Front Bioeng Biotechnol. 2025 May 6;13:1590962. doi: 10.3389/fbioe.2025.1590962. eCollection 2025.

ABSTRACT

BACKGROUND: The application of deep learning techniques in medical image analysis has shown great potential in assisting clinical diagnosis. This study focuses on the development and evaluation of deep learning models for the classification of knee joint injuries using Magnetic Resonance Imaging (MRI) data. The research aims to provide an efficient and reliable tool for clinicians to aid in the diagnosis of knee joint disorders, particularly focusing on Anterior Cruciate Ligament (ACL) tears.

METHODS: KneeXNet leverages the power of graph convolutional networks (GCNs) to capture the intricate spatial dependencies and hierarchical features in knee MRI scans. The proposed model consists of three main components: a graph construction module, graph convolutional layers, and a multi-scale feature fusion module. Additionally, a contrastive learning scheme is employed to enhance the model's discriminative power and robustness. The MRNet dataset, consisting of knee MRI scans from 1,370 patients, is used to train and validate KneeXNet.

RESULTS: The performance of KneeXNet is evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC) metric and compared to state-of-the-art methods, including traditional machine learning approaches and deep learning models. KneeXNet consistently outperforms the competing methods, achieving AUC scores of 0.985, 0.972, and 0.968 for the detection of knee joint abnormalities, ACL tears, and meniscal tears, respectively. The cross-dataset evaluation further validates the generalization ability of KneeXNet, maintaining its superior performance on an independent dataset.

APPLICATION: To facilitate the clinical application of KneeXNet, a user-friendly web interface is developed using the Django framework. This interface allows users to upload MRI scans, view diagnostic results, and interact with the system seamlessly. The integration of Grad-CAM visualizations enhances the interpretability of KneeXNet, enabling radiologists to understand and validate the model's decision-making process.

PMID:40395675 | PMC:PMC12088959 | DOI:10.3389/fbioe.2025.1590962

MAbs. 2025 Dec;17(1):2505090. doi: 10.1080/19420862.2025.2505090. Epub 2025 May 21.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive lung disease characterized by scarring and tissue remodeling. Current treatments have limited efficacy and significant side effects. To address these limitations, we developed AD-214, an anti-CXCR4-Fc-fusion protein composed of an anti-CXCR4 i-body (AD-114) tethered at its C terminus to constant domains 2 and 3 of the Fc region of a mutated human IgG1 lacking effector function. AD-214 binds with high affinity and specificity to CXCR4, modulates intracellular signaling, and inhibits key fibrotic pathways. Using fibrosis models, we demonstrate that AD-214 treatment significantly reduces collagen deposition and lung remodeling and has a unique mode of action. In Phase 1 clinical trials, intravenous infusion of AD-214 led to high and sustained CXCR4 receptor occupancy (RO), but whether RO and efficacy are causally linked remained to be determined. Herein, we demonstrate that CXCR4 RO by AD-214 inhibits primary human leukocyte migration, a model fibrotic process, and that migration inhibition is achievable at concentrations of AD-214 present in the serum of healthy human volunteers administered AD-214. Taken together, these data provide proof of concept for AD-214 as a novel treatment strategy for IPF and suggest that clinically feasible dosing regimens may be efficacious.

PMID:40395177 | DOI:10.1080/19420862.2025.2505090

Eur Heart J. 2025 May 21:ehaf324. doi: 10.1093/eurheartj/ehaf324. Online ahead of print.

ABSTRACT

BACKGROUND AND AIMS: Hypertrophic cardiomyopathy (HCM) is a genetic cardiac disorder characterized by left ventricular hypertrophy (LVH), diastolic dysfunction, and impaired metabolic efficiency. This study investigates the therapeutic potential of the sodium-glucose cotransporter 2 inhibitor (SGLT2i) empagliflozin (EMPA) in ameliorating these pathological features in a mouse model carrying the myosin R403Q mutation.

