J Phys Chem B. 2025 Jan 23. doi: 10.1021/acs.jpcb.4c06190. Online ahead of print.

ABSTRACT

PGLa, an antimicrobial peptide (AMP), primarily exerts its antibacterial effects by disrupting bacterial cell membrane integrity. Previous theoretical studies mainly focused on the binding mechanism of PGLa with membranes, while the mechanism of water pore formation induced by PGLa peptides, especially the role of structural flexibility in the process, remains unclear. In this study, using all-atom simulations, we investigated the entire process of membrane deformation caused by the interaction of PGLa with an anionic cell membrane composed of dimyristoylphosphatidylcholine (DMPC) and dimyristoylphosphatidylglycerol (DMPG). Using a deep learning-based key intermediate identification algorithm, we found that the C-terminal tail plays a crucial role for PGLa insertion into the membrane, and that with its assistance, a variety of water pores formed inside the membrane. Mutation of the tail residues revealed that, in addition to electrostatic and hydrophobic interactions, the flexibility of the tail residues is crucial for peptide insertion and pore formation. The full extension of these flexible residues enhances peptide-peptide and peptide-membrane interactions, guiding the transmembrane movement of PGLa and the aggregation of PGLa monomers within the membrane, ultimately leading to the formation of water-filled pores in the membrane. Overall, this study provides a deep understanding of the transmembrane mechanism of PGLa and similar AMPs, particularly elucidating for the first time the importance of C-terminal flexibility in both insertion and oligomerization processes.

PMID:39847609 | DOI:10.1021/acs.jpcb.4c06190

PLoS One. 2025 Jan 23;20(1):e0317619. doi: 10.1371/journal.pone.0317619. eCollection 2025.

ABSTRACT

This study presents a comprehensive comparative analysis of Machine Learning (ML) and Deep Learning (DL) models for predicting Wind Turbine (WT) power output based on environmental variables such as temperature, humidity, wind speed, and wind direction. Along with Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN), the following ML models were looked at: Linear Regression (LR), Support Vector Regressor (SVR), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). Using a dataset of 40,000 observations, the models were assessed based on R-squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). ET achieved the highest performance among ML models, with an R-squared value of 0.7231 and a RMSE of 0.1512. Among DL models, ANN demonstrated the best performance, achieving an R-squared value of 0.7248 and a RMSE of 0.1516. The results show that DL models, especially ANN, did slightly better than the best ML models. This means that they are better at modeling non-linear dependencies in multivariate data. Preprocessing techniques, including feature scaling and parameter tuning, improved model performance by enhancing data consistency and optimizing hyperparameters. When compared to previous benchmarks, the performance of both ANN and ET demonstrates significant predictive accuracy gains in WT power output forecasting. This study's novelty lies in directly comparing a diverse range of ML and DL algorithms while highlighting the potential of advanced computational approaches for renewable energy optimization.

PMID:39847588 | DOI:10.1371/journal.pone.0317619

PLoS Comput Biol. 2025 Jan 23;21(1):e1012708. doi: 10.1371/journal.pcbi.1012708. eCollection 2025 Jan.

ABSTRACT

The applications of artificial intelligence (AI) and deep learning (DL) are leading to significant advances in cancer research, particularly in analysing histopathology images for prognostic and treatment-predictive insights. However, effective translation of these computational methods requires computational researchers to have at least a basic understanding of histopathology. In this work, we aim to bridge that gap by introducing essential histopathology concepts to support AI developers in their research. We cover the defining features of key cell types, including epithelial, stromal, and immune cells. The concepts of malignancy, precursor lesions, and the tumour microenvironment (TME) are discussed and illustrated. To enhance understanding, we also introduce foundational histopathology techniques, such as conventional staining with hematoxylin and eosin (HE), antibody staining by immunohistochemistry, and including the new multiplexed antibody staining methods. By providing this essential knowledge to the computational community, we aim to accelerate the development of AI algorithms for cancer research.

PMID:39847582 | DOI:10.1371/journal.pcbi.1012708

PLoS One. 2025 Jan 23;20(1):e0318164. doi: 10.1371/journal.pone.0318164. eCollection 2025.

ABSTRACT

[This corrects the article DOI: 10.1371/journal.pone.0272423.].

PMID:39847555 | DOI:10.1371/journal.pone.0318164

Science. 2025 Jan 24;387(6732):eadn7277. doi: 10.1126/science.adn7277. Epub 2025 Jan 24.

