The sharp rise in non-alcoholic fatty liver disease (NAFLD) cases has become a major health concern in recent years. Accurately identifying tissue alteration regions is crucial for NAFLD diagnosis but challenging with small-scale pathology datasets. Recently, prompt tuning has emerged as an effective strategy for adapting vision models to small-scale data analysis. However, current prompting techniques, designed primarily for general image classification, use generic cues that are inadequate when dealing with the intricacies of pathological tissue analysis. To solve this problem, we introduce Quantitative Attribute-based Polarity Visual Prompting (Q-PoVP), a new prompting method for pathology image analysis. Q-PoVP introduces two types of measurable attributes: K-function-based spatial attributes and histogram-based morphological attributes. Both help to measure tissue conditions quantitatively. We develop a quantitative attribute-based polarity visual prompt generator that converts quantitative visual attributes into positive and negative visual prompts, facilitating a more comprehensive and nuanced interpretation of pathological images. To enhance feature discrimination, we introduce a novel orthogonal-based polarity visual prompt tuning technique that disentangles and amplifies positive visual attributes while suppressing negative ones. We extensively tested our method on three different tasks. Our task-specific prompting demonstrates superior performance in both diagnostic accuracy and interpretability compared to existing methods. This dual advantage makes it particularly valuable for clinical settings, where healthcare providers require not only reliable results but also transparent reasoning to support informed patient care decisions. Code is available at https://github.com/7LFB/Q-PoVP.

The increasing prevalence of non-alcoholic fatty liver disease (NAFLD) has caused public concern in recent years. The high prevalence and risk of severe complications make monitoring NAFLD progression a public health priority. Fibrosis staging from liver biopsy images plays a key role in demonstrating the histological progression of NAFLD. Fibrosis mainly involves the deposition of fibers around vessels. Current deep learning-based fi-brosis staging methods learn spatial relationships between tissue patches but do not explicitly consider the relation-ships between vessels and fibers, leading to limited performance and poor interpretability. In this paper, we propose an eXplicit vessel-fiber modeling method for Fibrosis staging from liver biopsy images, namely XFibrosis. Specifically, we transform vessels and fibers into graph-structured representations, where their micro-structures are depicted by vessel-induced primal graphs andfiber-induced dual graphs, respectively. Moreover, the fiber-induced dual graphs also represent the connectivity information between vessels caused by fiber deposition. A primal-dual graph convolution module is designed to facilitate the learning of spatial relationships between vessels and fibers, allowing for the joint exploration and interaction of their micro-structures. Experiments conducted on two datasets have shown that explicitly modeling the relationship between vessels and fibers leads to improved fibrosis staging and en-hanced interpretability.

The rapid increase in cases of non-alcoholic fatty liver disease (NAFLD) in recent years has raised significant public concern. Accurately identifying tissue alteration regions is crucial for the diagnosis of NAFLD, but this task presents challenges in pathology image analysis, particularly with small-scale datasets. Recently, the paradigm shift from full fine-tuning to prompting in adapting vision foundation models has offered a new perspective for small-scale data analysis. However, existing prompting methods based on task-agnostic prompts are mainly developed for generic image recognition, which fall short in providing instructive cues for complex pathology images. In this paper, we propose Quantitative Attribute-based Prompting (QAP), a novel prompting method specifically for liver pathology image analysis. QAP is based on two quantitative attributes, namely K-function-based spatial attributes and histogram-based morphological attributes, which are aimed for quantitative assessment of tissue states. Moreover, a conditional prompt generator is designed to turn these instance-specific attributes into visual prompts. Extensive experiments on three diverse tasks demonstrate that our task-specific prompting method achieves better diagnostic performance as well as better interpretability. Code is available at https://github.com/7LFBIQAP.

MOTIVATION: Enhanced by contemporary computational advances, the prediction of drug-target interactions (DTIs) has become crucial in developing de novo and effective drugs. Existing deep learning approaches to DTI prediction are frequently beleaguered by a tendency to overfit specific molecular representations, which significantly impedes their predictive reliability and utility in novel drug discovery contexts. Furthermore, existing DTI networks often disregard the molecular size variance between macro molecules (targets) and micro molecules (drugs) by treating them at an equivalent scale that undermines the accurate elucidation of their interaction. RESULTS: We propose a novel DTI network with a differential-scale scheme to model the binding site for enhancing DTI prediction, which is named as BindingSiteDTI. It explicitly extracts multiscale substructures from targets with different scales of molecular size and fixed-scale substructures from drugs, facilitating the identification of structurally similar substructural tokens, and models the concealed relationships at the substructural level to construct interaction feature. Experiments conducted on popular benchmarks, including DUD-E, human, and BindingDB, shown that BindingSiteDTI contains significant improvements compared with recent DTI prediction methods. AVAILABILITY AND IMPLEMENTATION: The source code of BindingSiteDTI can be accessed at https://github.com/MagicPF/BindingSiteDTI.