METHODS: Male mice harbouring the R403Q mutation were treated with EMPA for 16 weeks. Multi-nuclear magnetic resonance spectroscopy (31P, 13C, and 23Na MRS), echocardiography, transcriptomic, proteomic, and phosphoproteomic profiling were utilized to assess metabolic, structural, and functional changes.

RESULTS: Empagliflozin facilitated the coupling of glycolysis with glucose oxidation and normalized elevated intracellular sodium levels. Treatment resulted in a significant reduction in LVH and myocardial fibrosis as evidenced by echocardiography and histopathology. These structural improvements correlated with enhancements in mitochondrial adenosine triphosphate (ATP) synthesis, fatty acid oxidation, and branched-chain amino acid catabolism. Furthermore, EMPA improved left ventricular diastolic function and contractile reserve, underscored by improved ATP production and reduced energy cost of contraction. Notably, these benefits were linked to down-regulation of the mammalian target of rapamycin signalling pathway and normalization of myocardial substrate metabolic fluxes.

CONCLUSIONS: Empagliflozin significantly mitigates structural and metabolic dysfunctions in a mouse model of HCM, underscoring its potential as a therapeutic agent for managing this condition. These findings suggest broader applicability of SGLT2i in cardiovascular diseases, including those due to myocardial-specific mutations, warranting further clinical investigation.

PMID:40396194 | DOI:10.1093/eurheartj/ehaf324

Mechanobiol Med. 2024 Dec 14;3(1):100112. doi: 10.1016/j.mbm.2024.100112. eCollection 2025 Mar.

ABSTRACT

Mechanotransduction is the process that enables the conversion of mechanical cues into biochemical signaling. While all our cells are well known to be sensitive to such stimuli, the details of the systemic interaction between mechanical input and inflammation are not well integrated. Often, indeed, they are considered and studied in relatively compartmentalized areas, and we therefore argue here that to understand the relationship of mechanical stimuli with inflammation - with a high translational potential - it is crucial to offer and analyze a unified view of mechanotransduction. We therefore present here pathway representation, recollected with the standard systems biology markup language (SBML) and explored with network biology approaches, offering RAC1 as an exemplar and emerging molecule with potential for medical translation.

PMID:40396134 | PMC:PMC12082120 | DOI:10.1016/j.mbm.2024.100112

Clin Cosmet Investig Dermatol. 2025 May 15;18:1191-1198. doi: 10.2147/CCID.S518751. eCollection 2025.

ABSTRACT

INTRODUCTION: Lesion segmentation in dermoscopic images significantly enhances the diagnostic performance of AI-based classification models. However, conventional methods often require pixel-level annotations, which are resource-intensive and prone to errors caused by external artifacts, such as hair and skin markings.

METHODS: We propose a hybrid framework called SAM-enhanced YOLO, which integrates the Segment Anything Model (SAM) with You Only Look Once (YOLO) for precise pixel-level segmentation. This method combines YOLO's efficient lesion localization with SAM's advanced zero-shot segmentation capabilities. To further validate the framework, we compared it against traditional methods, including GrabCut and Otsu's thresholding, as well as SAM used without YOLO (SAM-only). For SAM-only, lesion segmentation was initialized at the image center to simulate a typical dermoscopic imaging setup.

RESULTS: SAM-enhanced YOLO demonstrated superior segmentation performance, achieving an Intersection over Union (IoU) of 0.738 and an F1-score (the harmonic mean of precision and recall) of 0.833, compared to 0.578 and 0.683 with SAM-only, respectively. This represents a 28% improvement in IoU and a 22% improvement in F1-score compared to SAM-only. The results were consistent across lesion shapes and contrast conditions, with SAM-enhanced YOLO exhibiting the lowest variability and highest robustness among the evaluated methods.

CONCLUSION: By reducing the need for pixel-level annotations and outperforming both standalone SAM and traditional methods, SAM-enhanced YOLO provides a scalable and resource-efficient solution for dermoscopic lesion segmentation. This framework holds significant potential for improving diagnostic workflows in clinical and resource-limited settings.