ABSTRACT

Vascular inflammation regulates endothelial pathophenotypes, particularly in pulmonary arterial hypertension (PAH). Dysregulated lysosomal activity and cholesterol metabolism activate pathogenic inflammation, but their relevance to PAH is unclear. Nuclear receptor coactivator 7 (NCOA7) deficiency in endothelium produced an oxysterol and bile acid signature through lysosomal dysregulation, promoting endothelial pathophenotypes. This oxysterol signature overlapped with a plasma metabolite signature associated with human PAH mortality. Mice deficient for endothelial Ncoa7 or exposed to an inflammatory bile acid developed worsened PAH. Genetic predisposition to NCOA7 deficiency was driven by single-nucleotide polymorphism rs11154337, which alters endothelial immunoactivation and is associated with human PAH mortality. An NCOA7-activating agent reversed endothelial immunoactivation and rodent PAH. Thus, we established a genetic and metabolic paradigm that links lysosomal biology and oxysterol processes to endothelial inflammation and PAH.

PMID:39847635 | DOI:10.1126/science.adn7277

Science. 2025 Jan 23:eadk9688. doi: 10.1126/science.adk9688. Online ahead of print.

ABSTRACT

Genomes contain mosaics of discordant evolutionary histories, challenging the accurate inference of the tree of life. While genome-wide data are routinely used for discordance-aware phylogenomic analyses, due to modeling and scalability limitations, the current practice leaves out large chunks of genomes. As more high-quality genomes become available, we urgently need discordance-aware methods to infer the tree directly from a multiple genome alignment. Here, we introduce CASTER, a theoretically justified site-based method that eliminates the need to predefine recombination-free loci. CASTER is scalable to hundreds of mammalian whole genomes. We demonstrate the accuracy and scalability of CASTER in simulations that include recombination and apply CASTER to several biological datasets, showing that its per-site scores can reveal both biological and artefactual patterns of discordance across the genome.

PMID:39847611 | DOI:10.1126/science.adk9688

PLoS Pathog. 2025 Jan 23;21(1):e1012903. doi: 10.1371/journal.ppat.1012903. Online ahead of print.

ABSTRACT

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) continues to persist, demonstrating the risks posed by emerging infectious diseases to national security, public health, and the economy. Development of new vaccines and antibodies for emerging viral threats requires substantial resources and time, and traditional development platforms for vaccines and antibodies are often too slow to combat continuously evolving immunological escape variants, reducing their efficacy over time. Previously, we designed a next-generation synthetic humanized nanobody (Nb) phage display library and demonstrated that this library could be used to rapidly identify highly specific and potent neutralizing heavy chain-only antibodies (HCAbs) with prophylactic and therapeutic efficacy in vivo against the original SARS-CoV-2. In this study, we used a combination of high throughput screening and machine learning (ML) models to identify HCAbs with potent efficacy against SARS-CoV-2 viral variants of interest (VOIs) and concern (VOCs). To start, we screened our highly diverse Nb phage display library against several pre-Omicron VOI and VOC receptor binding domains (RBDs) to identify panels of cross-reactive HCAbs. Using HCAb affinity for SARS-CoV-2 VOI and VOCs (pre-Omicron variants) and model features from other published data, we were able to develop a ML model that successfully identified HCAbs with efficacy against Omicron variants, independent of our experimental biopanning workflow. This biopanning informed ML approach reduced the experimental screening burden by 78% to 90% for the Omicron BA.5 and Omicron BA.1 variants, respectively. The combined approach can be applied to other emerging viruses with pandemic potential to rapidly identify effective therapeutic antibodies against emerging variants.

PMID:39847604 | DOI:10.1371/journal.ppat.1012903

PLoS Comput Biol. 2025 Jan 23;21(1):e1012198. doi: 10.1371/journal.pcbi.1012198. Online ahead of print.

