Radiology. 2025 Apr;315(1):e240775. doi: 10.1148/radiol.240775.

ABSTRACT

Background Acute ischemic stroke (AIS) is a major cause of morbidity and mortality, requiring swift and precise clinical decisions based on neuroimaging. Recent advances in deep learning-based computer vision and language artificial intelligence (AI) models have demonstrated transformative performance for several stroke-related applications. Purpose To evaluate deep learning applications for imaging in AIS in adult patients, providing a comprehensive overview of the current state of the technology and identifying opportunities for advancement. Materials and Methods A systematic literature review was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A comprehensive search of four databases from January 2016 to January 2024 was performed, targeting deep learning applications for imaging of AIS, including automated detection of large vessel occlusion and measurement of Alberta Stroke Program Early CT Score. Articles were selected based on predefined inclusion and exclusion criteria, focusing on convolutional neural networks and transformers. The top-represented areas were addressed, and the relevant information was extracted and summarized. Results Of 380 studies included, 171 (45.0%) focused on stroke lesion segmentation, 129 (33.9%) on classification and triage, 31 (8.2%) on outcome prediction, 15 (3.9%) on generative AI and large language models, and 11 (2.9%) on rapid or low-dose imaging specific to stroke applications. Detailed data extraction was performed for 68 studies. Public AIS datasets are also highlighted, for researchers developing AI models for stroke imaging. Conclusion Deep learning applications have permeated AIS imaging, particularly for stroke lesion segmentation. However, challenges remain, including the need for standardized protocols and test sets, larger public datasets, and performance validation in real-world settings. © RSNA, 2025 Supplemental material is available for this article.

PMID:40197098 | DOI:10.1148/radiol.240775

J Chem Inf Model. 2025 Apr 8. doi: 10.1021/acs.jcim.5c00051. Online ahead of print.

ABSTRACT

Deep learning has revolutionized difficult tasks in chemistry and biology, yet existing language models often treat these domains separately, relying on concatenated architectures and independently pretrained weights. These approaches fail to fully exploit the shared atomic foundations of molecular and protein sequences. Here, we introduce T5ProtChem, a unified model based on the T5 architecture, designed to simultaneously process molecular and protein sequences. Using a new pretraining objective, ProtiSMILES, T5ProtChem bridges the molecular and protein domains, enabling efficient, generalizable protein-chemical modeling. The model achieves a state-of-the-art performance in tasks such as binding affinity prediction and reaction prediction, while having a strong performance in protein function prediction. Additionally, it supports novel applications, including covalent binder classification and sequence-level adduct prediction. These results demonstrate the versatility of unified language models for drug discovery, protein engineering, and other interdisciplinary efforts in computational biology and chemistry.

PMID:40197028 | DOI:10.1021/acs.jcim.5c00051

J Chem Theory Comput. 2025 Apr 8. doi: 10.1021/acs.jctc.5c00409. Online ahead of print.

ABSTRACT

We present a deep learning approach for analyzing two-dimensional scattering data of semiflexible polymers under external forces. In our framework, scattering functions are compressed into a three-dimensional latent space using a Variational Autoencoder (VAE), and two converter networks establish a bidirectional mapping between the polymer parameters (bending modulus, stretching force, and steady shear) and the scattering functions. The training data are generated using off-lattice Monte Carlo simulations to avoid the orientational bias inherent in lattice models, ensuring robust sampling of polymer conformations. The feasibility of this bidirectional mapping is demonstrated by the organized distribution of polymer parameters in the latent space. By integrating the converter networks with the VAE, we obtain a generator that produces scattering functions from given polymer parameters and an inferrer that directly extracts polymer parameters from scattering data. While the generator can be utilized in a traditional least-squares fitting procedure, the inferrer produces comparable results in a single pass and operates 3 orders of magnitude faster. This approach offers a scalable automated tool for polymer scattering analysis and provides a promising foundation for extending the method to other scattering models, experimental validation, and the study of time-dependent scattering data.

PMID:40197011 | DOI:10.1021/acs.jctc.5c00409

JCI Insight. 2025 Apr 8;10(7):e185758. doi: 10.1172/jci.insight.185758.

