J Imaging Inform Med. 2025 May 12. doi: 10.1007/s10278-025-01480-z. Online ahead of print.

ABSTRACT

Alveolar echinococcosis (AE) is a parasitic disease caused by Echinococcus multilocularis, where early detection is crucial for effective treatment. This study introduces a novel method for the early diagnosis of liver diseases by differentiating between tumor, AE, and healthy cases using non-contrast CT images, which are widely accessible and eliminate the risks associated with contrast agents. The proposed approach integrates an automatic liver region detection method based on RCNN followed by a CNN-based classification framework. A dataset comprising over 27,000 thorax-abdominal images from 233 patients, including 8206 images with liver tissue, was constructed and used to evaluate the proposed method. The experimental results demonstrate the importance of the two-stage classification approach. In a 2-class classification problem for healthy and non-healthy classes, an accuracy rate of 0.936 (95% CI: 0.925 - 0.947) was obtained, and that for 3-class classification problem with AE, tumor, and healthy classes was obtained as 0.863 (95% CI: 0.847 - 0.879). These results highlight the potential use of the proposed framework as a fully automatic approach for liver classification without the use of contrast agents. Furthermore, the proposed framework demonstrates competitive performance compared to other state-of-the-art techniques, suggesting its applicability in clinical practice.

PMID:40355689 | DOI:10.1007/s10278-025-01480-z

Orphanet J Rare Dis. 2025 May 12;20(1):226. doi: 10.1186/s13023-025-03758-5.

ABSTRACT

Hermansky-Pudlak Syndrome (HPS) type 1 (HPS-1) is an autosomal recessive disorder characterized by oculocutaneous albinism, platelet dysfunction, and pulmonary fibrosis (HPS-PF), the leading cause of mortality in these patients. HPS-PF manifests earlier than idiopathic pulmonary fibrosis, typically between 30 and 40 years of age. The etiology and drivers of HPS-PF progression remain poorly understood, and no FDA-approved therapies exist. Neutrophil extracellular traps (NETs) and neutrophil-derived mediators have emerged as key players in fibrosis, promoting lung injury, inflammation, and fibroblast activation. This study evaluates the role of neutrophil activation in age-related changes in patients with HPS-1, focusing on differences in inflammatory markers, neutrophil granules, and NETosis capacity. We observed significantly elevated levels of NETs, neutrophil granule proteins (NE, NGAL, LF), and inflammatory cytokines (IL-8, IL-6) in patients with HPS-1 older than 40 years compared to younger patients and healthy controls. Additionally, fibrosis-related markers (MMP-7 and MMP-8) were significantly higher in older patients. Elevated levels of anandamide (AEA), a circulating marker of HPS-PF, were positively associated with neutrophil granule markers in older patients, suggesting its association with fibrosis. Neutrophils from older patients also demonstrated increased NETosis capacity. These findings suggest that age-related neutrophil activation may contribute to an inflammatory environment that promotes fibrosis progression in HPS-1.

PMID:40355888 | DOI:10.1186/s13023-025-03758-5

BMJ Open. 2025 May 12;15(5):e094559. doi: 10.1136/bmjopen-2024-094559.

ABSTRACT

OBJECTIVES: Idiopathic pulmonary fibrosis (IPF) is a progressive interstitial lung disease. Chest high-resolution CT (HRCT) is instrumental in IPF management, and the Quantitative Lung Fibrosis (QLF) score is a computer-assisted metric for quantifying lung disease using HRCT. This study aimed to assess the change in QLF score associated with a minimum clinically important difference (MCID) of IPF symptoms and physiological lung function, and also determine the MCID of QLF change associated with all-cause mortality to serve as an imaging biomarker to confirm disease progression and response to therapy.

DESIGN AND STUDY SETTING: We conducted post hoc analyses of prospective data from two IPF phase II studies of pamrevlumab, a fully human monoclonal antibody that binds to and inhibits connective tissue growth factor activity.

PARTICIPANTS: Overall, 152 patients with follow-up visits after week 24.

METHODS: We used the anchor-based Jaeschke's method to estimate the MCID of the QLF score that corresponded with the already established MCID of St. George's Respiratory Questionnaire (SGRQ) and percent-predicted forced vital capacity (ppFVC). We also conducted a Cox regression analysis to establish a sensitive and robust MCID of the QLF score in predicting all-cause mortality.