ABSTRACT

Systems biology tackles the challenge of understanding the high complexity in the internal regulation of homeostasis in the human body through mathematical modelling. These models can aid in the discovery of disease mechanisms and potential drug targets. However, on one hand the development and validation of knowledge-based mechanistic models is time-consuming and does not scale well with increasing features in medical data. On the other hand, data-driven approaches such as machine learning models require large volumes of data to produce generalisable models. The integration of neural networks and mechanistic models, forming universal differential equation (UDE) models, enables the automated learning of unknown model terms with less data than neural networks alone. Nevertheless, estimating parameters for these hybrid models remains difficult with sparse data and limited sampling durations that are common in biological applications. In this work, we propose the use of physiology-informed regularisation, penalising biologically implausible model behavior to guide the UDE towards more physiologically plausible regions of the solution space. In a simulation study we show that physiology-informed regularisation not only results in a more accurate forecasting of model behaviour, but also supports training with less data. We also applied this technique to learn a representation of the rate of glucose appearance in the glucose minimal model using meal response data measured in healthy people. In that case, the inclusion of regularisation reduces variability between UDE-embedded neural networks that were trained from different initial parameter guesses.

PMID:39847592 | DOI:10.1371/journal.pcbi.1012198

PLoS Biol. 2025 Jan 23;23(1):e3002707. doi: 10.1371/journal.pbio.3002707. eCollection 2025 Jan.

ABSTRACT

Antibodies are extensively used in biomedical research, clinical fields, and disease treatment. However, to enhance the reproducibility and reliability of antibody-based experiments, it is crucial to have a detailed understanding of the antibody's target specificity and epitope. In this study, we developed a high-throughput and precise epitope analysis method, DECODE (Decoding Epitope Composition by Optimized-mRNA-display, Data analysis, and Expression sequencing). This method allowed identifying patterns of epitopes recognized by monoclonal or polyclonal antibodies at single amino acid resolution and predicted cross-reactivity against the entire protein database. By applying the obtained epitope information, it has become possible to develop a new 3D immunostaining method that increases the penetration of antibodies deep into tissues. Furthermore, to demonstrate the applicability of DECODE to more complex blood antibodies, we performed epitope analysis using serum antibodies from mice with experimental autoimmune encephalomyelitis (EAE). As a result, we were able to successfully identify an epitope that matched the sequence of the peptide inducing the disease model without relying on existing antigen information. These results demonstrate that DECODE can provide high-quality epitope information, improve the reproducibility of antibody-dependent experiments, diagnostics and therapeutics, and contribute to discover pathogenic epitopes from antibodies in the blood.

PMID:39847587 | DOI:10.1371/journal.pbio.3002707

Mol Biol Evol. 2025 Jan 23:msaf005. doi: 10.1093/molbev/msaf005. Online ahead of print.

ABSTRACT

Copy-number variants (CNVs) are an important class of genetic variation that can mediate rapid adaptive evolution. Whereas CNVs can increase the relative fitness of the organism, they can also incur a cost due to the associated increased gene expression and repetitive DNA. We previously evolved populations of Saccharomyces cerevisiae over hundreds of generations in glutamine-limited (Gln-) chemostats and observed the recurrent evolution of CNVs at the GAP1 locus. To understand the role that gene expression plays in adaptation, both in relation to the adaptation of the organism to the selective condition and as a consequence of the CNV, we measured the transcriptome, translatome, and proteome of 4 strains of evolved yeast, each with a unique CNV, and their ancestor in Gln- conditions. We find CNV-amplified genes correlate with higher mRNA abundance; however, this effect is reduced at the level of the proteome, consistent with post-transcriptional dosage compensation. By normalizing each level of gene expression by the abundance of the preceding step we were able to identify widespread differences in the efficiency of each level of gene expression. Genes with significantly different translational efficiency were enriched for potential regulatory mechanisms including either upstream open reading frames (uORFs), RNA binding sites for Ssd1, or both. Genes with lower protein expression efficiency were enriched for genes encoding proteins in protein complexes. Taken together, our study reveals widespread changes in gene expression at multiple regulatory levels in lineages containing adaptive CNVs highlighting the diverse ways in which genome evolution shapes gene expression.

PMID:39847535 | DOI:10.1093/molbev/msaf005

Plant Cell. 2024 Dec 23;37(1):koaf004. doi: 10.1093/plcell/koaf004.

NO ABSTRACT

PMID:39847516 | DOI:10.1093/plcell/koaf004

Cell Rep. 2025 Jan 21;44(2):115224. doi: 10.1016/j.celrep.2024.115224. Online ahead of print.