ABSTRACT

Using transcriptomic profiling at single-cell resolution, we investigated cell-intrinsic and cell-extrinsic signatures associated with pathogenesis and inflammation-driven fibrosis in both adult and pediatric patients with localized scleroderma (LS). We performed single-cell RNA-Seq on adult and pediatric patients with LS and healthy controls. We then analyzed the single-cell RNA-Seq data using an interpretable factor analysis machine learning framework, significant latent factor interaction discovery and exploration (SLIDE), which moves beyond predictive biomarkers to infer latent factors underlying LS pathophysiology. SLIDE is a recently developed latent factor regression-based framework that comes with rigorous statistical guarantees regarding identifiability of the latent factors, corresponding inference, and FDR control. We found distinct differences in the characteristics and complexity in the molecular signatures between adult and pediatric LS. SLIDE identified cell type-specific determinants of LS associated with age and severity and revealed insights into signaling mechanisms shared between LS and systemic sclerosis (SSc), as well as differences in onset of the disease in the pediatric compared with adult population. Our analyses recapitulate known drivers of LS pathology and identify cellular signaling modules that stratify LS subtypes and define a shared signaling axis with SSc.

PMID:40197368 | DOI:10.1172/jci.insight.185758

bioRxiv [Preprint]. 2025 Mar 28:2025.03.24.644676. doi: 10.1101/2025.03.24.644676.

ABSTRACT

BACKGROUND: Alzheimer's disease (AD) is a complex neurodegenerative disorder with substantial molecular variability across different brain regions and individuals, hindering therapeutic development. This study introduces PRISM-ML, an interpretable machine learning (ML) framework integrating multiomics data to uncover patient-specific biomarkers, subtissue-level pathology, and drug repurposing opportunities.

METHODS: We harmonized transcriptomic and genomic data of three independent brain studies containing 2105 post-mortem brain samples (1363 AD, 742 controls) across nine tissues. A Random Forest classifier with SHapley Additive exPlanations (SHAP) identified patient-level biomarkers. Clustering further delineated each tissue into subtissues, and network analysis revealed critical "bottleneck" (hub) genes. Finally, a knowledge graph-based screening identified multi-target drug candidates, and a real-world pharmacoepidemiologic study evaluated their clinical relevance.

RESULTS: We uncovered 36 molecularly distinct subtissues, each defined by a set of associated unique biomarkers and genetic drivers. Through network analysis of gene-gene interactions networks, we highlighted 262 bottleneck genes enriched in synaptic, cytoskeletal, and membrane-associated processes. Knowledge graph queries identified six FDA-approved drugs predicted to target multiple bottleneck genes and AD-relevant pathways simultaneously. One candidate, promethazine, demonstrated an association with reduced AD incidence in a large healthcare dataset of over 364000 individuals (hazard ratios ≤ 0.43; p < 0.001). These findings underscore the potential for multi-target approaches, reveal connections between AD and cardiovascular pathways, and offer novel insights into the heterogeneous biology of AD.

CONCLUSIONS: PRISM-ML bridges interpretable ML with multi-omics and systems biology to decode AD heterogeneity, revealing region-specific mechanisms and repurposable therapeutics. The validation of promethazine in real-world data underscores the clinical relevance of multi-target strategies, paving the way for more personalized treatments in AD and other complex disorders.

PMID:40196631 | PMC:PMC11974764 | DOI:10.1101/2025.03.24.644676

J Pathol Transl Med. 2025 Mar;59(2):105-114. doi: 10.4132/jptm.2024.11.05. Epub 2025 Feb 25.

ABSTRACT

BACKGROUND: The present research was designed to study the associations between genetic variants of TYMS and ENOSF1 genes with TYMS and ENOSF1 gene expression in neoadjuvant chemotherapy response among patients with gastric cancer.

METHODS: Formalin-embedded and paraffin-fixed matched tumor and normal gastric cancer tissue samples from patients who received neoadjuvant 5-fluorouracil (5-FU) treatment were obtained. DNA and RNA were extracted for all samples. A 28-bp variable number tandem repeat (VNTR) at the 5' untranslated region of TYMS gene and rs2612091 and rs2741171 variants in the ENOSF1 gene were genotyped for normal tissue samples. The real-time polymerase chain reaction method was used to study the expression of ENOSF1 and TYMS genes in both normal and tumor tissues. Data were analyzed using REST 2000 and SPSS ver. 26.0 software programs.