PMID:40396125 | PMC:PMC12089257 | DOI:10.2147/CCID.S518751

Autophagy Rep. 2022 Apr 24;1(1):183-186. doi: 10.1080/27694127.2022.2065602. eCollection 2022.

ABSTRACT

In plants, macroautophagy/autophagy is an essential mechanism responsible for a large variety of processes throughout the plant's lifecycle, including nutrient processing, immunity, stress responses and senescence. Previous studies had observed the presence of autophagosomes in an Arabidopsis sexual reproduction system that prevents self-fertilization (self-incompatibility), but their requirement in this pathway was unclear. Using autophagy-deficient mutants, we have recently found that autophagy is a key contributor in the Arabidopsis self-incompatibility response to reject self-pollen.

PMID:40395998 | PMC:PMC11864688 | DOI:10.1080/27694127.2022.2065602

Mechanobiol Med. 2024 Apr 27;2(3):100068. doi: 10.1016/j.mbm.2024.100068. eCollection 2024 Sep.

ABSTRACT

Dendritic cells (DCs) play a pivotal role in bridging the innate and adaptive immune systems. From their immature state, scavenging tissue for foreign antigens to uptake, then maturation, to their trafficking to lymph nodes for antigen presentation, these cells are exposed to various forms of mechanical forces. Particularly, in the tumor microenvironment, it is widely known that microenvironmental biomechanical cues are heightened. The source of these forces arises from cell-to-extracellular matrix (ECM) and cell-to-cell interactions, as well as being exposed to increased microenvironmental pressures and fluid shear forces typical of tumors. DCs then integrate these forces, influencing their immune functions through mechanotransduction. This aspect of DC biology holds alternative, but important clues to understanding suppressed/altered DC responses in tumors, or allow the artificial enhancement of DCs for therapeutic purposes. This review discusses the current understanding of DC mechanobiology from the perspectives of DCs as sensors of mechanical forces and providers of mechanical forces.

PMID:40395498 | PMC:PMC12082323 | DOI:10.1016/j.mbm.2024.100068

Int J Biol Macromol. 2025 May 18:144106. doi: 10.1016/j.ijbiomac.2025.144106. Online ahead of print.

ABSTRACT

Melioidosis, also known as Whitmore's disease, is caused by the deadly pathogen Burkholderia pseudomallei and remains a significant global health concern, particularly in South Asia. The disease is contracted through exposure to contaminated soil, water, air, and food. Infected individuals often present with abscesses in internal organs such as the lungs, spleen, and liver, and in soft tissues, with severe cases leading to septic shock and acute pneumonia. The rising incidence and mortality rates, coupled with B. pseudomallei's ability to form biofilms and develop resistance to antibiotics like cephalosporins, make treatment increasingly challenging. This highlights the urgent need for novel therapeutic approaches. D-Alanine-D-Alanine ligase (Ddl), a crucial enzyme involved in the final stage of bacterial cell wall synthesis, which protects the pathogen from the hostile cellular environment of the host. While many bacteria have two isoforms of this enzyme, B. pseudomallei possesses only the DdlB isoform, presenting a significant vulnerability. Our study represents the first successful attempt to target DdlB through a combination of molecular docking and molecular dynamics simulations. These investigations provide strong evidence that Conivaptan acts as an effective inhibitor of DdlB, offering a novel therapeutic approach for combating melioidosis.

PMID:40393604 | DOI:10.1016/j.ijbiomac.2025.144106

Cancer Gene Ther. 2025 May 21. doi: 10.1038/s41417-025-00914-8. Online ahead of print.