ABSTRACT

The redox state of proteins is essential for their function and guarantees cell fitness. Peroxiredoxins protect cells against oxidative stress, maintain redox homeostasis, act as chaperones, and transmit hydrogen peroxide signals to redox regulators. Despite the profound structural and functional knowledge of peroxiredoxins action, information on how the different functions are concerted is still scarce. Using global proteomic analyses, we show here that the yeast peroxiredoxin Tsa1 interacts with many proteins of essential biological processes, including protein turnover and carbohydrate metabolism. Several of these interactions are of a covalent nature, and we show that failure of peroxiredoxinylation of Gnd1 affects its phosphogluconate dehydrogenase activity and impairs recovery upon stress. Thioredoxins directly remove TSA1-formed mixed disulfide intermediates, thus expanding the role of the thioredoxin-peroxiredoxin redox cycle pair to buffer the redox state of proteins.

PMID:39847483 | DOI:10.1016/j.celrep.2024.115224

Medicines (Basel). 2024 Dec 31;12(1):1. doi: 10.3390/medicines12010001.

ABSTRACT

Cystic fibrosis (CF) is a rare genetic disorder commonly affecting multiple organs such as the lungs, pancreas, liver, kidney, and intestine. Our search focuses on the pathophysiological changes that affect the drugs' absorption, distribution, metabolism, and excretion (ADME). This review aims to identify the ADME data that compares the pharmacokinetics (PK) of different drugs in CF and healthy subjects. The published data highlight multiple factors that affect absorption, such as the bile salt precipitation and the gastrointestinal pH. Changes in CF patients' protein binding and body composition affected the drug distribution. The paper also discusses the factors affecting metabolism and renal elimination, such as drug-protein binding and metabolizing enzyme capacity. The majority of CF patients are on multidrug therapy, which increases the risk of drug-drug interactions (DDI). This is particularly true for those receiving the newly developed transmembrane conductance regulator (CFTR), as they are at a higher risk for CYP-related DDI. Our research highlights the importance of meticulously evaluating PK variations and DDIs in drug development and the therapeutic management of CF patients.

PMID:39846711 | DOI:10.3390/medicines12010001

Noncoding RNA. 2025 Jan 12;11(1):3. doi: 10.3390/ncrna11010003.

ABSTRACT

The discovery of the involvement of microRNAs (miRNAs) in cystic fibrosis (CF) has generated increasing interest in the past years, due to their possible employment as a novel class of drugs to be studied in pre-clinical settings of therapeutic protocols for cystic fibrosis. In this narrative review article, consider and comparatively evaluate published laboratory information of possible interest for the development of miRNA-based therapeutic protocols for cystic fibrosis. We consider miRNAs involved in the upregulation of CFTR, miRNAs involved in the inhibition of inflammation and, finally, miRNAs exhibiting antibacterial activity. We suggest that antago-miRNAs and ago-miRNAs (miRNA mimics) can be proposed for possible validation of therapeutic protocols in pre-clinical settings.

PMID:39846681 | DOI:10.3390/ncrna11010003

Brief Bioinform. 2024 Nov 22;26(1):bbaf006. doi: 10.1093/bib/bbaf006.

ABSTRACT

Studying the changes in cellular transcriptional profiles induced by small molecules can significantly advance our understanding of cellular state alterations and response mechanisms under chemical perturbations, which plays a crucial role in drug discovery and screening processes. Considering that experimental measurements need substantial time and cost, we developed a deep learning-based method called Molecule-induced Transcriptional Change Predictor (MiTCP) to predict changes in transcriptional profiles (CTPs) of 978 landmark genes induced by molecules. MiTCP utilizes graph neural network-based approaches to simultaneously model molecular structure representation and gene co-expression relationships, and integrates them for CTP prediction. After training on the L1000 dataset, MiTCP achieves an average Pearson correlation coefficient (PCC) of 0.482 on the test set and an average PCC of 0.801 for predicting the top 50 differentially expressed genes, which outperforms other existing methods. Furthermore, we used MiTCP to predict CTPs of three cancer drugs, palbociclib, irinotecan and goserelin, and performed gene enrichment analysis on the top differentially expressed genes and found that the enriched pathways and Gene Ontology terms are highly relevant to the corresponding diseases, which reveals the potential of MiTCP in drug development.

PMID:39847444 | DOI:10.1093/bib/bbaf006

Transl Vis Sci Technol. 2025 Jan 2;14(1):20. doi: 10.1167/tvst.14.1.20.

ABSTRACT

PURPOSE: The purpose of this study was to develop and validate a deep-learning model for noninvasive anemia detection, hemoglobin (Hb) level estimation, and identification of anemia-related retinal features using fundus images.