RESULTS: A significant association between TYMS 2R3R VNTR genotypes and 5-FU therapy was found (p = .032). The 3R3R and 2R2R genotypes were significantly associated with increased and decreased survival time, respectively (p = .003). The 3R3R genotype was significantly associated with TYMS overexpression (p < .001). Moreover, a significant association was found between the rs2612091 genotype and treatment outcome (p = .017).

CONCLUSIONS: This study highlights the impact of TYMS and ENOSF1 genes as predictive indicators for survival and response to 5-FU-based neoadjuvant chemotherapy in gastric cancer patients.

PMID:40195828 | DOI:10.4132/jptm.2024.11.05

Prostate Cancer Prostatic Dis. 2025 Apr 7. doi: 10.1038/s41391-025-00964-x. Online ahead of print.

ABSTRACT

BACKGROUND: The association between statin medication use and prostate cancer remains inconclusive. Evidence shows that genetic variation modifies lipid-lowering efficacy of statins, however, there are limited data on the pharmacogenomics of statins in prostate cancer chemoprevention.

METHODS: Clinical and germline data were extracted from the prostate biopsy database at the University Health Network, Toronto, Canada (1996-2014). A genome-wide association study (GWAS) and a custom array of 54 single nucleotide polymorphisms (SNPs) related to statin metabolism were performed. Using a case-control design, we examined the associations between statin use and overall and high-grade (Grade Group ≥2) prostate cancer risk. A case-only design was employed to explore interactions between candidate/GWAS SNPs and the statin-cancer association.

RESULTS: Among 3481 patients, 1104 (32%) were using statins at biopsy. Statin users were older and had higher body mass index, greater number of positive cores, and higher Gleason scores. In total, 2061 participants (59%) were diagnosed with prostate cancer, with 922 cases (45%) classified as high-grade. When adjusted for baseline characteristics, the use of statins was not associated with decreased risk of overall or high-grade prostate cancer. Two unique SNPs implicated in statin metabolism showed significant interaction with the statin-cancer association. In particular, statin users harboring the GG genotype (n = 668; 24%) of rs10276036 had significantly lower prostate cancer risk (HR 0.71, 95% CI 051-1.00). However, none of the SNPs achieved genome-wide significance.

CONCLUSIONS: In our study, statin use was not associated with either prostate cancer or high-grade prostate cancer risk. While one candidate SNP that influences statin metabolism may be associated with a lower cancer risk among statin users and thus warrants further study, neither this nor any other SNPs achieved genome-wide significance. Thus, our findings do not add evidence in support of a prostate cancer chemopreventive role for statins.

PMID:40195554 | DOI:10.1038/s41391-025-00964-x

bioRxiv [Preprint]. 2025 Mar 24:2025.03.21.644589. doi: 10.1101/2025.03.21.644589.