RESULTS: QLF changes of 4.4% and 3.6% corresponded to the established MCID of a 5-point increase in SGRQ and a 3.4% reduction in ppFVC, respectively. QLF changes of 1% (HR=4.98, p=0.05), 2% (HR=4.04, p=0.041), 20 mL (HR=6.37, p=0.024) and 22 mL (HR=6.38, p=0.024) predicted mortality.

CONCLUSION: A conservative metric of 2% can be used as the MCID of QLF for predicting all-cause mortality. This may be considered in IPF trials in which the degree of structural fibrosis assessed via HRCT is an endpoint. The MCID of SGRQ and FVC corresponds with a greater amount of QLF and may reflect that a greater amount of change in fibrosis is required before there is functional change.

TRIAL REGISTRATION NUMBER: NCT01262001, NCT01890265.

PMID:40355288 | DOI:10.1136/bmjopen-2024-094559

Medicine (Baltimore). 2025 May 9;104(19):e42376. doi: 10.1097/MD.0000000000042376.

ABSTRACT

This study employed bioinformatics to investigate potential molecular markers associated with idiopathic pulmonary fibrosis (IPF) and examined their correlation with immune-infiltrating cells. Microarray data for IPF were retrieved from the Gene Expression Omnibus database. Differentially expressed genes (DEGs) and module genes were identified through Limma analysis and weighted gene co-expression network analysis. Enrichment analysis and protein-protein interaction network development were performed on the DEGs. Machine learning algorithms, including least absolute shrinkage and selection operator regression, random forest, and extreme gradient boosting, were applied to identify potential key genes. The predictive accuracy was assessed through a nomogram and a receiver operating characteristic (ROC) curve. Additionally, the correlation between core genes and immune-infiltrating cells was assessed utilizing the CIBERSORT algorithm. An IPF model was established in a human fetal lung fibroblast 1 (HFL-1) through induction with transforming growth factor β1 (TGF-β1), and validation was conducted via reverse transcription-quantitative polymerase chain reaction. A sum of 1246 genes exhibited upregulation, whereas 879 genes were downregulated. Pathway enrichment analysis and functional annotation revealed that DEGs were predominantly involved in extracellular processes. Four key genes - cd19, cxcl13, fcrl5, and slamf7 - were identified. Furthermore, ROC analysis demonstrated high predictive accuracy for these 4 genes. Compared to healthy individuals, lung tissues from IPF patients exhibited an increased presence of plasma cells, CD4 memory-activated T cells, M0 macrophages, activated dendritic cells, resting NK cells, and M2 macrophage infiltration. The upregulation of cd19, cxcl13, fcrl5, and slamf7 in TGF-β1-treated HFL-1 cells was confirmed, aligning with the findings from the microarray data analysis. cd19, cxcl13, fcrl5, and slamf7 serve as diagnostic markers for IPF, providing fresh perspectives regarding the fundamental pathogenesis and molecular mechanisms associated with this condition.

PMID:40355204 | DOI:10.1097/MD.0000000000042376

J Ethnopharmacol. 2025 May 10:119934. doi: 10.1016/j.jep.2025.119934. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: Idiopathic pulmonary fibrosis (IPF) is a progressive and fatal disease. Baihe Gujin decoction (BHGJ), a traditional Chinese medicine consisting of ten medicine food homology herbs, has shown therapeutic effects in various lung diseases; however, its efficacy in ameliorating IPF and the underlying mechanisms remain unclear.

AIM OF THE STUDY: This study aimed to evaluate the effects of BHGJ on IPF and investigate its potential mechanisms.

MATERIALS AND METHODS: We established a bleomycin (BLM)-induced IPF model and performed proteomic analysis. The therapeutic effects of BHGJ on IPF were assessed by measuring lung index, hydroxyproline (HYP) content, lung function parameters, and histopathological changes. Mechanistic insights were further explored using western blot and RT-qPCR analyses.

RESULTS: Our results demonstrated that BHGJ significantly alleviated BLM-induced IPF, improved lung function, reduced histopathological damage, and decreased collagen deposition. BHGF reduced apoptosis and inhibited EMT in TGF-β-induced A549 cells. Proteomic analysis revealed that its effects were associated with the modulation of the proline metabolism pathway.

CONCLUSIONS: BHGJ effectively attenuated IPF progression via regulating proline metabolism, providing a potential therapeutic strategy for pulmonary fibrosis.