METHODS: The dataset included 2265 participants aged 40 years and above from a population-based study in South India. The dataset included ocular and systemic clinical parameters, dilated retinal fundus images, and hematological data such as complete blood counts and Hb concentration levels. Eighty percent of the dataset was used for algorithm development and 20% for validation. A deep-convolutional neural network, utilizing VGG16, ResNet50, and InceptionV3 architectures, was trained to predict anemia and estimate Hb levels. Sensitivity, specificity, and accuracy were calculated, and receiver operating characteristic (ROC) curves were generated for comparison with clinical anemia data. GradCAM saliency maps highlighted regions linked to anemia and image processing techniques to quantify anemia-related features.

RESULTS: For predicting anemia, the InceptionV3 model demonstrated the best performance, achieving 98% accuracy, 99% sensitivity, 97% specificity, and an area under the curve (AUC) of 0.98 (95% confidence interval [CI] = 0.97-0.99). For estimating Hb levels, the mean absolute error for the InceptionV3 model was 0.58 g/dL (95% CI = 0.57-0.59 g/dL). The model focused on the area around the optic disc and the neighboring retinal vessels, revealing that anemic subjects exhibited significantly increased vessel tortuosity and reduced vessel density (P < 0.001), with variable effects on vessel thickness.

CONCLUSIONS: The InceptionV3 model accurately predicted anemia and Hb levels, highlighting the potential of deep learning and vessel analysis for noninvasive anemia detection.

TRANSLATIONAL RELEVANCE: The proposed method offers the possibility to quantitatively predict hematological parameters in a noninvasive manner.

PMID:39847377 | DOI:10.1167/tvst.14.1.20

Transl Vis Sci Technol. 2025 Jan 2;14(1):22. doi: 10.1167/tvst.14.1.22.

ABSTRACT

PURPOSE: The purpose of this study was to develop a deep learning approach that restores artifact-laden optical coherence tomography (OCT) scans and predicts functional loss on the 24-2 Humphrey Visual Field (HVF) test.

METHODS: This cross-sectional, retrospective study used 1674 visual field (VF)-OCT pairs from 951 eyes for training and 429 pairs from 345 eyes for testing. Peripapillary retinal nerve fiber layer (RNFL) thickness map artifacts were corrected using a generative diffusion model. Three convolutional neural networks and 2 transformer-based models were trained on original and artifact-corrected datasets to estimate 54 sensitivity thresholds of the 24-2 HVF test.

RESULTS: Predictive performances were calculated using root mean square error (RMSE) and mean absolute error (MAE), with explainability evaluated through GradCAM, attention maps, and dimensionality reduction techniques. The Distillation with No Labels (DINO) Vision Transformers (ViT) trained on artifact-corrected datasets achieved the highest accuracy (RMSE, 95% confidence interval [CI] = 4.44, 95% CI = 4.07, 4.82 decibel [dB], MAE = 3.46, 95% CI = 3.14, 3.79 dB), and the greatest interpretability, showing improvements of 0.15 dB in global RMSE and MAE (P < 0.05) compared to the performance on original maps. Feature maps and visualization tools indicate that artifacts compromise DINO-ViT's predictive ability but improve with artifact correction.

CONCLUSIONS: Combining self-supervised ViTs with generative artifact correction enhances the correlation between glaucomatous structures and functions.

TRANSLATIONAL RELEVANCE: Our approach offers a comprehensive tool for glaucoma management, facilitates the exploration of structure-function correlations in research, and underscores the importance of addressing artifacts in the clinical interpretation of OCT.

PMID:39847375 | DOI:10.1167/tvst.14.1.22

Endocr Pathol. 2025 Jan 23;36(1):2. doi: 10.1007/s12022-025-09846-3.

