Spatial transcriptomics provides a multi-modal perspective by simultaneously capturing gene expression profiles, spatial coordinates, and histological images. While existing methods focus on maintaining view consistency to handle distribution shifts, they frequently neglect semantic conflicts introduced by distorted views-a common limitation arising from technical data acquisition and processing constraints. These conflicts lead to distorted consensus representations. To address this challenge, we propose Holistic Invariant RetrAcing for mitigating representation distortion (HiraST). Our framework explicitly corrects distorted multi-view representations through two complementary mechanisms: 1) Cross-view invariant retracing, which jointly aligns instance-level features and pseudo-label distributions to retrace invariant information. This dual alignment ensures that semantically similar cells or tissue regions remain consistent across heterogeneous modalities, even in the presence of acquisition-induced distortions; and 2) holistic prototype learning, which leverages low-frequency structural components to recalibrate corrupted views and enhance robustness against noise. Extensive experiments on spatial transcriptomics datasets and incomplete multi-view clustering benchmarks demonstrate our framework's state-of-the-art performance. Meanwhile, HiraST demonstrates strong capability across various downstream tasks. The demo code of this work is publicly available at https://github.com/hexiao0275/HiraST.

The Segment Anything Model (SAM) has attracted considerable attention due to its impressive performance and demonstrates potential in medical image segmentation. Compared to SAM's native point andbounding box prompts, text prompts offer a simpler and more efficient alternative in the medical field, yet this approach remains relatively underexplored. In this paper, we propose a SAM-based framework that integrates a pre-trained vision-language model to generate referring prompts, with SAM handling the segmentation task. The outputs from multimodal models such as CLIP serve as input to SAM's prompt encoder. A critical challenge stems from the inherent complexity of medical text descriptions: they typically encompass anatomical characteristics, imaging modalities, and diagnostic priorities, resulting in information redundancy and semantic ambiguity. To address this, we propose a text decomposition-recomposition strategy. First, clinical narratives are parsed into atomic semantic units (appearance, location, pathology, and so on). These elements are then recombined into optimized text expressions. We employ a cross-attention module among multiple texts to interact with the joint features, ensuring that the model focuses on features corresponding to effective descriptions. To validate the effectiveness of our method, we conducted experiments on several datasets. Compared to the native SAM based on geometric prompts, our model shows improved performance and usability.

The rapid and accurate direct multi-frame interpolation method for Digital Subtraction Angiography (DSA) images is crucial for reducing radiation and providing real-time assistance to physicians for precise diagnostics and treatment. DSA images contain complex vascular structures and various motions. Applying natural scene Video Frame Interpolation (VFI) methods results in motion artifacts, structural dissipation, and blurriness. Recently, MoSt-DSA has specifically addressed these issues for the first time and achieved SOTA results. However, MoSt-DSA's focus on real-time performance leads to insufficient suppression of high-frequency noise and incomplete filtering of low-frequency noise in the generated images. To address these issues within the same computational time scale, we propose GaraMoSt. Specifically, we optimize the network pipeline with a parallel design and propose a module named MG-MSFE. MG-MSFE extracts frame-relative motion and structural features at various granularities in a fully convolutional parallel manner and supports independent, flexible adjustment of context-aware granularity at different scales, thus enhancing computational efficiency and accuracy. Extensive experiments demonstrate that GaraMoSt achieves the SOTA performance in accuracy, robustness, visual effects, and noise suppression, comprehensively surpassing MoSt-DSA and other natural scene VFI methods.

Continual learning for large language models (LLMs) demands a precise balance between $\textbf{plasticity}$ - the ability to absorb new tasks - and $\textbf{stability}$ - the preservation of previously learned knowledge. Conventional rehearsal methods, which replay stored examples, are limited by long-term data inaccessibility; earlier pseudo-rehearsal methods require additional generation modules, while self-synthesis approaches often generate samples that poorly align with real tasks, suffer from unstable outputs, and ignore task relationships. We present $\textbf{\textit{Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity}}(\textbf{SERS})$, a lightweight framework that 1) decouples pseudo-input synthesis from label creation, using semantic masking and template guidance to produce diverse, task-relevant prompts without extra modules; 2) applies label self-evolution, blending base-model priors with fine-tuned outputs to prevent over-specialization; and 3) introduces a dynamic regularizer driven by the Wasserstein distance between task distributions, automatically relaxing or strengthening constraints in proportion to task similarity. Experiments across diverse tasks on different LLMs show that our SERS reduces forgetting by over 2\% points against strong pseudo-rehearsal baselines, by ensuring efficient data utilization and wisely transferring knowledge. The code will be released at https://github.com/JerryWangJun/LLM_CL_SERS/.

Accurately identifying and classifying protein active sites is crucial for understanding protein mechanisms, drug design, and synthetic biology. Current methods often rely on binary classification and single-modal data, limiting their scope. To address these limitations, we propose M$^{3}$Site, a multimodal framework that integrates protein sequence embeddings, structural graph representations, and functional text annotations for residue-level, multiclass active site prediction. Built upon a curated dataset of 25 883 proteins sourced from UniProt and AlphaFold2, M$^{3}$Site leverages pretrained protein language models, equivariant graph neural networks, and biomedical language models for feature extraction. The function informed cross-attention module enables cross-modal feature fusion, while the adaptive weighted fusion mechanism balances modality contributions. A compound loss function tackles class imbalance, ensuring robust performance. Experimental results show M$^{3}$Site significantly outperforms existing models, and an interactive application has been developed to enhance its practical utility for predictions and visualizations. The dataset, source code for experiments, and interactive application are publicly available at https://github.com/Gift-OYS/M3Site.