ABSTRACT

Glioblastoma (GBM) is one of the most aggressive primary brain tumors, characterized by extensive neovascularization and a highly infiltrative phenotype. Anti-vascular endothelial growth factor (VEGF) therapies, such as bevacizumab, have emerged as significant adjunct treatments for recurrent and high-grade GBM by targeting abnormal tumor vasculature. Despite demonstrated benefits in slowing tumor progression and alleviating peritumoral edema, these agents are associated with notable vascular complications, including hemorrhagic and ischemic events. Hemorrhagic complications range from minor intracranial microbleeds to life-threatening intracranial hemorrhages (ICH). Mechanistically, VEGF inhibition disrupts endothelial function and decreases vascular integrity, making already fragile tumor vessels prone to rupture. Glioma-associated vascular abnormalities, including disorganized vessel networks and compromised blood-brain barrier, further exacerbate bleeding risks. Concurrent use of anticoagulants, hypertension, and genetic predispositions also significantly elevate hemorrhagic risk. In addition to bleeding complications, ischemic events are increasingly recognized in patients receiving anti-VEGF therapy. Reduced vascular endothelial cells (ECs) survival and diminished microvascular density can lead to regional hypoperfusion and potentially precipitate cerebrovascular ischemia. Impaired vasoreactivity and increased vascular resistance, often accompanied by endothelial dysfunction and microvascular rarefaction, contribute to elevated stroke and arterial thrombotic risk. This review synthesizes current evidence on hemorrhagic and ischemic complications arising from anti-VEGF therapy in GBM. We discuss underlying pathophysiological mechanisms, risk factors, and clinically relevant biomarkers, as well as prevention strategies-such as rigorous blood pressure (BP) control and close monitoring of coagulation parameters. We further highlight emerging avenues in precision medicine, including pharmacogenomic profiling and targeted adjunct agents that protect vascular integrity, aimed at mitigating adverse vascular events while preserving therapeutic efficacy. The goal is to optimize outcomes for GBM patients by balancing the benefits of anti-VEGF therapy with vigilant management of its inherent vascular risks. In addition, this study analyzes existing clinical trials of the use of anti-VEGF drugs in the treatment of gliomas using data from the clinicaltirals.gov website.

PMID:40394233 | DOI:10.1038/s41417-025-00914-8

J Cyst Fibros. 2025 May 19:S1569-1993(25)01466-3. doi: 10.1016/j.jcf.2025.04.011. Online ahead of print.

ABSTRACT

BACKGROUND: The role of autoimmune beta-cell damage in cystic fibrosis-related glucose abnormalities remains unclear. This study evaluates the prevalence of pancreatic islet autoantibodies (AABs) by glycemic status and age, and assesses the risk of developing cystic fibrosis-related diabetes (CFRD) in people with cystic fibrosis (pwCF).

METHODS: A random-effects meta-analysis examined AABs against glutamic acid decarboxylase (GADA), insulin (IAA), islet cell (ICA), islet antigen-2 (IA-2A) and zinc transporter 8 (ZnT8A) in pwCF (CRD42023482663). Prevalence, odds ratios (OR), and 95 % confidence intervals (CI) were calculated with subgroup analyses by glycemic status and age.

RESULTS: Analysis of 20 studies (2229 pwCF) found an overall islet AAB positivity rate of 4 % (CI: 2-9 %) and multiple positivity at 1 % (CI: 0-11 %). IAA had the highest prevalence at 6 % (CI: 3-14 %), and ICA the lowest at 1 % (CI: 0-9 %). Islet AAB prevalence trended higher in CFRD than non-CFRD patients and in children than adults. CFRD was significantly associated with islet AAB positivity, notably for GADA (OR 4.63, CI: 3.42-6.28), ICA (OR 3.57, CI: 1.05-12.18), and IA-2A (OR 2.36, CI: 1.29-4.34). Any and multiple AAB positivity were similarly correlated to CFRD (OR 2.82, CI: 1.22-6.51 and OR 2.71, CI: 1.49-4.93).

CONCLUSIONS: Pancreatic islet AABs are present in 1-6 % of pwCF and increase the risk of CFRD by 2.36 to 4.63 times. While there's a suggested link, limited study quality and inconsistent testing warrant cautious interpretation. Further robust studies are needed to confirm these findings and improve screening strategies.

PMID:40393876 | DOI:10.1016/j.jcf.2025.04.011

Se Pu. 2025 Jun;43(6):696-704. doi: 10.3724/SP.J.1123.2024.05012.

