SEARCH · PubMed Health

Results for “Convolutional Neural Networks”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2Linked to original sources

PubMed2026

Artificial intelligence in treatment prediction for skeletal Class III malocclusion: A systematic review.

In skeletal Class III patients, treatment options range from orthodontics to orthognathic surgery. Choosing the optimal approach requires a comprehensive clinical evaluation, which may be supported by AI tools. The aim of this study was to assess the performance of AI models in predicting the need for orthognathic surgery and in identifying predictors influencing treatment decisions. A PRISMA-guided electronic database search (PubMed, Web of Science; 2009-2024; English/French) was performed to identify studies using machine learning (ML) or deep learning (DL) on cephalometric and clinical data. After screening and assessment for eligibility, 15 studies were critically appraised. Model performance was summarized using accuracy, sensitivity, specificity, and the area under the curve (AUC). ML algorithms (particularly Random Forest and XGBoost) and DL models (ResNet-based convolutional neural networks (CNNs)) achieved high accuracy for predicting surgical need. Frequently selected predictors included Wits appraisal, ANB angle, the maxillomandibular ratio (Mx/Md), overjet, and the divergence of the lower gonial angle. AI methods show promise for assisting treatment decisions in Class III malocclusion, with Random Forest and XGBoost performing well on tabular cephalometric data and CNNs on imaging. Larger, multicentre datasets and external validation are needed to improve reliability, address bias, and support clinical implementation.

Humans↗

PubMed2026

Leveraging Interradiomic Feature Relationships for Enhanced Prediction of Distant Metastasis and Characterization of Heterogeneity in Head and Neck Cancer.

PURPOSE: Distant metastasis remains a major cause of treatment failure in head and neck (HN) cancer, highlighting the need for more accurate early risk stratification. This study developed and validated a deep radiomics framework to characterize tumor heterogeneity from pretreatment computed tomography (CT) images and improve prediction of distant metastasis-free survival (DMFS). METHODS AND MATERIALS: This multicenter study included 3421 patients with HN cancer from 4 cohorts across 12 institutions. Radiomics features were extracted from primary tumors and transformed into OmicsMaps, a structured representation that spatially organizes interfeature relationships to facilitate learning of complex prognostic patterns. A convolutional neural network was trained to derive prognostic signatures, which were integrated with key clinical variables to construct an OmicsMap-clinical fusion model for patient risk stratification. Model performance was assessed using the concordance index (C-index) and time-dependent area under the receiver operating characteristic curve (AUC) in the CT Images from Large Head and Neck Cohort (RADCURE), HEAD-NECK-RADIOMICS-HN1 (HN1), and Head-Neck-Positron Emission Tomography-Computed Tomography (HN-PET-CT) cohorts. Radiogenomic analyses using RNA-seq data were conducted in the Cancer Genome Atlas Head-Neck Squamous Cell Carcinoma (TCGA-HNSC) cohort to investigate biological characteristics associated with the imaging-defined risk groups. RESULTS: The OmicsMap achieved C-index values of 0.742, 0.768, and 0.671 in the RADCURE, HN1, and HN-PET-CT cohorts, outperforming the conventional radiomics approach by 5.40%-6.37%. Incorporating clinical variables further improved generalizability, yielding a C-index of 0.864 (HN1) and 0.730 (HN-PET-CT), with time-dependent AUC of 0.727-0.895. The fusion model consistently stratified patients into distinct high- and low-risk groups for both DMFS and overall survival across cohorts (P <.01). Radiogenomic analyses revealed enrichment of immune-related pathways in the low-risk group, whereas the high-risk group exhibited a more aggressive phenotype enriched for proliferation, hypoxia, and epithelial-mesenchymal transition pathways, along with a fibrosis-prone tumor microenvironment characterized by extracellular matrix remodeling. CONCLUSIONS: Modeling interradiomic feature relationships using the OmicsMap representation substantially improves CT-based prediction of DMFS and characterization of tumor heterogeneity in HN cancer, supporting precision risk stratification in clinical oncology.

Journal Article↗

PubMed2026

Artificial intelligence (AI) uses in stereotactic radiosurgery (SRS): diagnosis with brain metastasis (BM) - A systematic review.

