Virtual Immunohistochemistry (IHC) staining technology employs generative models to directly synthesize IHC images from Hematoxylin and Eosin (H&E) images, reducing reliance on chemical staining while improving diagnostic efficiency and reducing costs. However, existing virtual staining methods relying on adjacent sections face two critical challenges: insufficient mining of pathological semantics and the spatial misalignment of pathological semantics due to physical discrepancies between sections. To address these, we propose GSGStain, a Graph-Semantic Guided Learning for virtual Staining. Our method innovatively transforms the problem from pixel space to graph space, enabling semantic noise correction for spatial misalignment features. Specifically, to capture the rich pathological semantics, we construct a cell graph from the H&E image to encode tissue architecture, annotating nodes with noisy biomarker semantic features derived from misaligned adjacent IHC sections. Furthermore, to correct for the semantic misalignment, a Graph Semantic Rectification Module (GSRM) then refines these features using graph contextual reasoning, while a Graph Semantic Consistency Loss ensures alignment between generated IHC images and rectified semantics. Additionally, we propose a dual-branch discriminator to compel the generator to match the empirical distribution of real images, significantly improving generation quality. Extensive experiments on two public benchmarks demonstrate that GSGStain significantly outperforms state-of-the-art methods in both image quality and pathological consistency. This work establishes a new paradigm for semantically robust virtual staining.

Spatial domain identification is a central task in spatial transcriptomics (ST) data analysis. We present GDST, a novel graph contrastive learning framework that leverages graph diffusion to enhance spatial domain delineation in ST data. In contrast to prior approaches based on random perturbations or masking strategies, GDST introduces biologically inspired diffusion augmentation to simulate intercellular signal propagation while preserving the intrinsic topological structure of the spatial graph. To further reduce noise from irrelevant neighbors, a graph attention mechanism is incorporated to enable adaptive neighborhood aggregation. Extensive evaluations on five benchmark ST datasets spanning three experimental platforms demonstrate that GDST consistently outperforms several state-of-the-art deep learning models in spatial domain identification.

Accurate polyp segmentation is crucial for early diagnosis and treatment of colorectal cancer. Due to boundary ambiguity and uncertainty within lesions, achieving precise segmentation remains a significant challenge. Uncertainty modeling has emerged as a promising approach to address ambiguous and error-prone lesion regions, but existing methods still face two major limitations:(1) insufficient handling of semantic ambiguity within lesions; (2) fixed inference mechanisms that struggle with complex polyp structures. To address these challenges, we propose RUNet, an innovative polyp segmentation framework that integrates signal response mechanisms with confidenceaware learning. First, we design a multi-signal response (MSR) module, which leverages the signal response (SR) mechanism for multisource feature extraction between foreground and background, along with the compensatory enhancement module (CEM) to enhance weakly responsive regions, significantly improving feature completeness in ambiguous regions. Second, we introduce a confidence-aware strategy that dynamically focuses on guiding the learning of hard pixels in boundary regions, effectively reducing uncertainty and enabling precise boundary delineation. Extensive experiments on five public datasets demonstrate that our proposed RUNet outperforms state-of-theart methods in both segmentation accuracy and generalization capability, providing a robust solution for clinical early diagnosis of colorectal cancer.

Cell segmentation is critical for early cervical cancer screening, yet it faces challenges inherent in cervical cell images, such as cell occlusion and scale diversity. In this paper we proposed an innovative cell image segmentation framework called ACNet. This framework employs an Easy-to-Difficult Indirect Decoupling Strategy (EDS), combined with a Feature Refinement Module (FRM), to improve the model’s perception of occluded instances and invisible regions. Additionally, we designed a Squeeze-and-Excitation Module (SEM) and a Point Supervision Module (PSM) to improve the model’s ability to capture features of larger occluded cells and smaller cells in low-contrast images, respectively. We verified our method using two occlusion cytology image segmentation datasets, and compared it with state of the art segmentation methods. ACNet achieved superior segmentation results on cervical cell images with cell occlusion and scale diversity. This study provides an important driving force for early screening for cervical cancer.