ABSTRACT

Pseudomonas aeruginosa (PA) causes severe respiratory infections utilizing multiple virulence functions. Our previous findings on PA quorum sensing (QS)-regulated small molecule, 2'-aminoacetophenone (2-AA), secreted by the bacteria in infected tissues, revealed its effect on immune and metabolic functions favouring a long-term presence of PA in the host. However, studies on 2-AA's specific effects on bronchial-airway epithelium and pulmonary endothelium remain elusive. To evaluate 2AA's spatiotemporal changes in the human airway, considering endothelial cells as the first point of contact when the route of lung infection is hematogenic, we utilized the microfluidic airway-on-chip lined by polarized human bronchial-airway epithelium and pulmonary endothelium. Using this platform, we performed RNA-sequencing to analyse responses of 2-AA-treated primary human pulmonary microvascular endothelium (HPMEC) and adjacent primary normal human bronchial epithelial (NHBE) cells from healthy female donors and potential cross-talk between these cells. Analyses unveiled specific signaling and biosynthesis pathways to be differentially regulated by 2-AA in epithelial cells, including HIF-1 and pyrimidine signaling, glycosaminoglycan, and glycosphingolipid biosynthesis, while in endothelial cells were fatty acid metabolism, phosphatidylinositol and estrogen receptor signaling, and proinflammatory signaling pathways. Significant overlap in both cell types in response to 2-AA was found in genes implicated in immune response and cellular functions. In contrast, we found that genes related to barrier permeability, cholesterol metabolism, and oxidative phosphorylation were differentially regulated upon exposure to 2-AA in the cell types studied. Murine in-vivo and additional in vitro cell culture studies confirmed cholesterol accumulation in epithelial cells. Results also revealed specific biomarkers associated with cystic fibrosis and idiopathic pulmonary fibrosis to be modulated by 2-AA in both cell types, with the cystic fibrosis transmembrane regulator expression to be affected only in endothelial cells. The 2-AA-mediated effects on healthy epithelial and endothelial primary cells within a microphysiological dynamic environment mimicking the human lung airway enhance our understanding of this QS signaling molecule. This study provides novel insights into their functions and potential interactions, paving the way for innovative, cell-specific therapeutic strategies to combat PA lung infections.

PMID:40196568 | PMC:PMC11974707 | DOI:10.1101/2025.03.21.644589

BMJ Public Health. 2025 Apr 2;3(1):e001584. doi: 10.1136/bmjph-2024-001584. eCollection 2025 Jan.

ABSTRACT

OBJECTIVES: In countries at the forefront of gender equality policy, mothers still play a more pronounced role than fathers in the provision of parental care for their children. This study aimed to explore gender equality in attendance at doctor's appointments among caregivers of children with chronic diseases before and after the introduction of video conference visits.

METHODS: Children aged 0-17 years diagnosed with cystic fibrosis, inflammatory bowel disease, diabetes or a chronic neurological disease at Gothenburg's and Lund's paediatric hospitals were included. Data on caregiver attendance from 2019 to 2022 were retrospectively collected from medical records. Doctors' appointments were categorised as in-person, telephone or video conference visits. Using mixed-effects models, we evaluated trends in parental attendance and assessed the associations between different types of appointments and gender equality in healthcare.

RESULTS: A total of 347 participants were included between 2019 and 2022, resulting in 6134 appointments. Overall attendance rates were 74% for mothers and 44% for fathers, corresponding to a difference of 30%-points (95% CI 27% to 32%-points, p<0.001). Mothers had consistently higher attendance rates across all types of appointments (all p<0.05). The attendance gap between mothers and fathers remained similar over time, except for video conference visits where an increase in maternal attendance was observed (p<0.001) while paternal attendance remained constant (p=0.90). Video conference visits had higher joint attendance rates than in-person and telephone appointments (both p<0.001).

CONCLUSION: Mothers attended paediatric outpatient visits more frequently than fathers across all appointment types. The gender gap in attendance remained unchanged after the introduction of video conference visits, while the joint attendance increased. Future interventions should explore structural strategies to enhance gender equality in caregiver attendance.

PMID:40196439 | PMC:PMC11973768 | DOI:10.1136/bmjph-2024-001584

Front Immunol. 2025 Mar 24;16:1550724. doi: 10.3389/fimmu.2025.1550724. eCollection 2025.

ABSTRACT

Pseudomonas aeruginosa is a prevalent opportunistic Gram-negative bacterial pathogen. One of its key virulence factors is pyocyanin, a redox-active phenazine secondary metabolite that plays a crucial role in the establishment and persistence of chronic infections. This review provides a synopsis of the mechanisms through which pyocyanin exacerbates pulmonary infections. Pyocyanin induces oxidative stress by generating reactive oxygen and nitrogen species which disrupt essential defense mechanisms in respiratory epithelium. Pyocyanin increases airway barrier permeability and facilitates bacterial invasion. Pyocyanin also impairs mucociliary clearance by damaging ciliary function, resulting in mucus accumulation and airway obstruction. Furthermore, it modulates immune responses by promoting the production of pro-inflammatory cytokines, accelerating neutrophil apoptosis, and inducing excessive neutrophil extracellular trap formation, which exacerbates lung tissue damage. Additionally, pyocyanin disrupts macrophage phagocytic function, hindering the clearance of apoptotic cells and perpetuating inflammation. It also triggers mucus hypersecretion by inactivating the transcription factor FOXA2 and enhancing the IL-4/IL-13-STAT6 and EGFR-AKT/ERK1/2 signaling pathways, leading to goblet cell metaplasia and increased mucin production. Insights into the role of pyocyanin in P. aeruginosa infections may reveal potential therapeutic strategies to alleviate the severity of infections in chronic respiratory diseases including cystic fibrosis (CF) and chronic obstructive pulmonary disease (COPD).