BACKGROUND: Brain metastases (BM) are the most common intracranial tumors in adults, and stereotactic radiosurgery (SRS) has become a mainstay of management. However, several diagnostic challenges persist in the SRS pathway, particularly the differentiation of radiation necrosis (RN) from true tumor progression, which conventional MRI and even advanced imaging techniques often cannot reliably resolve. Recent advances in artificial intelligence (AI) offer the potential to address these diagnostic limitations. This systematic review synthesizes current literature on AI applications for MRI-based diagnostic decision support in BM patients undergoing SRS, with a focus on radiomics and deep learning tools for distinguishing RN from progression, classifying molecular and histologic subtypes, and predicting treatment response. METHODS: A systematic review was performed in accordance with PRISMA guidelines. PubMed, Web of Science, and Scopus were searched using a targeted query combining terms related to AI, brain metastasis, diagnosis or imaging, and SRS. After screening 483 records and applying strict inclusion and exclusion criteria, 18 studies published between 2015 and 2025 were included. Data were extracted on study design, cohort characteristics, imaging modality, AI methodology, validation strategy, and reported diagnostic performance. RESULTS: Among the 18 included studies, AI models demonstrated strong performance across diagnostic tasks in the BM-SRS pathway. The differentiation of RN from true tumor progression was the most extensively studied application, addressed by 14 of 18 studies, with reported AUCs ranging from 0.71 to 0.94. Support vector machines, random-forest ensembles, convolutional neural networks, and transformer-based multimodal architectures were widely used. The literature evolved from single-sequence radiomic classifiers in 2018 to multimodal deep learning frameworks fusing imaging with clinical and genomic data in 2025. Contrast-enhanced T1-weighted MRI was the dominant imaging input, and texture-based radiomic features (GLCM, GLSZM, GLDM, and wavelet-derived features) were the most consistently predictive. The highest-performing models reached AUCs of 0.85-0.91 through multimodal integration of imaging with clinical and genomic features, and consistently outperformed expert neuroradiologist read on matched cases. Remaining studies addressed longitudinal segmentation-based detection of local failure and adverse radiation effects, BRAF mutation status in melanoma BM, early Gamma Knife treatment response, and primary tumor histology classification, with more variable performance. CONCLUSION: AI models, particularly those integrating MRI-derived radiomic features with clinical and genomic data, show high accuracy in supporting diagnostic decisions for BM patients treated with SRS. The post-SRS differentiation of radiation necrosis from true tumor progression has reached the greatest level of maturity and is closest to clinical translation, with potential to reduce unnecessary biopsies, personalize surveillance intervals, and rationalize treatment-pathway decisions. Other diagnostic applications, including molecular subtyping and primary tumor histology classification, remain exploratory and require further multicenter validation. Integration of AI tools into multidisciplinary tumor-board workflows, combined with prospective validation and standardized reporting, will be essential to realize the full clinical benefits of AI in SRS for brain metastases.

Humans↗

PubMed2026

Data-driven approaches in green microbiology: strategies for plant growth-promoting bacteria.

Plant growth-promoting bacteria (PGPB) are gaining attention as scalable biological solutions to enhance crop productivity and resilience. However, accurately identifying and characterizing PGPB remains challenging, particularly under variable environmental conditions where microbial functions are context-dependent and shaped by complex plant-microbe interactions. Advances in high-throughput sequencing have shifted the field from culture-dependent approaches to genome-informed strategies, enabling large-scale taxonomic and functional profiling. Although trait-based databases support the prediction of plant-beneficial genes, they capture only a fraction of the underlying biological complexity and often require labor-intensive analyses. Machine learning (ML) and deep learning (DL) have emerged as powerful tools to integrate genomic, physiological, and ecological data, enabling the prioritization of candidate strains with plant growth-promoting potential. To evaluate advances in the field, we conducted a systematic review of studies integrating ML and DL with PGPB characterization, assessing algorithm selection, performance, and target plant systems. Across 248 observations, only 6.0% of studies directly addressed PGPB screening, whereas the majority (77.4%) focused on plant disease detection, revealing a substantial gap in the application of AI to beneficial microorganisms for plant growth. Convolutional neural networks (CNNs) were the most frequently applied algorithms, largely driven by image-based phenotyping tasks. Overall, the field is constrained by limited datasets, high computational demands, and challenges in modeling multispecies and host-associated interactions. We highlight the need for integrative and interpretable ML and DL frameworks that bridge genomic data and functional validation. Such approaches represent a promising path toward scalable, data-driven discovery and deployment of bioinoculants in sustainable agriculture.