PMID:40354839 | DOI:10.1016/j.jep.2025.119934

Nat Methods. 2025 May 12. doi: 10.1038/s41592-025-02660-z. Online ahead of print.

ABSTRACT

Despite being information rich, the vast majority of untargeted mass spectrometry data are underutilized; most analytes are not used for downstream interpretation or reanalysis after publication. The inability to dive into these rich raw mass spectrometry datasets is due to the limited flexibility and scalability of existing software tools. Here we introduce a new language, the Mass Spectrometry Query Language (MassQL), and an accompanying software ecosystem that addresses these issues by enabling the community to directly query mass spectrometry data with an expressive set of user-defined mass spectrometry patterns. Illustrated by real-world examples, MassQL provides a data-driven definition of chemical diversity by enabling the reanalysis of all public untargeted metabolomics data, empowering scientists across many disciplines to make new discoveries. MassQL has been widely implemented in multiple open-source and commercial mass spectrometry analysis tools, which enhances the ability, interoperability and reproducibility of mining of mass spectrometry data for the research community.

PMID:40355727 | DOI:10.1038/s41592-025-02660-z

Nat Plants. 2025 May 12. doi: 10.1038/s41477-025-01996-w. Online ahead of print.

ABSTRACT

Agrobacterium pathogenesis, which involves transferring T-DNA into plant cells, is the cornerstone of plant genetic engineering. As the applications that rely on Agrobacterium increase in sophistication, it becomes critical to achieve a quantitative and predictive understanding of T-DNA expression at the level of single plant cells. Here we examine if a classic Poisson model of interactions between pathogens and host cells holds true for Agrobacterium infecting Nicotiana benthamiana. Systematically challenging this model revealed antagonistic and synergistic density-dependent interactions between bacteria that do not require quorum sensing. Using various approaches, we studied the molecular basis of these interactions. To overcome the engineering constraints imposed by antagonism, we created a dual binary vector system termed 'BiBi', which can improve the efficiency of a reconstituted complex metabolic pathway in a predictive fashion. Our findings illustrate how combining theoretical models with quantitative experiments can reveal new principles of bacterial pathogenesis, impacting both fundamental and applied plant biology.

PMID:40355701 | DOI:10.1038/s41477-025-01996-w

Nat Rev Genet. 2025 May 12. doi: 10.1038/s41576-025-00853-y. Online ahead of print.

NO ABSTRACT

PMID:40355601 | DOI:10.1038/s41576-025-00853-y

Nat Biotechnol. 2025 May 12. doi: 10.1038/s41587-025-02697-7. Online ahead of print.

NO ABSTRACT

PMID:40355567 | DOI:10.1038/s41587-025-02697-7

Drug Ther Bull. 2025 May 12:dtb-2025-000016. doi: 10.1136/dtb.2025.000016. Online ahead of print.

NO ABSTRACT

PMID:40355247 | DOI:10.1136/dtb.2025.000016

Int Dent J. 2025 May 11;75(4):100827. doi: 10.1016/j.identj.2025.04.007. Online ahead of print.

ABSTRACT

Dental caries is one of the most prevalent chronic diseases among both children and adults, despite being largely preventable. This condition has significant negative impacts on human health and imposes a substantial economic burden. In recent years, scientists and dentists have increasingly started to utilize artificial intelligence (AI), particularly machine learning, to improve the efficiency of dental caries management. This study aims to provide an overview of the current knowledge about the AI-enabled approaches for dental caries management within the framework of personalized patient care. Generally, AI works as a promising tool that can be used by both dental professionals and patients. For dental professionals, it predicts the risk of dental caries by analyzing dental caries risk and protective factors, enabling to formulate personalized preventive measures. AI, especially those based on machine learning and deep learning, can also analyze images to detect signs of dental caries, assist in developing treatment plans, and help to make a risk assessment for pulp exposure during treatment. AI-powered tools can also be used to train dental students through simulations and virtual case studies, allowing them to practice and refine their clinical skills in a risk-free environment. Additionally, AI tracks brushing patterns and provides feedback to improve oral hygiene practices of the patients and the general population, thereby improving their understanding and compliance. This capability of AI can inform future research and the development of new strategies for dental caries management and control.

PMID:40354695 | DOI:10.1016/j.identj.2025.04.007

Bioinformatics. 2025 May 12:btaf298. doi: 10.1093/bioinformatics/btaf298. Online ahead of print.