ABSTRACT

Gel electrophoresis is used to separate and analyze macromolecules （such as DNA， RNA， and proteins） and their fragments， and highly reproducible and efficient automatic band-detection methods have been developed to analyze gel images. Uneven background， low contrast， lane distortion， blurred band edges， and geometric deformation pose detection-accuracy challenges during automatic band detection. In order to address these issues， various correction algorithms have been proposed； however， these algorithms rely on researcher experience to adjust and optimize parameters based on image characteristics， which introduces human error while qualitatively and quantitatively processing bands. Isoelectric focusing （IEF） gel electrophoresis separates proteins with high-resolution based on isoelectric point （pI） differences. Microarray IEF （mIEF） is used for the auxiliary diagnosis of diabetes and adult β-thalassemia owing to operational ease， low sample consumption， and high throughout. This diagnostic method relies on accurately positioning and precisely determining protein bands. To avoid errors associated with correction algorithms during band analysis， this paper introduces a method for rapidly recognizing bands in gel electrophoresis patterns that relies on a deep learning object detection algorithm， and uses it to quantify and classify the IEF electrophoresis pattern of hemoglobin （Hb）. We used mIEF experiments to collect 1 665 pI-marker-free Hb IEF images as a model dataset to train the YOLOv8 model. The trained model accepts a Hb IEF image as input and infers band bounding boxes and classification results. Using inference data， the gray intensities of the pixels in each band area are summed to determine the content of each protein. The background and foreground of the image need to be separated prior to summing the abovementioned gray intensities， and the threshold method is used to achieve this. The threshold is defined as the average intensity of the background area， which is obtained by summing and averaging the background intensities of gel areas between the detection bounding boxes of each protein band. The baseline band areas are unified after removing the background. This method only requires the input image， directly outputs the corresponding electrophoretic band information， and does not rely on the experience of professionals nor is it affected by factors such as lane distortion or band deformation. In addition， the developed method does not depend on pI markers for qualitatively determining bands， thereby reducing experimental costs and improving detection efficiency. YOLOv8n delivered a detection accuracy of 92.9% and an inference time of 0.6 ms while using limited computing resources. Using Hb A2 as an example， we compared its content measured using the developed method with clinical data. The quantitative results were subjected to regression analysis， which delivered a linearity of 0.981 2 and a correlation coefficient of 0.980 0. We also used the Bland-Altman analysis method to verify that these two values are highly consistent. Compared with the traditional automatic band detection methods， the method developed in this study is fast， accurate， more repeatable， and stable， and can be used to determine the Hb A2 content in clinical practice， thereby potentially assisting in the auxiliary diagnosis of adult β-thalassemia.

PMID:40394749 | DOI:10.3724/SP.J.1123.2024.05012

BMC Musculoskelet Disord. 2025 May 20;26(1):498. doi: 10.1186/s12891-025-08733-6.

ABSTRACT

OBJECTIVE: The aim of this study was to develop a hybrid diagnostic framework integrating radiomic and deep features for accurate and reproducible detection and classification of wrist fractures using X-ray images.

MATERIALS AND METHODS: A total of 3,537 X-ray images, including 1,871 fracture and 1,666 non-fracture cases, were collected from three healthcare centers. Radiomic features were extracted using the PyRadiomics library, and deep features were derived from the bottleneck layer of an autoencoder. Both feature modalities underwent reliability assessment via Intraclass Correlation Coefficient (ICC) and cosine similarity. Feature selection methods, including ANOVA, Mutual Information (MI), Principal Component Analysis (PCA), and Recursive Feature Elimination (RFE), were applied to optimize the feature set. Classifiers such as XGBoost, CatBoost, Random Forest, and a Voting Classifier were used to evaluate diagnostic performance. The dataset was divided into training (70%) and testing (30%) sets, and metrics such as accuracy, sensitivity, and AUC-ROC were used for evaluation.