Agriculture↗

PubMed2026

Perseus: Lineage-Aware Refinement of Kraken2 Taxonomic Classification for Long Read Metagenomes.

MOTIVATION: Long-read metagenomic sequencing improves assembly contiguity and enables genome-resolved analysis of complex microbial communities, but accurate taxonomic classification of long reads and assembled contigs remains challenging. Highly scalable k-mer-based classifiers such as Kraken2 frequently over-assign fine-rank taxonomic labels when applied to long-read data, producing high false positive classification rates driven by sparse or localized k-mer matches, particularly in microbiomes with extensive taxonomic novelty. RESULTS: We present Perseus, a lineage-aware confidence estimation framework for taxonomic classification that models the spatial distribution and hierarchical consistency of k-mer evidence along sequences. This formulation reframes taxonomic classification as a hierarchical confidence estimation problem rather than a single-rank prediction task. Perseus refines k-mer-level taxonomic signals from Kraken2 using a multi-headed convolutional neural network that estimates calibrated confidence scores for taxonomic correctness at each canonical rank. Using these estimates, Perseus confirms assignments, backs off to higher taxonomic ranks, or abstains when evidence is insufficient, prioritizing correctness and lineage consistency over overly specific assignments. Across simulations of taxonomic novelty and real-world metagenomic datasets, Perseus consistently and substantially reduces the false assignment rate while improving precision and lineage-consistent accuracy. These improvements are most pronounced for long reads and assembled contigs, where spatial context enables reliable discrimination between consistent taxonomic signal and spurious matches. AVAILABILITY AND IMPLEMENTATION: Perseus integrates with existing Kraken2 workflows and is available at https://github.com/matnguyen/perseus.

Journal Article↗

PubMed2026

Deep learning reveals genomic regions introgressed between two recurrently hybridizing lynx species.

Recently, diverged species with overlapping distributional ranges have high chances of hybridizing and if hybrids are viable, genomic material can be transferred between species in a process called introgression. To characterize the patterns and consequences of introgression in species with historically low population sizes and recent steep declines resulting in genetic erosion, we analyze the Iberian and Eurasian lynx (EL) as an illustrative and relevant case study. While genome-wide introgression was already detected, here we apply a method using a deep convolutional neural network to detect specific regions of the genome with signals of introgression in three populations of these two species. Over 6% of the genome of both Iberian lynx and ELw shows introgression from the other species, compared with only 2% in the ELs. This observation, along with the results from demographic modeling, suggests that the ELw population is genetically closest to the source of EL introgression, a probably now extinct group that coexisted with the Iberian lynx in Southern Europe and Northern Iberia until recently. As predicted by theory, introgression was generally higher in populations with smaller effective sizes and in genomic regions of high recombination. However, the Iberian lynx did not show higher overall introgression than the more abundant ELw, and coding regions introgressed as frequently as intergenic regions. Local genetic diversity is boosted approximately 3-fold in genomic windows where introgression occurs, potentially including the adaptively relevant and highly diverse MHC region of the Iberian lynx.

Animals↗

PubMed2026

The Role of Artificial Intelligence Combined With Digital Cholangioscopy for Indeterminant and Malignant Biliary Strictures: A Systematic Review and Meta-analysis.