ABSTRACT

MOTIVATION: Predicting protein-ligand binding affinity accurately and quickly is a major challenge in drug discovery. Recent advancements suggest that deep learning-based computational methods can effectively quantify binding affinity, making them a promising alternative. Environmental factors significantly influence the interactions between protein pockets and ligands, affecting the binding strength. However, many existing deep learning approaches tend to overlook these environmental effects, focusing instead on extracting features from proteins and ligands based solely on their sequences or structures.

RESULTS: We propose a deep learning method, EM-PLA, which is based on an environment-aware heterogeneous graph neural network and utilizes multimodal data. This method improves protein-ligand binding affinity prediction by incorporating environmental information derived from the biochemical properties of proteins and ligands. Specifically, EM-PLA employs a heterogeneous graph neural network(HGT) with environmental information to improve the calculation of non-covalent interactions, while also considering the interaction calculations between protein sequences and ligand sequences. We evaluate the performance of the proposed EM-PLA through comprehensive benchmark experiments for binding affinity prediction, demonstrating its superior performance and generalization capability compared to state-of-the-art baseline methods. Furthermore, by analyzing the results of the ablation experiments and integrating visual analyses and case studies, we validate the rationale of the proposed method. These results indicate that EM-PLA is an effective method for binding affinity prediction and may provide valuable insights for future applications.

AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/littlemou22/EM-PLA.

CONTACT: pzhang@tju.edu.com.

SUPPLEMENTARY INFORMATION: Supplementary data are available in the submitted files.

PMID:40354612 | DOI:10.1093/bioinformatics/btaf298

Anal Chem. 2025 May 12. doi: 10.1021/acs.analchem.5c01082. Online ahead of print.

ABSTRACT

Precise discrimination of the crucial substances, e.g., synthetic cannabinoids (SCs) that are composed of low-active chemical groups and structurally similar to each other with tiny differences, is a pressing need and of great significance for safeguarding public security and human health. The structure-relevant vibrational spectroscopic techniques, e.g., Raman spectroscopy, could reflect structural fingerprint information on the target; however, the algorithm-assisted phrasing is inevitable. This work achieved the accurate identification of CA series SCs by proposing an attention mechanism involving a CNN algorithm to phrase the Raman data. Specifically, these SCs have only one different chemical group compared to each other, the attention mechanism was introduced to intensify the computation on their structural difference from the massive data, realizing the accurate discrimination. Furthermore, how the spectral peaks corresponded to the specific structure was revealed, which plays a decisive role for the algorithm to distinguish these substances, and provides an instructive reference for differentiating other SCs based on Raman spectra. Hence, this work provides a research paradigm for applying the advanced CNN algorithm-aided Raman spectral analysis to sub-differentiate the substances, strengthening the understanding of spectral information from the sub-molecular level and propelling the integration of interdisciplinary areas.

PMID:40354573 | DOI:10.1021/acs.analchem.5c01082

PLoS One. 2025 May 12;20(5):e0319562. doi: 10.1371/journal.pone.0319562. eCollection 2025.

ABSTRACT

The increasing importance of deep learning in software development has greatly improved software quality by enabling the efficient identification of defects, a persistent challenge throughout the software development lifecycle. This study seeks to determine the most effective model for detecting defects in software projects. It introduces an intelligent approach that combines Temporal Convolutional Networks (TCN) with Antlion Optimization (ALO). TCN is employed for defect detection, while ALO optimizes the network's weights. Two models are proposed to address the research problem: (a) a basic TCN without parameter optimization and (b) a hybrid model integrating TCN with ALO. The findings demonstrate that the hybrid model significantly outperforms the basic TCN in multiple performance metrics, including area under the curve, sensitivity, specificity, accuracy, and error rate. Moreover, the hybrid model surpasses state-of-the-art methods, such as Convolutional Neural Networks, Gated Recurrent Units, and Bidirectional Long Short-Term Memory, with accuracy improvements of 21.8%, 19.6%, and 31.3%, respectively. Additionally, the proposed model achieves a 13.6% higher area under the curve across all datasets compared to the Deep Forest method. These results confirm the effectiveness of the proposed hybrid model in accurately detecting defects across diverse software projects.

PMID:40354496 | DOI:10.1371/journal.pone.0319562

PLoS One. 2025 May 12;20(5):e0317758. doi: 10.1371/journal.pone.0317758. eCollection 2025.