Consistent perturbation strategies have emerged as a dominant paradigm in semi-supervised medical image segmentation. Nevertheless, prevailing approaches inadequately address two critical challenges: 1) prediction errors induced by data uncertainty from distribution shifts, and 2) loss instability caused by model uncertainty in parameter generalization. To overcome these limitations, we propose an Uncertainty-Guided Adaptive Correction (UGAC) framework with three key innovations. First, we develop a dual-path uncertainty rectification mechanism that employs normalized entropy measures to detect error-prone regions in unlabeled predictions, followed by bilateral correction through confidence-weighted fusion. Second, we introduce adversarial consistency constraints that leverage labeled data to discriminate authentic segmentation patterns, effectively regularizing uncertainty propagation in unlabeled predictions through spectral normalization. Third, we architect a frequency-aware segmentation backbone through our novel Freqfusion module, which performs adaptive spectral decomposition during feature decoding to explicitly disentangle high-frequency (boundary-aware) and low-frequency (structural) components, thereby enhancing anatomical boundary sensitivity. Comprehensive evaluations on MM-WHS, BUSI, M&Ms and PROMISE12 datasets demonstrate UGAC's superior performance. The proposed framework exhibits robust generalizability across CT, MRI, and ultrasound modalities, while achieving significantly lower computational complexity than baseline UNet implementations. The code will be available at https://github.com/SIGMACX/UGAC.

Four-dimensional Digital Subtraction Angiography (4D DSA) is a medical imaging technique that provides a series of 2D images captured at different stages and angles during the process of contrast agent filling blood vessels. It plays a significant role in the diagnosis of cerebrovascular diseases. Improving the rendering quality and speed under sparse sampling is important for observing the status and location of lesions. The current methods exhibit inadequate rendering quality in sparse views and suffer from slow rendering speed. To overcome these limitations, we propose TOGS, a Gaussian splatting method with opacity offset over time, which can effectively improve the rendering quality and speed of 4D DSA. We introduce an opacity offset table for each Gaussian to model the opacity offsets of the Gaussian, using these opacity-varying Gaussians to model the temporal variations in the radiance of the contrast agent. By interpolating the opacity offset table, the opacity variation of the Gaussian at different time points can be determined. This enables us to render the 2D DSA image at that specific moment. Additionally, we introduced a Smooth loss term in the loss function to mitigate overfitting issues that may arise in the model when dealing with sparse view scenarios. During the training phase, we randomly prune Gaussians, thereby reducing the storage overhead of the model. The experimental results demonstrate that compared to previous methods, this model achieves state-of-the-art render quality under the same number of training views. Additionally, it enables real-time rendering while maintaining low storage overhead.

Artificial intelligence has become a crucial tool for medical image analysis. As an advanced cerebral angiography technique, Digital Subtraction Angiography (DSA) poses a challenge where the radiation dose to humans is proportional to the image count. By reducing images and using AI interpolation instead, the radiation can be cut significantly. However, DSA images present more complex motion and structural features than natural scenes, making interpolation more challenging. We propose MoSt-DSA, the first work that uses deep learning for DSA frame interpolation. Unlike natural scene Video Frame Interpolation (VFI) methods that extract unclear or coarse-grained features, we devise a general module that models motion and structural context interactions between frames in an efficient full convolution manner by adjusting optimal context range and transforming contexts into linear functions. Benefiting from this, MoSt-DSA is also the first method that directly achieves any number of interpolations at any time steps with just one forward pass during both training and testing. We conduct extensive comparisons with 7 representative VFI models for interpolating 1 to 3 frames, MoSt-DSA demonstrates robust results across 470 DSA image sequences (each typically 152 images), with average SSIM over 0.93, average PSNR over 38 (standard deviations of less than 0.030 and 3.6, respectively), comprehensively achieving state-of-the-art performance in accuracy, speed, visual effect, and memory usage. Our code is available at https://github.com/ZyoungXu/MoSt-DSA.

In this paper, we are proposing a novel motion correction algorithm for high-resolution OR-PAM imaging. Our algorithm combines a modified demons-based tracking approach with a newly developed multi-scale vascular feature matching method to track motion between adjacent B-scan images without needing any reference object. We first applied this algorithm to correct motion artifacts within one three-dimensional (3D) data segment of rat iris obtained with OR-PAM imaging. We then extended the application of this algorithm to correct motions to obtain vasculature imaging in the whole mouse back. In here, we stitched five adjacent 3D data segments (large field-of-view) obtained while changing the focus of OR-PAM differently for each subarea. The results showed that the motion artifacts of both large blood vessels and microvessels could be accurately corrected in both cases. Compared to the manually stitching method and the traditional SIFT algorithm, the algorithm proposed in this paper has better performance in stitching adjacent data segments. The high accuracy of the motion correction algorithm makes it valuable in OR-PAM for high-resolution imaging of large animals and for quantitative functional imaging.