BACKGROUND: Current endoscopic retrograde cholangiopancreatography (ERCP) and cholangioscopic-based diagnostic sampling for indeterminant biliary strictures remain suboptimal. Artificial intelligence (AI)-based algorithms by means of computer vision in machine learning have been applied to cholangioscopy in an effort to improve diagnostic yield. The aim of this study was to perform a systematic review and meta-analysis to evaluate the diagnostic performance of AI-based diagnostic performance of AI-associated cholangioscopic diagnosis of indeterminant or malignant biliary strictures. METHODS: Individualized searches were developed in accordance with PRISMA and MOOSE guidelines, and meta-analysis according to Cochrane Diagnostic Test Accuracy working group methodology. A bivariate model was used to compute pooled sensitivity and specificity, likelihood ratio, diagnostic odds ratio, and summary receiver operating characteristics curve (SROC). RESULTS: Five studies (n=675 lesions; a total of 2,685,674 cholangioscopic images) were included. All but one study analyzed a deep learning AI-based system using a convoluted neural network (CNN) with an average image processing speed of 30 to 60 frames per second. The pooled sensitivity and specificity were 95% (95% CI: 85-98) and 88% (95% CI: 76-94), with a diagnostic accuracy (SROC) of 97% (95% CI: 95-98). Sensitivity analysis of CNN studies (4 studies, 538 patients) demonstrated a pooled sensitivity, specificity, and accuracy (SROC) of 95% (95% CI: 82-99), 88% (95% CI: 72-95), and 97% (95% CI: 95-98), respectively. CONCLUSIONS: Artificial intelligence-based machine learning of cholangioscopy images appears to be a promising modality for the diagnosis of indeterminant and malignant biliary strictures.

Humans↗

PubMed2025

Prediction and functional interpretation of inter-chromosomal genome architecture from DNA sequence with TwinC.

Three-dimensional nuclear DNA architecture comprises well-studied intra-chromosomal (cis) folding and less characterized inter-chromosomal (trans) interfaces. Current predictive models of 3D genome folding can effectively infer pairwise cis-chromatin interactions from the primary DNA sequence but generally ignore trans contacts. There is an unmet need for robust models of trans-genome organization that provide insights into their underlying principles and functional relevance. We present TwinC, an interpretable convolutional neural network model that reliably predicts trans contacts measurable through proximity ligation-dependent (in situ and intact Hi-C) and independent (DNA SPRITE) genome-wide chromatin conformation assays. . TwinC uses a paired sequence design from replicate Hi-C experiments to learn single base pair relevance in trans interactions across two stretches of DNA. The method achieves high predictive accuracy (AUROC=0.80) on a cross-chromosomal test set from in situ and intact Hi-C experiments in heart tissue. Furthermore, we train TwinC using in situ Hi-C data from the widely used GM12878 cell line and validate its performance with orthogonal DNA SPRITE assay in the same cell type. Mechanistically, the neural network learns the importance of compartments, chromatin accessibility, clustered transcription factor binding and G-quadruplexes in forming trans contacts. In summary, TwinC models and interprets trans genome architecture, shedding light on this poorly understood aspect of gene regulation.

Journal Article↗

PubMed2025

Efficient detection and characterization of targets of natural selection using transfer learning.

Natural selection leaves detectable patterns of altered spatial diversity within genomes, and identifying affected regions is crucial for understanding species evolution. Recently, machine learning approaches applied to raw population genomic data have been developed to uncover these adaptive signatures. Convolutional neural networks (CNNs) are particularly effective for this task, as they handle large data arrays while maintaining element correlations. However, shallow CNNs may miss complex patterns due to their limited capacity, while deep CNNs can capture these patterns but require extensive data and computational power. Transfer learning addresses these challenges by utilizing a deep CNN pre-trained on a large dataset as a feature extraction tool for downstream classification and evolutionary parameter prediction. This approach reduces extensive training data generation requirements and computational needs while maintaining high performance. In this study, we developed TrIdent, a tool that uses transfer learning to enhance detection of adaptive genomic regions from image representations of multilocus variation. We evaluated TrIdent across various genetic, demographic, and adaptive settings, in addition to unphased data and other confounding factors. TrIdent demonstrated improved detection of adaptive regions compared to recent methods using similar data representations. We further explored model interpretability through class activation maps and adapted TrIdent to infer selection parameters for identified adaptive candidates. Using whole-genome haplotype data from European and African populations, TrIdent effectively recapitulated known sweep candidates and identified novel cancer, and other disease-associated genes as potential sweeps.

Journal Article↗

PubMed2025

Interpreting the CTCF-mediated sequence grammar of genome folding with AkitaV2.