ABSTRACT

Eliminating flickering from digital images captured by cameras equipped with a rolling shutter is of paramount importance in computer vision applications. The ripple effect observed in an individual image is a consequence of the non-synchronized exposure of rolling shutters utilized in CMOS sensor-based cameras. To date, there have been only a limited number of studies focusing on the mitigation of flickering in single images. Furthermore, it is more feasible to eliminate these flickers with prior knowledge, such as camera specifications or matching images. To solve these problems, we present an unsupervised framework Super-Resolution Generative Adversarial Networks and Partition-Based Adaptive Filtering Technique (SRGAN-PBAFT) trained on unpaired images from end to end Deflickering of a single image. Flicker artifacts, which are commonly caused by dynamic lighting circumstances and sensor noise, can severely reduce an image's visual quality and authenticity. To enhance image resolution SRGAN is used, while Partition based Adaptive Filtering technique detects and mitigates flicker distortions successfully. Combining the strengths of deep learning and adaptive filtering results in a potent approach for restoring image integrity. Experimental results shows that the Proposed SRGAN-PBAFT method is effective, with major improvements in visual quality and flicker aberration reduction compared to existing methods.

PMID:40354494 | DOI:10.1371/journal.pone.0317758

PLOS Digit Health. 2025 May 12;4(5):e0000831. doi: 10.1371/journal.pdig.0000831. eCollection 2025 May.

ABSTRACT

Diabetic retinopathy (DR) is a frequent complication of diabetes, affecting millions worldwide. Screening for this disease based on fundus images has been one of the first successful use cases for modern artificial intelligence in medicine. However, current state-of-the-art systems typically use black-box models to make referral decisions, requiring post-hoc methods for AI-human interaction and clinical decision support. We developed and evaluated an inherently interpretable deep learning model, which explicitly models the local evidence of DR as part of its network architecture, for clinical decision support in early DR screening. We trained the network on 34,350 high-quality fundus images from a publicly available dataset and validated its performance on a large range of ten external datasets. The inherently interpretable model was compared to post-hoc explainability techniques applied to a standard DNN architecture. For comparison, we obtained detailed lesion annotations from ophthalmologists on 65 images to study if the class evidence maps highlight clinically relevant information. We tested the clinical usefulness of our model in a retrospective reader study, where we compared screening for DR without AI support to screening with AI support with and without AI explanations. The inherently interpretable deep learning model obtained an accuracy of .906 [.900-.913] (95%-confidence interval) and an AUC of .904 [.894-.913] on the internal test set and similar performance on external datasets, comparable to the standard DNN. High evidence regions directly extracted from the model contained clinically relevant lesions such as microaneurysms or hemorrhages with a high precision of .960 [.941-.976], surpassing post-hoc techniques applied to a standard DNN. Decision support by the model highlighting high-evidence regions in the image improved screening accuracy for difficult decisions and improved screening speed. This shows that inherently interpretable deep learning models can provide clinical decision support while obtaining state-of-the-art performance improving human-AI collaboration.

PMID:40354306 | DOI:10.1371/journal.pdig.0000831

J Exp Psychol Gen. 2025 May 12. doi: 10.1037/xge0001740. Online ahead of print.

ABSTRACT

Pertaining to goal orientation and achievement, agency is a fundamental aspect of human cognition and behavior. Accordingly, detecting and quantifying linguistic encoding of agency are critical for the analysis of human actions, interactions, and social dynamics. Available agency-quantifying computational tools rely on word-counting methods, which typically are insensitive to the semantic context in which the words are used and consequently prone to miscoding, for example, in case of polysemy. Additionally, some currently available tools do not take into account differences in the intensity and directionality of agency. In order to overcome these shortcomings, we present BERTAgent, a novel tool to quantify semantic agency in text. BERTAgent is a computational language model that utilizes the transformers architecture, a popular deep learning approach to natural language processing. BERTAgent was fine-tuned using textual data that were evaluated by human coders with respect to the level of conveyed agency. In four validation studies, BERTAgent exhibits improved convergent and discriminant validity compared to previous solutions. Additionally, the detailed description of BERTAgent's development procedure serves as a tutorial for the advancement of similar tools, providing a blueprint for leveraging the existing lexicographical data sets in conjunction with the deep learning techniques in order to detect and quantify other psychological constructs in textual data. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

PMID:40354292 | DOI:10.1037/xge0001740

IEEE Trans Image Process. 2025 May 12;PP. doi: 10.1109/TIP.2025.3567205. Online ahead of print.