PMID:40196115 | PMC:PMC11973339 | DOI:10.3389/fimmu.2025.1550724

J Law Med Ethics. 2025 Apr 8:1-9. doi: 10.1017/jme.2025.48. Online ahead of print.

ABSTRACT

Genome editing, prominently led by the revolutionary CRISPR-Cas9 technology, is a powerful tool with significant applications in diverse fields, particularly in medicine and agriculture. It empowers scientists with the ability to effect precise genetic modifications, thereby potentially paving the way for advanced treatments for genetic disorders such as Huntington's disease, hemophilia, and cystic fibrosis. Yet, the significant capabilities of this technology also brings to the fore a myriad of intricate bioethical, legal, and regulatory dilemmas. In light of these complexities, this article endeavors to conduct a comprehensive scoping review of the existing literature on the most significant ethical implications emanating from genome editing. In conducting this review, we utilized the power of software tools like EndNote and Rayyan to aid in the systematic and thorough review of the literature. EndNote, a reference management software, was instrumental in organizing and managing the references and bibliographies, while Rayyan, a web application designed for managing and screening records for systematic and scoping reviews, proved crucial in the import and management of text records for the review.The review identified as main aspects of ethical, bioethical and medico-legal interest the exacerbation of social inequalities, safety concerns such as off-target mutations and immunological risks, ecological and evolutionary implications, and challenges to human dignity. It highlights the necessity for equitable access, rigorous regulation, and public engagement to address these issues responsibly.The ultimate objective of this article is to underscore the importance of an informed and inclusive dialogue regarding genome editing. Such dialogue is pivotal for fostering responsible innovation in this rapidly advancing field, ensuring that scientific progress aligns with ethical considerations. By presenting a comprehensive examination of the ethical implications of genome editing, we aim to contribute to this ongoing dialogue and promote a balanced and nuanced understanding of this impactful technology.

PMID:40195291 | DOI:10.1017/jme.2025.48

Front Cell Dev Biol. 2025 Mar 24;13:1549811. doi: 10.3389/fcell.2025.1549811. eCollection 2025.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA) represent the primary liver cancer types. Traditional diagnostic techniques, reliant on radiologist interpretation, are both time-intensive and often inadequate for detecting the less prevalent CCA. There is an emergent need to explore automated diagnostic methods using deep learning to address these challenges.

METHODS: This study introduces HTRecNet, a novel deep learning framework for enhanced diagnostic precision and efficiency. The model incorporates sophisticated data augmentation strategies to optimize feature extraction, ensuring robust performance even with constrained sample sizes. A comprehensive dataset of 5,432 histopathological images was divided into 5,096 for training and validation, and 336 for external testing. Evaluation was conducted using five-fold cross-validation and external validation, applying metrics such as accuracy, area under the receiver operating characteristic curve (AUC), and Matthews correlation coefficient (MCC) against established clinical benchmarks.

RESULTS: The training and validation cohorts comprised 1,536 images of normal liver tissue, 3,380 of HCC, and 180 of CCA. HTRecNet showed exceptional efficacy, consistently achieving AUC values over 0.99 across all categories. In external testing, the model reached an accuracy of 0.97 and an MCC of 0.95, affirming its reliability in distinguishing between normal, HCC, and CCA tissues.