Interphase mammalian genomes are folded in 3D with complex locus-specific patterns that impact gene regulation. CTCF (CCCTC-binding factor) is a key architectural protein that binds specific DNA sites, halts cohesin-mediated loop extrusion, and enables long-range chromatin interactions. There are hundreds of thousands of annotated CTCF-binding sites in mammalian genomes; disruptions of some result in distinct phenotypes, while others have no visible effect. Despite their importance, the determinants of which CTCF sites are necessary for genome folding and gene regulation remain unclear. Here, we update and utilize Akita, a convolutional neural network model, to extract the sequence preferences and grammar of CTCF contributing to genome folding. Our analyses of individual CTCF sites reveal four predictions: (i) only a small fraction of genomic sites are impactful; (ii) impact is highly dependent on sequences flanking the core CTCF binding motif; (iii) core and flanking nucleotides contribute largely additively to the overall impact of a site; (iv) sites created as combinations of different core and flanking sequences have impacts proportional to the product of their average impacts, i.e. they are broadly compatible. Our analysis of collections of CTCF sites make two predictions for multi-motif grammar: (i) insulation strength depends on the number of CTCF sites within a cluster, and (ii) pattern formation is governed by the orientation and spacing of these sites, rather than any inherent specialization of the CTCF motifs themselves. In sum, we present a framework for using neural network models to probe the sequences instructing genome folding and provide a number of predictions to guide future experimental inquiries.

CCCTC-Binding Factor↗

PubMed2026

Enterocutaneous Fistula-Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model.

BACKGROUND: Predicting enterocutaneous fistula (ECF)-associated sepsis and mortality poses significant challenges in digital health care due to the disease's complexity and heterogeneous clinical manifestations. Current approaches that rely on single-modal data or traditional scoring systems often fail to capture the intricate immune-inflammatory dynamics and multisystem involvement in patients with ECF. OBJECTIVE: This study aims to develop an artificial intelligence (AI)-driven multimodal fusion model integrating clinical, imaging, and transcriptomic data for early prediction of ECF-associated sepsis and 28-day mortality, addressing the limitations of conventional single-dimensional models. METHODS: This study leveraged publicly available datasets (Medical Information Mart for Intensive Care III [MIMIC-III], electronic Intensive Care Unit [eICU], and The Cancer Genome Atlas) to construct a multimodal framework. Clinical parameters were processed using Extreme Gradient Boosting, abdominal imaging features were extracted via convolutional neural networks, and transcriptomic profiles were analyzed with variational autoencoders. A Transformer-based fusion network was employed for joint prediction and validated through cross-validation and external testing. Key features were identified using Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretability algorithms, while immune regulatory mechanisms were explored via weighted gene co-expression network analysis. RESULTS: The multimodal model achieved an area under the curve (AUC) of 0.89 for predicting sepsis and 28-day mortality, outperforming unimodal models (clinical-only model, AUC 0.72, and imaging-only model, AUC 0.78). Critical predictors included Sequential Organ Failure Assessment score, lactate levels, intra-abdominal free fluid on imaging, and immunoregulatory genes (programmed death-ligand 1 [PD-L1] and indoleamine 2,3-dioxygenase 1 [IDO1]). Mechanistic analysis revealed distinct immune reprogramming in patients with sepsis, characterized by increased regulatory T cells and M2 macrophages, along with downregulated cluster of differentiation 8+ (CD8+) T cells. CONCLUSIONS: This multimodal AI model offers an innovative digital solution in medical informatics, enabling precise early risk stratification for ECF-associated sepsis. By integrating multisource data and providing interpretable insights into immune-inflammatory pathways, the model enhances health care quality for patients with ECF and paves the way for personalized intervention strategies.

Humans↗

PubMed2026

Development of a PCR-based technique for genotyping UGT1A1 gene and distribution of rs3064744 alleles in the Russian population.