Immunohistochemistry (IHC) staining provides precise localization and qualitative analysis for tumor diagnosis, while its application is often constrained by complexity and high costs. Recently, many researchers have employed virtual staining based on deep learning to translate hematoxylin and eosin (H&E) images into IHC images, presenting a more efficient and cost-effective alternative. However, these methods usually rely on Generative Adversarial Networks (GANs), which are prone to various issues such as mode collapse, thereby limiting the effectiveness. To address this issue, we propose a weakly supervised virtual staining method based on the Schrödinger bridge called StainSB. This method establishes an optimal random process between the source and target distributions, effectively translating H&E images into IHC images. Specifically, we design a regional color state loss to model the pathological similarity between the generated and real IHC images, thereby incorporating pathological information into the generation process. Furthermore, the proposed aggregation strategy enables the generated images to achieve a balance between image quality and pathological consistency. Extensive experiments on two public benchmark datasets show that the proposed StainSB method achieves state-of-the-art performance across multiple metrics.

This research presents a music theory-inspired acoustic representation (hereafter, MTAR) to address improved speech emotion recognition. The recognition of emotion in speech and music is developed in parallel, yet a relatively limited understanding of MTAR for interpreting speech emotions is involved. In the present study, we use music theory to study representative acoustics associated with emotion in speech from vocal emotion expressions and auditory emotion perception domains. In experiments assessing the role and effectiveness of the proposed representation in classifying discrete emotion categories and predicting continuous emotion dimensions, it shows promising performance compared with extensively used features for emotion recognition based on the spectrogram, Mel-spectrogram, Mel-frequency cepstral coefficients, VGGish, and the large baseline feature sets of the INTERSPEECH challenges. This proposal opens up a novel research avenue in developing a computational acoustic representation of speech emotion via music theory.

Based on the Threshold Predicate Encryption (TPE), the biometric authentication schemePassBioaims to correctly authenticate genuine end-users without leaking their biometric privacy information. However, this article proposes two impersonation attacks toPassBioby merely sending very few query messages. Specifically, an attacker is able to cheat the authentication server with probability 50% by sending the server a random query, or almost 100% by sending the server a collusion of old genuine queries, without being identified. Moreover, in order to defeat the impersonation attacks, this article presents a Verifiable Threshold Predicate Encryption (VTPE) scheme which includes three components: (1) a multi-segment TPE for reducing the computational cost and communication overhead significantly; (2) a segment-wise watermarking for defeating the random attacks; and (3) a challenge-response mechanism for defeating the replay and collusion attacks. In addition, the watermarking also creates a secure channel between the querying user and the server. The experiments on both simulated feature vectors and real face images demonstrate that the present attacks and countermeasures are effective and efficient.

Functional brain network (FBN) is becoming an increasingly important measurement for exploring cerebral mechanisms and mining informative biomarkers that assist diagnosis of some neurodegenerative disorders. Despite its effectiveness to discover valuable hidden patterns in the human brain, the estimated FBNs are often heavily influenced by the quality of the observed data (e.g., blood oxygen level dependent signal series). In practice, a preprocessing pipeline is usually employed for improving data quality. With this in mind, some data points (volumes or time course in the time series) are still not clean enough, due to artifacts including spurious resting-state processes (head movement, mind-wandering). Therefore, not all volumes in the fMRI time series can contribute to the subsequent FBN estimation. To address this issue, we propose a novel FBN estimation method by introducing a latent variable as an indicator of the data quality, and develop an alternating optimization algorithm for jointly scrubbing the data and estimating FBN simultaneously. To further illustrate the effectiveness of the proposed method, we conduct experiments on two public datasets to identify subjects with mild cognitive impairment from normal controls based on the estimated FBNs, and achieve improved accuracies than the baseline methods.