CONCLUSION: HTRecNet markedly enhances the capability for early and accurate differentiation of HCC and CCA from normal liver tissues. Its high diagnostic accuracy and efficiency position it as an invaluable tool in clinical settings, potentially transforming liver cancer diagnostic protocols. This system offers substantial support for refining diagnostic workflows in healthcare environments focused on liver malignancies.

PMID:40196844 | PMC:PMC11973358 | DOI:10.3389/fcell.2025.1549811

Bioinform Adv. 2025 Apr 2;5(1):vbaf021. doi: 10.1093/bioadv/vbaf021. eCollection 2025.

ABSTRACT

MOTIVATION: Volumetric electron microscopy (VEM) enables nanoscale resolution three-dimensional imaging of biological samples. Identification and labeling of organelles, cells, and other structures in the image volume is required for image interpretation, but manual labeling is extremely time-consuming. This can be automated using deep learning segmentation algorithms, but these traditionally require substantial manual annotation for training and typically these labeled datasets are unavailable for new samples.

RESULTS: We show that transfer learning can help address this challenge. By pretraining on VEM data from multiple mammalian tissues and organelle types and then fine-tuning on a target dataset, we segment multiple organelles at high performance, yet require a relatively small amount of new training data. We benchmark our method on three published VEM datasets and a new rat liver dataset we imaged over a 56×56×11 μ m volume measuring 7000×7000×219 px using serial block face scanning electron microscopy with corresponding manually labeled mitochondria and endoplasmic reticulum structures. We further benchmark our approach against the Segment Anything Model 2 and MitoNet in zero-shot, prompted, and fine-tuned settings.

AVAILABILITY AND IMPLEMENTATION: Our rat liver dataset's raw image volume, manual ground truth annotation, and model predictions are freely shared at github.com/Xrioen/cross-tissue-transfer-learning-in-VEM.

PMID:40196751 | PMC:PMC11974384 | DOI:10.1093/bioadv/vbaf021

bioRxiv [Preprint]. 2025 Mar 26:2025.03.23.644838. doi: 10.1101/2025.03.23.644838.

ABSTRACT

Object tracking in microscopy videos is crucial for understanding biological processes. While existing methods often require fine-tuning tracking algorithms to fit the image dataset, here we explored an alternative paradigm: augmenting the image time-lapse dataset to fit the tracking algorithm. To test this approach, we evaluated whether generative video frame interpolation can augment the temporal resolution of time-lapse microscopy and facilitate object tracking in multiple biological contexts. We systematically compared the capacity of Latent Diffusion Model for Video Frame Interpolation (LDMVFI), Real-time Intermediate Flow Estimation (RIFE), Compression-Driven Frame Interpolation (CDFI), and Frame Interpolation for Large Motion (FILM) to generate synthetic microscopy images derived from interpolating real images. Our testing image time series ranged from fluorescently labeled nuclei to bacteria, yeast, cancer cells, and organoids. We showed that the off-the-shelf frame interpolation algorithms produced bio-realistic image interpolation even without dataset-specific retraining, as judged by high structural image similarity and the capacity to produce segmentations that closely resemble results from real images. Using a simple tracking algorithm based on mask overlap, we confirmed that frame interpolation significantly improved tracking across several datasets without requiring extensive parameter tuning and capturing complex trajectories that were difficult to resolve in the original image time series. Taken together, our findings highlight the potential of generative frame interpolation to improve tracking in time-lapse microscopy across diverse scenarios, suggesting that a generalist tracking algorithm for microscopy could be developed by combining deep learning segmentation models with generative frame interpolation.

PMID:40196554 | PMC:PMC11974701 | DOI:10.1101/2025.03.23.644838

bioRxiv [Preprint]. 2025 Mar 27:2025.03.24.644668. doi: 10.1101/2025.03.24.644668.

ABSTRACT

Convolutional neural networks (CNNs) have become powerful tools for population genomic inference, yet understanding which genomic features drive their performance remains challenging. We introduce ConfuseNN, a method that systematically shuffles input haplotype matrices to disrupt specific population genetic features and evaluate their contribution to CNN performance. By sequentially removing signals from linkage disequilibrium, allele frequency, and other population genetic patterns in test data, we evaluate how each feature contributes to CNN performance. We applied ConfuseNN to three published CNNs for demographic history and selection inference, confirming the importance of specific data features and identifying limitations of network architecture and of simulated training and testing data design. ConfuseNN provides an accessible biologically motivated framework for interpreting CNN behavior across different tasks in population genetics, helping bridge the gap between powerful deep learning approaches and traditional population genetic theory.