ABSTRACT

All-in-one image restoration, which seeks to handle multiple types of degradation within a unified model, has become a prominent research topic in computer vision. While existing deep learning models have achieved remarkable success in specific restoration tasks, extending these models to heterogenous degradations presents significant challenges. Current all-in-one methods predominantly concentrate on extracting degradation priors, often employing learned and fixed task prompts to guide the restoration process. However, these static prompts are inclined to generate an average distribution characteristics of degradations, unable to accurately depict the unique attribute of the given input, consequently providing suboptimal restoration results. To tackle these challenges, we propose a novel dynamic prompt approach called Degradation Prototype Assignment and Prompt Distribution Learning (DPPD). Our approach decouples the degradation prior extraction into two novel components: Degradation Prototype Assignment (DPA) and Prompt Distribution Learning (PDL). DPA anchors the degradation representations to predefined prototypes, providing discriminative and scalable representations. In addition, PDL models prompts as distributions rather than fixed parameters, facilitating dynamic and adaptive prompt sampling. Extensive experiments demonstrate that our DPPD framework can achieve significant performance improvement on different image restoration tasks. Codes are available at our project page https://github.com/Aitical/DPPD.

PMID:40354220 | DOI:10.1109/TIP.2025.3567205

IEEE J Biomed Health Inform. 2025 May 12;PP. doi: 10.1109/JBHI.2025.3569160. Online ahead of print.

ABSTRACT

Respiratory diseases present significant challenges to global health due to their high morbidity and mortality rates. Traditional diagnostic methods, such as chest radiographs and blood tests, often lead to unnecessary costs and resource strain, as well as potential risks of cross-contamination during these procedures. In recent years, contactless sensing and intelligent technologies, particularly multi-modal sound-based deep learning methods, have emerged as promising solutions for the early detection of respiratory diseases. While these methods have shown encouraging results, the integration of multi-modal features has not been sufficiently explored, which limits the enhancement of diagnostic accuracy. To address this issue, we introduce GAMMNet, a novel multi-modal neural network designed to enhance the detection of respiratory diseases by leveraging multi-modal sound data collected from contactless recording devices. GAMMNet utilizes a unique gating mechanism that adaptively regulates the influence of each modality on the classification results. Additionally, our model incorporates multi-head attention and linear transformation modules to further enhance classification performance. Our GAMMNet achieves state-of-the-art classification results, compared to existing deep learning based methods, on real-world multi-modal respiratory sound datasets. These findings demonstrate the robustness and effectiveness of GAMMNet in the contactless monitoring and early detection of respiratory diseases.

PMID:40354202 | DOI:10.1109/JBHI.2025.3569160

IEEE J Biomed Health Inform. 2025 May 12;PP. doi: 10.1109/JBHI.2025.3569726. Online ahead of print.

ABSTRACT

Breast cancer poses a serious threat to women's health, and its early detection is crucial for enhancing patient survival rates. While deep learning has significantly advanced mammographic image analysis, existing methods struggle to balance between view consistency with input adaptability. Furthermore, current models face challenges in accurately capturing multi-scale features, especially when subtle lesion variations across different scales are involved. To address this challenge, this paper proposes a Hybrid View Learning (HVL) paradigm that unifies traditional Single-View and Multi-View Learning approaches. The core component of this paradigm, our Attention-based Hybrid View Learning (AHVL) framework, incorporates two essential attention mechanisms: Contrastive Switch Attention (CSA) and Selective Pooling Attention (SPA). The CSA mechanism flexibly alternates between self-attention and cross-attention based on data integrity, integrating a pre-trained language model for contrastive learning to enhance model stability. Meanwhile, the SPA module employs multi-scale feature pooling and selection to capture critical features from mammographic images, overcoming the limitations of traditional models that struggle with fine-grained lesion detection. Experimental validation on the INbreast and CBIS-DDSM datasets shows that the AHVL framework outperforms both single-view and multi-view methods, especially under extreme view missing conditions. Even with an 80% missing rate on both datasets, AHVL maintains the highest accuracy and experiences the smallest performance decline in metrics like F1 score and AUC-PR, demonstrating its robustness and stability. This study redefines mammographic image analysis by leveraging attention-based hybrid view processing, setting a new standard for precise and efficient breast cancer diagnosis.

PMID:40354201 | DOI:10.1109/JBHI.2025.3569726