ABSTRACT

Pancreatic neuroendocrine tumors (PanNETs) are a heterogeneous group of neoplasms that include tumors with different histomorphologic characteristics that can be correlated to sub-categories with different prognoses. In addition to the WHO grading scheme based on tumor proliferative activity, a new parameter based on the scoring of infiltration patterns at the interface of tumor and non-neoplastic parenchyma (tumor-NNP interface) has recently been proposed for PanNET categorization. Despite the known correlations, these categorizations can still be problematic due to the need for human judgment, which may involve intra- and inter-observer variability. Although there is a great need for automated systems working on quantitative metrics to reduce observer variability, there are no such systems for PanNET categorization. Addressing this gap, this study presents a computational pipeline that uses deep learning models to automatically categorize PanNETs for the first time. This pipeline proposes to quantitatively characterize PanNETs by constructing entity-graphs on the cells, and to learn the PanNET categorization using a graph neural network (GNN) trained on these graphs. Different than the previous studies, the proposed model integrates pathology domain knowledge into the GNN construction and training for the purpose of a deeper utilization of the tumor microenvironment and its architectural changes for PanNET categorization. We tested our model on 105 HE stained whole slide images of PanNET tissues. The experiments revealed that this domain knowledge integrated pipeline led to a 76.70% test set F1-score, resulting in significant improvements over its counterparts.

PMID:39847242 | DOI:10.1007/s12022-025-09846-3

Med Biol Eng Comput. 2025 Jan 23. doi: 10.1007/s11517-025-03296-z. Online ahead of print.

ABSTRACT

Positron emission tomography (PET) imaging plays a pivotal role in oncology for the early detection of metastatic tumors and response to therapy assessment due to its high sensitivity compared to anatomical imaging modalities. The balance between image quality and radiation exposure is critical, as reducing the administered dose results in a lower signal-to-noise ratio (SNR) and information loss, which may significantly affect clinical diagnosis. Deep learning (DL) algorithms have recently made significant progress in low-dose (LD) PET reconstruction. Nevertheless, a successful clinical application requires a thorough evaluation of uncertainty to ensure informed clinical judgment. We propose NPB-LDPET, a DL-based non-parametric Bayesian framework for LD PET reconstruction and uncertainty assessment. Our framework utilizes an Adam optimizer with stochastic gradient Langevin dynamics (SGLD) to sample from the underlying posterior distribution. We employed the Ultra-low-dose PET Challenge dataset to assess our framework's performance relative to the Monte Carlo dropout benchmark. We evaluated global reconstruction accuracy utilizing SSIM, PSNR, and NRMSE, local lesion conspicuity using mean absolute error (MAE) and local contrast, and the clinical relevance of uncertainty maps employing correlation between the uncertainty measures and the dose reduction factor (DRF). Our NPB-LDPET reconstruction method exhibits a significantly superior global reconstruction accuracy for various DRFs (paired t-test, p < 0.0001 , N=10, 631). Moreover, we demonstrate a 21% reduction in MAE (573.54 vs. 723.70, paired t-test, p < 0.0001 , N=28) and an 8.3% improvement in local lesion contrast (2.077 vs. 1.916, paired t-test, p < 0.0001 , N=28). Furthermore, our framework exhibits a stronger correlation between the predicted uncertainty 95th percentile score and the DRF ( r 2 = 0.9174 vs. r 2 = 0.6144 , N=10, 631). The proposed framework has the potential to improve clinical decision-making for LD PET imaging by providing a more accurate and informative reconstruction while reducing radiation exposure.

PMID:39847156 | DOI:10.1007/s11517-025-03296-z

Med Biol Eng Comput. 2025 Jan 23. doi: 10.1007/s11517-025-03301-5. Online ahead of print.

ABSTRACT

The generalization of deep learning (DL) models is critical for accurate lesion segmentation in breast ultrasound (BUS) images. Traditional DL models often struggle to generalize well due to the high frequency and scale variations inherent in BUS images. Moreover, conventional loss functions used in these models frequently result in imbalanced optimization, either prioritizing region overlap or boundary accuracy, which leads to suboptimal segmentation performance. To address these issues, we propose UMA-Net, an enhanced UNet architecture specifically designed for BUS image segmentation. UMA-Net integrates residual connections, attention mechanisms, and a bottleneck with atrous convolutions to effectively capture multi-scale contextual information without compromising spatial resolution. Additionally, we introduce an adaptive ensemble loss function that dynamically balances the contributions of different loss components during training, ensuring optimization across key segmentation metrics. This novel approach mitigates the imbalances found in conventional loss functions. We validate UMA-Net on five diverse BUS datasets-BUET, BUSI, Mendeley, OMI, and UDIAT-demonstrating superior performance. Our findings highlight the importance of addressing frequency and scale variations, confirming UMA-Net as a robust and generalizable solution for BUS image segmentation.

PMID:39847155 | DOI:10.1007/s11517-025-03301-5