body composition quantification and survival analysis in cirrhotic patients, offering potential support for clinical decision-making and personalized treatment strategies.

Accurate and automated segmentation of interstitial lung disease (ILD) lesions from CT sequence images is essential for quantitatively assessing disease progression and evaluating potential therapeutic strategies. The heterogeneity of ILD lesions and the complexity of manual annotations present significant challenges in achieving precise segmentation. Leveraging the inherent continuity of slice data in CT, where lesion shapes and locations exhibit systematic and progressive changes, we propose a deep reinforcement learning (DRL) driven weakly supervised ILD leision segmentation framework, called CT Smoother Agent (CTSA). Specifically, given an initial mask trained by an arbitrary weakly supervised network, CTSA uses the DRL algorithm to ensure the continuity of the CT sequence by changing the value of pixels in the optical flow change region, so as to obtain a optimized mask. Subsequently, CTSA uses a dual U-Net to train the constraint segmentation module based on the optimized mask and initial mask. This process is cycled to achieve the purpose of segmenting ILD lesions. The policy network and segmentation network interact to optimize ILD lesion boundaries and segmentation results simultaneously. We evaluated our model on a dataset comprising 306 ILD patients, and the proposed CTSA improves DCS by 9.3%, mIoU by 21.7%, and HD by 1.522. The experimental results show that our proposed CTSA optimization model can achieve the state-of-the-art (SOTA) performance by learning the contextual information of CT sequences. Our code has been released at: https://anonymous.4open.science/r/CT-Smoother-Agent-1E8A.

Summary: Sketching technologies have recently emerged as a promising solution for real-time, large-scale phylogenetic analysis. However, existing sketching-based phylogenetic tools exhibit drawbacks, including platform restrictions, deficiencies in tree visualization, and inherent distance estimation bias. These limitations collectively impede the overall convenience and efficiency of the analysis. In this study, we introduce Kssdtree, an interactive Python package designed to address these challenges. Kssdtree surpasses other sketching-based tools by demonstrating superior performance in terms of both accuracy and time efficiency on comprehensive benchmarking datasets. Notably, Kssdtree offers key advantages such as intra-species phylogenomic analysis and GTDB-based phylogenetic placement analysis, significantly enhancing the scope and depth of phylogenetic investigations. Through extensive evaluations and comparisons, Kssdtree stands out as an efficient and versatile method for real-time, large-scale phylogenetic analysis. Availability and implementation: The Kssdtree Python package is freely accessible at https://pypi.org/project/kssdtree and source code is available at https://github.com/yhlink/kssdtree. The documentation and instantiation for the software is available at https://kssdtree.readthedocs.io/en/latest. The video tutorial is available at https://youtu.be/_6hg59Yn-Ws.

The characterization of amorphous materials has been a long-standing challenge in materials science due to their lack of long-range order, which makes it difficult to define structural metrics. Here, we describe a 2D amorphous system-based high-precision detection model(HPDM) that utilizes the concepts of “bag” and instances to achieve image-level classification to structure-level segmentation of amorphous systems without any additional dynamical information. We introduce an order parameter that describes the structural evolution in amorphous phase transitions and demonstrate the accuracy of HPDM in detecting amorphous microstructures. A fundamental structural scale for 2D amorphous systems can be obtained based on the optimal detection dimensions of HPDM for finite-scale systems, eliminating the need to calculate structural and dynamical information. Our findings and methodology hold significant scientific implications for understanding the nature of disordered structures in amorphous materials.

Accurate and efficient 3D medical image segmentation models are critical for clinical applications. However, many models which performed well in recent years have consumed significant computational cost, especially those based on self‐attention. For more efficient and accurate segmentation of medical 3D images, we develop an efficient multiscale spatial attention model for 3D abdominal multiorgan segmentation. We use 1D and 2D kernels in the encoder and decoder modules to simulate 3D kernels to reduce the number of parameters and computational cost. Furthermore, we use the lightweight spatial attention and mixed pooling module to capture cross‐dimensional information, multiscale features, and long‐range contextual information. We achieved a Dice Similarity Coefficient (DSC) of 89.86 and a Normalized Surface Dice (NSD) of 78.2 on the FLARE dataset with only 1183 M GPU memory usage, 9 M parameters, and 193G floating point operations(FLOPs).

Comorbidities are prevalent in digestive cancers, intensifying patient discomfort and complicating prognosis. Identifying potential comorbidities and investigating their genetic connections in a systemic manner prove to be instrumental in averting additional health challenges during digestive cancer management. Here, we investigated 150 diseases across 18 categories by collecting and integrating various factors related to disease comorbidity, such as disease-associated SNPs or genes from sources like MalaCards, GWAS Catalog and UK Biobank. Through this extensive analysis, we have established an integrated pleiotropic gene set comprising 548 genes in total. Particularly, there enclosed the genes encoding major histocompatibility complex or related to antigen presentation. Additionally, we have unveiled patterns in protein-protein interactions and key hub genes/proteins including TP53, KRAS, CTNNB1 and PIK3CA, which may elucidate the co-occurrence of digestive cancers with certain diseases. These findings provide valuable insights into the molecular origins of comorbidity, offering potential avenues for patient stratification and the development of targeted therapies in clinical trials.

Accurately diagnosing chronic kidney disease requires pathologists to assess the structure of multiple tissues under different stains, a process that is timeconsuming and labor-intensive. Current AI-based methods for automatic structure assessment, like segmentation, often demand extensive manual annotation and focus on single stain domain. To address these challenges, we introduce MSMTSeg, a generative self-supervised meta-learning framework for multi-stained multi-tissue segmentation in renal biopsy whole slide images (WSIs). MSMTSeg incorporates multiple stain transform models for style translation of inter-stain domains, a self-supervision module for obtaining pre-trained models with the domain-specific feature representation, and a meta-learning strategy that leverages generated virtual data and pre-trained models to learn the domain-invariant feature representation across multiple stains, thereby enhancing segmentation performance. Experimental results demonstrate that MSMTSeg achieves superior and robust performance, with mDSC of 0.836 and mIoU of 0.718 for multiple tissues under different stains, using only one annotated training sample for each stain. Our ablation study confirms the effectiveness of each component, positioning MSMTSeg ahead of classic advanced segmentation networks, recent few-shot segmentation methods, and unsupervised domain adaptation methods. In conclusion, our proposed few-shot cross-domain technology offers a feasible and cost-effective solution for multi-stained renal histology segmentation, providing convenient assistance to pathologists in clinical practice. The source code and conditionally accessible data are available at https://github.com/SnowRain510/MSMTSeg.