BACKGROUND: Accurate determination of tandem thymine-adenine (TA) repeat numbers in the UGT1A1 promoter region (rs3064744) is essential for diagnosing Gilbert's syndrome and personalizing therapy with toxic agents like irinotecan and atazanavir. However, traditional polymerase chain reaction (PCR) assays face severe limitations due to the AT-rich sequence and overlapping melting temperatures (Tm) of the highly homologous 7TA and 8TA alleles. In this context, melting curve analysis (MCA) employing fluorophore-quencher systems has emerged as a promising alternative. The purpose of this study was to develop a novel genotyping approach combining optimized aPCR-MCA analysis with an automated classifier to overcome the limitations posed by the differentiation of highly homologous alleles and to demonstrate its practical application, providing the distribution of rs3064744 genotypes across four regional cohorts of the Russian population. METHODS: A specialized Dual Head 1D-convolutional neural network (1D-CNN) ensemble with Test-Time Augmentation (TTA) was developed. The model was trained and internally validated on 1,620 engineered plasmid samples, and independently evaluated on an external clinical test set of 440 unique patient genomic DNA specimens. Real-time PCR was performed on CFX96 and DTprime platforms. Additionally, population-wide screening was conducted on 997 archival clinical samples from Moscow, Sakha (Yakutia), Dagestan, and Rostov regions. RESULTS: While 5TA and 6TA alleles were easily separated, absolute Tm distributions of 7TA and 8TA alleles overlapped significantly, and non-uniform Tm shifts of 0.8 °C-1.4 °C occurred across platforms. Conventional absolute Tm thresholding was therefore inadequate. By assessing relative morphological curve divergence against co-amplified 7TA/7TA and 7TA/8TA reference anchors, the 1D-CNN ensemble neutralized instrument noise. It achieved 100% accuracy on internal validation and 100% concordance (440/440) with clinical reference pyrosequencing. Population screening revealed that Dagestan, Yakutia, and Rostov cohorts closely align with the European population. Rare 5TA and 8TA alleles were detected at low frequencies in Yakutia and Moscow. CONCLUSION: Combining LNA-modified aPCR-MCA with a comparative 1D-CNN model successfully circumvents thermodynamic limitations and eliminates human operator bias. This integrated system offers an accessible, high-throughput, and clinically valid solution for routine UGT1A1 pharmacogenetic testing.

1D-CNN↗

PubMed2025

Improving spliced alignment by modeling splice sites with deep learning.

MOTIVATION: Spliced alignment refers to the alignment of messenger RNA (mRNA) or protein sequences to eukaryotic genomes. It plays a critical role in gene annotation and the study of gene functions. Accurate spliced alignment demands sophisticated modeling of splice sites, but current aligners use simple models, which may affect their accuracy given dissimilar sequences. RESULTS: We implemented minisplice to learn splice signals with a one-dimensional convolutional neural network (1D-CNN) and trained a model with 7,026 parameters for vertebrate and insect genomes. It captures conserved splice signals across phyla and reveals GC-rich introns specific to mammals and birds. We used this model to estimate the empirical splicing probability for every GT and AG in genomes, and modified minimap2 and miniprot to leverage pre-computed splicing probability during alignment. Evaluation on human long-read RNA-seq data and cross-species protein datasets showed our method greatly improves the junction accuracy especially for noisy long RNA-seq reads and proteins of distant homology. AVAILABILITY AND IMPLEMENTATION: https://github.com/lh3/minisplice.

Journal Article↗

PubMed2026

Systematic evaluation of one-dimensional-to-two-dimensional near-infrared spectroscopy transformations with deep learning for quantifying coconut sap adulteration.

Near-infrared (NIR) spectroscopy have limitations when combined with deep learning (DL) algorithms because they rely on low-dimensional datasets. Therefore, we investigated the potential of transforming one-dimensional (1D) NIR spectra into two-dimensional (2D) spectrograms using synchronous and asynchronous techniques and the continuous wavelet transform (CWT) and their effectiveness by integrating with DL for detecting adulteration in coconut sap. NIR spectra (12,500-4000 cm-1) were collected from binary mixtures (0%-100%;w/w). The performance of all DL (convolutional neural networks-CNN, AlexNet and ResNet) models was compared with that of partial least squares (PLS). The models were ranked in the mentioned order based on their performances: 2D-CWT > 2D-asynchronous > 2D-synchronous > 1D/2D-PLS. The important features of the best model can be explained and visualized using gradient-weighted-class-activation-mapping. The findings highlight that the 1D-to-2D NIR data transformation combined with DL is a highly robust approach because it addresses the feature representation gap in NIR data and effectively captures the spatial-spectral correlations.

Spectroscopy, Near-Infrared↗

PubMed2025

Three-dimensional U-Net with transfer learning improves automated whole brain delineation from MRI brain scans of rats, mice, and monkeys.