RESULTS: The combined radiomic and deep feature approach consistently outperformed standalone methods. The Voting Classifier paired with MI achieved the highest performance, with a test accuracy of 95%, sensitivity of 94%, and AUC-ROC of 96%. The end-to-end model achieved competitive results with an accuracy of 93% and AUC-ROC of 94%. SHAP analysis and t-SNE visualizations confirmed the interpretability and robustness of the selected features.

CONCLUSIONS: This hybrid framework demonstrates the potential for integrating radiomic and deep features to enhance diagnostic performance for wrist and forearm fractures, providing a reliable and interpretable solution suitable for clinical applications.

PMID:40394557 | DOI:10.1186/s12891-025-08733-6

BMC Bioinformatics. 2025 May 20;26(1):130. doi: 10.1186/s12859-025-06138-9.

ABSTRACT

Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity, but dropout events, where gene expression is undetected in individual cells, present a significant challenge. We propose scMASKGAN, which transforms matrix imputation into a pixel restoration task to improve the recovery of missing gene expression data. Specifically, we integrate masking, convolutional neural networks (CNNs), attention mechanisms, and residual networks (ResNets) to effectively address dropout events in scRNA-seq data. The masking mechanism ensures the preservation of complete cellular information, while convolution and attention mechanisms are employed to capture both global and local features. Residual networks augment feature representation and effectively mitigate the risk of model overfitting. Additionally, cell-type labels are incorporated as constraints to guide the methods in learning more accurate cellular features. Finally, multiple experiments were conducted to evaluate the methods' performance using seven different data types and scRNA-seq data from ten neuroblastoma samples. The results demonstrate that the data imputed by scMASKGAN not only perform excellently across various evaluation metrics but also significantly enhance the effectiveness of downstream analyses, enabling a more comprehensive exploration of underlying biological information.

PMID:40394489 | DOI:10.1186/s12859-025-06138-9

J Imaging Inform Med. 2025 May 20. doi: 10.1007/s10278-025-01539-x. Online ahead of print.

ABSTRACT

The objective of this study is to enhance the understanding of ophthalmic disease physiology and genetic architecture through the analysis of optical coherence tomography (OCT) images using artificial intelligence (AI). We introduce a novel AI methodology that addresses the challenge of transferring OCT phenotypes across datasets. The approach employs unsupervised and self-supervised learning techniques to phenotype and cluster OCT-derived retinal layer thicknesses, using glaucoma as a model disease. Our method integrates deep learning, manifold learning, and a Gaussian mixture model to identify distinct phenotypic clusters. Across two large datasets-Massachusetts Eye and Ear (MEE; 18,985 images) and UK Biobank (UKBB; 86,115 images)-the model identified 9 to 11 phenotypic clusters per retinal layer, which were clinically meaningful and showed consistent patterns across datasets. Pearson correlation analysis confirmed the intra-cluster similarity, with within-cluster correlations exceeding inter-cluster correlations (Supplemental Figs. 4-5). Clinical associations showed that specific phenotypes correlated strongly with glaucoma severity markers, including visual field mean deviation (e.g., 12.57±10.1 for phenotype 6) and cup-to-disc ratio (e.g., 0.694±0.237). These results validate the robustness of the model and its ability to generalize across datasets. This work advances OCT-based phenotyping, enabling phenotype transfer and facilitating translational research in disease mechanisms and genetic discovery.

PMID:40394321 | DOI:10.1007/s10278-025-01539-x

J Imaging Inform Med. 2025 May 20. doi: 10.1007/s10278-025-01543-1. Online ahead of print.