Liver biopsy images play a key role in the diagnosis of global non-alcoholic fatty liver disease (NAFLD). The NAFLD activity score (NAS) on liver biopsy images grades the amount of histological findings that reflect the progression of NAFLD. However, liver biopsy image analysis remains a challenging task due to its complex tissue structures and sparse distribution of histological findings. In this paper, we propose a sparse interpretable feature learning method (SparseX) to efficiently estimate NAS scores. First, we introduce an interpretable spatial sampling strategy based on histological features to effectively select informative tissue regions containing tissue alterations. Then, SparseX formulates the feature learning as a low-rank decomposition problem. Non-negative matrix factorization (NMF)-based attributes learning is embedded into a deep network to compress and select sparse features for a small portion of tissue alterations contributing to diagnosis. Experiments conducted on the internal Liver-NAS and public SteatosisRaw datasets show the effectiveness of the proposed method in terms of classification performance and interpretability. regions containing tissue alterations. Then, SparseX formulates the feature learning as a low-rank decomposition problem. Non-negative matrix factorization (NMF)-based attributes learning is embedded into a deep network to compress and select sparse features for a small portion of tissue alterations contributing to diagnosis. Experiments conducted on the internal Liver-NAS and public SteatosisRaw datasets show the effectiveness of the proposed method in terms of classification performance and interpretability.

It is a well-known fact that the variations in illumination could seriously affect the performance of 2D face analysis algorithms, such as face landmarking and face recognition. Unfortunately, the illumination condition is usually uncontrolled and unpredictable in most practical applications. Numerous methods have been developed to tackle this problem but the results is poor, especially for images with extreme lighting condition. Furthermore, most traditional illumination processing methods only demonstrate on grayscale images and require strict alignment of face images, resulting in limited applications in real world. In this paper, we proposed to reformulate the face image illumination processing problem as a style translation task with a Generative Adversarial Network (GAN). The key insight is to use the powerful mapping ability of GAN between two domains without knowing their true distributions. In this new sight, we developed a new multi-scale dual discriminate nets and employed multi-scale adversarial learning for visually realistic illumination processing. Advocating the use of the insights from traditional method, we also use reconstruction learning and add two new loss items of image quality assessment to enforce the preservation of all other illumination excluding details on the generated image. Experiments on CMU Multi-PIE and FRGC datasets show that our method can obtain promising illumination normalization results and preserve a superior visual quality.

In this paper, we look at the raising spatial antenna correlations in massive antenna arrays and leverage spatial correlation combined with Compressive Sensing (CS) theory in the process of channel estimation. According to CS, the success probability of recovery is highly dependent on the restricted isometry property (RIP) of dictionary matrix. Recent advances in CS suggest that minimizing the coherence of dictionary matrix is an alternative efficient and effective way to test RIP. In this basis, this paper addresses the pilot pattern design problem in spatial domain aiming at minimizing the averaged coherence of the dictionary matrix. We first formulate an optimization problem with regard to pilot power distribution (PPD) and pilot antenna indexes set (PAIS) in CS-based channel estimation. Then two algorithms are proposed to separately design PPD and PAIS. Moreover, a jointly optimizing algorithm is presented. Simulation results demonstrate that the designed CS-based spatial pilot pattern outperforms random pilots and equal pilots, which significantly reduce pilot overhead and improve channel estimation quality compared with linear square (LS) estimation in spatial domain for massive antenna arrays.

Clustering is a promising interference mitigation scheme in dynamic TDD systems. However, most previous works just took large-scale path loss or coupling loss as criteria of the clustering schemes, thus the throughput performance would be limited by the varying traffic requirements among different small cells within one cluster. In this paper, a novel dynamic cluster-based Interference Mitigation and Traffic Adaptation (IMTA) scheme is proposed and evaluated with dense deployment of small cells (SCs). Firstly, a new clustering criterion named Differentiating Metric (DM) is defined. Based on the defined DM value, a DM matrix is formed and further presented by a clustering graph. In the clustering graph, the dynamic clustering strategy is mapped to a MAX K-CUT problem, which is addressed in polynomial time by a proposed heuristic clustering algorithm. Furthermore, the system level simulation results demonstrate a promising improvement on uplink traffic throughput (UTP) in our proposed scheme compared with traditional clustering schemes.

Energy efficiency (EE) has become an increasingly important issue in Device-to-Device (D2D) communications since wireless terminals are hand-held equipments with limited battery life. In this paper, an energy-efficient channel reusing scheme for multi-D2D links is proposed. We first analyze the EE of a single D2D link in both non-cooperative mode (NCM) and cooperative mode (CM), and prove that the EE of the D2D link is mainly determined by the location of the cellular user equipment (CUE) that shares resource with the D2D pair. On this basis, a location-based algorithm (LBA) is proposed to select the optimal CUE for each of the D2D pairs, aiming to maximize the sum EE of all D2D links. Numerical results show that the proposed LBA could effectively improve the overall EE of the D2D system while guaranteeing the target rate of each D2D link. Moreover, the proposed LBA does not require the channel state information (CSI) of all the involved links, which could significantly reduce the feedback overhead and computational complexity.