BACKGROUND: Automated whole-brain delineation (WBD) techniques often struggle to generalize across pre-clinical studies due to variations in animal models, magnetic resonance imaging (MRI) scanners, and tissue contrasts. We developed a 3D U-Net neural network for WBD pre-trained on organophosphate intoxication (OPI) rat brain MRI scans. We used transfer learning (TL) to adapt this OPI-pretrained network to other animal models: rat model of Alzheimer's disease (AD), mouse model of tetramethylenedisulfotetramine (TETS) intoxication, and titi monkey model of social bonding. METHODS: We assessed an OPI-pretrained 3D U-Net across animal models under three conditions: (1) direct application to each dataset; (2) utilizing TL; and (3) training disease-specific U-Net models. For each condition, training dataset size (TDS) was optimized, and output WBDs were compared to manual segmentations for accuracy. RESULTS: The OPI-pretrained 3D U-Net (TDS = 100) achieved the best accuracy [median[min-max]] for the test OPI dataset with a Dice coefficient (DC) = [0.987 [0.977-0.992]] and Hausdorff distance (HD) = [0.86 [0.55-1.27]]mm. TL improved generalization across all models [AD (TDS = 40): DC = 0.987 [0.977-0.992] and HD = 0.72 [0.54-1.00]mm; TETS (TDS = 10): DC = 0.992 [0.984-0.993] and HD = 0.40 [0.31-0.50]mm; Monkey (TDS = 8): DC = 0.977 [0.968-0.979] and HD = 3.03 [2.19-3.91]mm], showing performance comparable to disease-specific networks. CONCLUSIONS: The OPI-pretrained 3D U-Net with TL achieved accuracy comparable to disease-specific networks with reduced training data (TDS ≤ 40 scans) across all models. Future work will focus on developing a multi-region delineation pipeline for pre-clinical MRI brain data, utilizing the proposed WBD as an initial step.

Animals↗

PubMed2026

Artificial Intelligence and Machine Learning Applications in Fibromuscular Dysplasia: Transforming Diagnosis, Risk Stratification, and Clinical Decision-Making.

Fibromuscular dysplasia (FMD) is a non-atherosclerotic vascular disorder with heterogeneous presentations, making diagnosis and management highly dependent on imaging and clinical expertise. This narrative review examines how artificial intelligence (AI) and machine learning (ML) are transforming FMD care. AI-enhanced imaging, particularly convolutional neural network-based analysis, improves detection of the characteristic "string-of-beads" pattern on CT angiography, magnetic resonance angiography, and ultrasound, although FMD-specific validation remains limited. ML models facilitate risk stratification, prediction of disease progression, and early identification of complications such as aneurysms and stroke by integrating clinical, imaging, and genomic data. AI-driven clinical decision support systems further enable personalized treatment selection through pharmacogenomic insights and robot-assisted interventions. Despite promising real-world applications, challenges persist, including limited large-scale datasets, workflow integration, regulatory barriers, and algorithmic bias affecting underrepresented populations. Future advances in explainable AI, federated learning, and digital health integration may enable a shift toward predictive, patient-centered FMD management.

Humans↗

PubMed2026

Integrating histology and spatial transcriptomics via multimodal transformers and contrastive representation learning for accurate gene expression prediction.

Predicting spatial gene expression from Histological images is a fundamental task in understanding tissue organization and molecular phenotypes. However, existing methods often rely on single-model representations or lack effective alignment between image and transcriptomic features. To address these limitations, we propose a unified multimodal learning framework that integrates histological imaging and spatial transcriptomics through a shared latent representation space. Specifically, histological H&E images are encoded by a ResNet50-based convolutional stem and a MobileViT Transformer backbone to extract hierarchical visual representations. Both modalities are projected into a shared latent space via linear-GELU-dropout transformation blocks, enabling cross-modal alignment through a contrastive learning objective that maximizes agreement between the corresponding image and the spot embeddings. Experimental results on the 10x Genomics Visium dataset of human liver tissue demonstrate that MViTGene achieves significantly higher prediction accuracy than existing methods across multiple gene subsets, with improvements of 20%, 33%, and 12% in predicting marker genes, highly expressed genes, and highly variable genes, respectively. The significant improvement in relevance indicates that the model can more accurately capture the true correspondence between tissue morphology and gene expression, therefore enabling more reliable biological interpretation. It provides a computational tool for high-throughput spatial gene expression prediction that balances performance and interpretability.

Humans↗

PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