ABSTRACT

Prostate cancer is the most prevalent solid tumor in males and one of the most common causes of male mortality. It is the most common type of cancer in men, a major global public health issue, and accounts for up to 7.3% of all male cancer diagnoses worldwide. To optimize patient outcomes and ensure therapeutic success, an accurate diagnosis must be made promptly. To achieve this, we focused on using ResNet50, a convolutional neural network (CNN) architecture, to analyze prostate histological images to classify prostate cancer. ResNet50, due to its efficiency in medical image classification, was used to classify the histological images as benign or malignant. In this study, a total of 1276 prostate biopsy images were used on the ResNet50 model. We employed evaluation metrics such as accuracy, precision, recall, and F1 score. The results showed that the ResNet50 model performed excellently with an overall accuracy of 0.98, 1.00 as precision, 0.98 as recall, and 0.97 as F1 score for benign. The malignant histological image has 0.99, 0.98, and 0.97 as precision, recall, and F1 scores. It also recorded a 95% confidence interval (CI) for accuracy as (0.91, 1.00) and a performance gain of 4.26% compared to MobileNet and CNN-RNN. The result of our model was also compared with the state-of-the-art (SOTA) DL models to ensure robustness. This study has demonstrated the potential of the ResNet50 model in the classification of prostate cancer. Again, the clinical integration of the results of this study will aid decision-makers in enhancing patient outcomes.

PMID:40394318 | DOI:10.1007/s10278-025-01543-1

Eur Arch Otorhinolaryngol. 2025 May 20. doi: 10.1007/s00405-025-09451-4. Online ahead of print.

ABSTRACT

PURPOSE: Deep learning, a subset of machine learning, is widely utilized in medical applications. Identifying maxillary sinus pathologies before surgical interventions is crucial for ensuring successful treatment outcomes. Cone beam computed tomography (CBCT) is commonly employed for maxillary sinus evaluations due to its high resolution and lower radiation exposure. This study aims to assess the accuracy of artificial intelligence (AI) algorithms in detecting maxillary sinus pathologies from CBCT scans.

METHODS: A dataset comprising 1000 maxillary sinuses (MS) from 500 patients was analyzed using CBCT. Sinuses were categorized based on the presence or absence of pathology, followed by segmentation of the maxillary sinus. Manual segmentation masks were generated using the semiautomatic software ITK-SNAP, which served as a reference for comparison. A convolutional neural network (CNN)-based machine learning model was then implemented to automatically segment maxillary sinus pathologies from CBCT images. To evaluate segmentation accuracy, metrics such as the Dice similarity coefficient (DSC) and intersection over union (IoU) were utilized by comparing AI-generated results with human-generated segmentations.

RESULTS: The automated segmentation model achieved a Dice score of 0.923, a recall of 0.979, an IoU of 0.887, an F1 score of 0.970, and a precision of 0.963.

CONCLUSION: This study successfully developed an AI-driven approach for segmenting maxillary sinus pathologies in CBCT images. The findings highlight the potential of this method for rapid and accurate clinical assessment of maxillary sinus conditions using CBCT imaging.

PMID:40394252 | DOI:10.1007/s00405-025-09451-4

Sci Rep. 2025 May 20;15(1):17481. doi: 10.1038/s41598-025-01763-z.

ABSTRACT

Modeling the 3D structures of cells and tissues is crucial in biology. Sequential cross-sectional images from electron microscopy provide high-resolution intracellular structure information. The segmentation of complex cell structures remains a laborious manual task for experts, demanding time and effort. This bottleneck in analyzing biological images requires efficient and automated solutions. In this study, the deep learning-based automated segmentation of biological images was explored to enable accurate reconstruction of the 3D structures of cells and organelles. An analysis system for the cell images of Cyanidioschyzon merolae, a primitive unicellular red algae, was constructed. This system utilizes sequential cross-sectional images captured by a focused ion beam scanning electron microscope (FIB-SEM). A U-Net was adopted and training was performed to identify and segment cell organelles from single-cell images. In addition, the segment anything model (SAM) and 3D watershed algorithm were employed to extract individual 3D images of each cell from large-scale microscope images containing numerous cells. Finally, the trained U-Net was applied to segment each structure within these 3D images. Through this procedure, the creation of 3D cell models could be fully automated. The adoption of other deep learning techniques and combinations of image processing methods will also be explored to enhance the segmentation accuracy further.

PMID:40394179 | DOI:10.1038/s41598-025-01763-z