PMID:40196528 | PMC:PMC11974698 | DOI:10.1101/2025.03.24.644668

Front Hum Neurosci. 2025 Mar 24;19:1549698. doi: 10.3389/fnhum.2025.1549698. eCollection 2025.

ABSTRACT

Prosthetic vision systems aim to restore functional sight for visually impaired individuals by replicating visual perception by inducing phosphenes through electrical stimulation in the visual cortex, yet there remain challenges in visual representation strategies such as including gaze information and task-dependent optimization. In this paper, we introduce Point-SPV, an end-to-end deep learning model designed to enhance object recognition in simulated prosthetic vision. Point-SPV takes an initial step toward gaze-based optimization by simulating viewing points, representing potential gaze locations, and training the model on patches surrounding these points. Our approach prioritizes task-oriented representation, aligning visual outputs with object recognition needs. A behavioral gaze-contingent object discrimination experiment demonstrated that Point-SPV outperformed a conventional edge detection method, by facilitating observers to gain a higher recognition accuracy, faster reaction times, and a more efficient visual exploration. Our work highlights how task-specific optimization may enhance representations in prosthetic vision, offering a foundation for future exploration and application.

PMID:40196449 | PMC:PMC11973266 | DOI:10.3389/fnhum.2025.1549698

Front Digit Health. 2025 Mar 24;7:1507159. doi: 10.3389/fdgth.2025.1507159. eCollection 2025.

ABSTRACT

This paper investigates the importance of Trustworthy Machine Learning (ML) in the context of Multiple Sclerosis (MS) research and care. Due to the complex and individual nature of MS, the need for reliable and trustworthy ML models is essential. In this paper, key aspects of trustworthy ML, such as out-of-distribution generalization, explainability, uncertainty quantification and calibration are explored, highlighting their significance for healthcare applications. Challenges in integrating these ML tools into clinical workflows are addressed, discussing the difficulties in interpreting AI outputs, data diversity, and the need for comprehensive, quality data. It calls for collaborative efforts among researchers, clinicians, and policymakers to develop ML solutions that are technically sound, clinically relevant, and patient-centric.

PMID:40196398 | PMC:PMC11973328 | DOI:10.3389/fdgth.2025.1507159

Front Med (Lausanne). 2025 Mar 24;12:1547588. doi: 10.3389/fmed.2025.1547588. eCollection 2025.

ABSTRACT

BACKGROUND: Early diagnosis of non-union fractures is vital for treatment planning, yet studies using bone morphometric parameters for this purpose are scarce. This study aims to create a fracture micro-CT image dataset, design a deep learning algorithm for fracture segmentation, and develop an early diagnosis model for fracture non-union.

METHODS: Using fracture animal models, micro-CT images from 12 rats at various healing stages (days 1, 7, 14, 21, 28, and 35) were analyzed. Fracture lesion frames were annotated to create a high-resolution dataset. We proposed the Vision Mamba Triplet Attention and Edge Feature Decoupling Module UNet (VM-TE-UNet) for fracture area segmentation. And we extracted bone morphometric parameters to establish an early diagnostic evaluation system for the non-union of fractures.

RESULTS: A dataset comprising 2,448 micro-CT images of the rat fracture lesions with fracture Region of Interest (ROI), bone callus and healing characteristics was established and used to train and test the proposed VM-TE-UNet which achieved a Dice Similarity Coefficient of 0.809, an improvement over the baseline's 0.765, and reduced the 95th Hausdorff Distance to 13.1. Through ablation studies, comparative experiments, and result analysis, the algorithm's effectiveness and superiority were validated. Significant differences (p < 0.05) were observed between the fracture and fracture non-union groups during the inflammatory and repair phases. Key indices, such as the average CT values of hematoma and cartilage tissues, BS/TS and BS/TV of mineralized cartilage, BS/TV of osteogenic tissue, and BV/TV of osteogenic tissue, align with clinical methods for diagnosing fracture non-union by assessing callus presence and local soft tissue swelling. On day 14, the early diagnosis model achieved an AUC of 0.995, demonstrating its ability to diagnose fracture non-union during the soft-callus phase.

