Ningfeng Que | Searcharxiv

arXiv2026

CoInS-Net: A Continuous Position-Aware Network for Joint Medical Image Interpolation and Segmentation

Accurate medical image interpolation and anatomical structure segmentation are fundamental for computer-aided diagnosis and treatment planning. Anisotropic medical volumes with sparse through-plane sampling often suffer from structural discontinuity and boundary blur, hindering reliable clinical image analysis. Most existing methods implement interpolation and segmentation independently, which introduces redundant computation and fails to fully exploit complementary cross-slice structural information between sequential slices. To address these issues, we propose a continuous position-aware interaction network, termed CoInS-Net, for joint frame interpolation and lesion segmentation. Unlike conventional cascaded interpolation-then-segmentation paradigms, the framework enables bidirectional interaction under a shared Swin encoder with continuous spatial coordinate queries. A spatially continuous position interpolation module generates target-position features at every scale from the relative coordinate and physical spacing, and a prototype-based task mutual interaction module lets the segmentation and interpolation branches exchange global structure through a small set of shared prototypes rather than dense feature mixing. A multi-scale task-cooperative decoder further separates each scale into shared and task-specific components, so the two tasks reinforce common anatomy while preserving their distinct requirements down to the boundary level, without extra annotations. Experiments on four public medical imaging datasets with diverse modalities and anatomical regions demonstrate that the proposed method outperforms conventional single-task schemes. The joint optimization framework effectively realizes mutual promotion between interpolation and segmentation tasks, providing a reliable and universal technical scheme for intelligent clinical medical image analysis.

cs.CV↗

arXiv2026

StateXDiff: Cell State-Contextualized Multimodal Diffusion for Single-Cell Perturbation Prediction

Predicting drug-induced cellular state changes at single-cell resolution remains a central challenge in virtual cell modeling, particularly under out-of-distribution (OOD) conditions. Current approaches predominantly rely on RNA-based assays, which often fail to adequately capture the diverse cellular states underlying drug responses. Moreover, conditional distribution shifts and low signal-to-noise ratios frequently cause models to learn spurious correlations rather than genuine state transitions. To address these limitations, we introduce StateXDiff, a cell State-contextualized multimodal (X) Diffusion framework for predicting single-cell responses to drug perturbations. The framework operates sequentially: first, it learns a disentangled, multimodal representation of cellular state by integrating transcriptomic profiles with inferred protein features; second, it employs a conditional diffusion model to generate perturbation-specific changes. Our approach introduces a Virtual Multimodal Cell State, which augments RNA-based representations with protein-level context, and a Mechanism-aware Drug-Gene Template, which consolidates multi-source biological knowledge for accurate drug representation. Generation is driven by a latent-space diffusion Transformer, regularized through quality-aware triplet constraints, including positive drug-protein pairs or protein-drug mismatched pairs, and explicit protein-reliability weighting. Extensive evaluation demonstrates that StateXDiff consistently enhances generalization performance across three challenging settings: unseen cell lines, unseen drugs, and combinatorial perturbations.

q-bio.GN↗