CONCLUSION: This study proposed the VM-TE-UNet for fracture areas segmentation, extracted micro-CT indices, and established an early diagnostic model for fracture non-union. We believe that the prediction model can effectively screen out samples of poor fracture rehabilitation caused by blood supply limitations in rats 14 days after fracture, rather than the widely accepted 35 or 40 days. This provides important reference for the clinical prediction of fracture non-union and early intervention treatment.

PMID:40196347 | PMC:PMC11973290 | DOI:10.3389/fmed.2025.1547588

medRxiv [Preprint]. 2025 Mar 25:2025.03.24.25324556. doi: 10.1101/2025.03.24.25324556.

ABSTRACT

Artificial intelligence (AI) applied to single-cell data has the potential to transform our understanding of biological systems by revealing patterns and mechanisms that simpler traditional methods miss. Here, we develop a general-purpose, interpretable AI pipeline consisting of two deep learning models: the Multi- Input Set Transformer++ (MIST) model for prediction and the single-cell FastShap model for interpretability. We apply this pipeline to a large set of routine clinical data containing single-cell measurements of circulating red blood cells (RBC), white blood cells (WBC), and platelets (PLT) to study population fluxes and homeostatic hematological mechanisms. We find that MIST can use these single-cell measurements to explain 70-82% of the variation in blood cell population sizes among patients (RBC count, PLT count, WBC count), compared to 5-20% explained with current approaches. MIST's accuracy implies that substantial information on cellular production and clearance is present in the single-cell measurements. MIST identified substantial crosstalk among RBC, WBC, and PLT populations, suggesting co-regulatory relationships that we validated and investigated using interpretability maps generated by single-cell FastShap. The maps identify granular single-cell subgroups most important for each population's size, enabling generation of evidence-based hypotheses for co-regulatory mechanisms. The interpretability maps also enable rational discovery of a single-WBC biomarker, "Down Shift", that complements an existing marker of inflammation and strengthens diagnostic associations with diseases including sepsis, heart disease, and diabetes. This study illustrates how single-cell data can be leveraged for mechanistic inference with potential clinical relevance and how this AI pipeline can be applied to power scientific discovery.

PMID:40196278 | PMC:PMC11974774 | DOI:10.1101/2025.03.24.25324556

medRxiv [Preprint]. 2025 Mar 26:2025.03.25.25324627. doi: 10.1101/2025.03.25.25324627.

ABSTRACT

Accurate understanding of biological aging and the impact of environmental stressors is crucial for understanding cardiovascular health and identifying patients at risk for adverse outcomes. Chronological age stands as perhaps the most universal risk predictor across virtually all populations and diseases. While chronological age is readily discernible, efforts to distinguish between biologically older versus younger individuals can, in turn, potentially identify individuals with accelerated versus delayed cardiovascular aging. This study presents a deep learning artificial intelligence (AI) approach to predict age from echocardiogram videos, leveraging 2,610,266 videos from 166,508 studies from 90,738 unique patients and using the trained models to identify features of accelerated and delayed aging. Leveraging multi-view echocardiography, our AI age prediction model achieved a mean absolute error (MAE) of 6.76 (6.65 - 6.87) years and a coefficient of determination (R 2 ) of 0.732 (0.72 - 0.74). Stratification by age prediction revealed associations with increased risk of coronary artery disease, heart failure, and stroke. The age prediction can also identify heart transplant recipients as a discontinuous prediction of age is seen before and after a heart transplant. Guided back propagation visualizations highlighted the model's focus on the mitral valve, mitral apparatus, and basal inferior wall as crucial for the assessment of age. These findings underscore the potential of computer vision-based assessment of echocardiography in enhancing cardiovascular risk assessment and understanding biological aging in the heart.

PMID:40196275 | PMC:PMC11974980 | DOI:10.1101/2025.03.25.25324627