Computer methods and programs in biomedicine最新文献

{"title":"Graph-theoretic characterization of nuclear spatial organization in renal cell carcinoma images","authors":"Rohini Palanisamy ,&nbsp;Shruthi Gokul ,&nbsp;Gokul Manoj ,&nbsp;Abinaya Srinivasan ,&nbsp;Sandhya Sundaram ,&nbsp;Ramakrishnan Swaminathan","doi":"10.1016/j.cmpb.2025.108930","DOIUrl":"10.1016/j.cmpb.2025.108930","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Renal cell carcinoma (RCC) is a highly prevalent and aggressive kidney malignancy that necessitates accurate histopathological evaluation for effective diagnosis and treatment planning. While traditional diagnostic approaches primarily rely on nuclear morphology, emerging computational techniques offer alternative strategies to quantify nuclear spatial organization. This study leverages topological data analysis and graph theory to characterize nuclear aggregation patterns in RCC histopathological images.</div></div><div><h3>Methods</h3><div>Graph-based features, including Betti numbers (<em>β₀</em> and <em>β₁</em>) and clustering coefficients, were extracted to quantify nuclear connectivity and structural organization. Nuclear segmentation was performed across multiple intensity thresholds to assess the impact of threshold variation on feature extraction. The elbow method was used to determine the optimal threshold, balancing connectivity, and structural stability. Statistical significance between tumor and normal tissues was evaluated using the Mann-Whitney U test.</div></div><div><h3>Results</h3><div>Betti numbers (<em>β₀</em> and <em>β₁</em>) and clustering coefficients exhibited distinct trends across different threshold values, effectively differentiating RCC from normal renal tissue. Tumor tissues demonstrated higher <em>β₁</em> and clustering coefficient values, indicating increased nuclear aggregation and irregular connectivity, while normal tissues exhibited higher <em>β₀</em> values, suggesting a more fragmented nuclear distribution. The elbow method identified 100 pixels as the optimal threshold for feature extraction, and statistical analysis confirmed significant differences (<em>p</em> &lt; 0.05) between tumor and normal tissues.</div></div><div><h3>Conclusion</h3><div>The results validate the effectiveness of topological and graph-based descriptors in capturing tumor-associated structural variations. By systematically evaluating intensity thresholds and selecting the optimal one, this study enhances the reliability of nuclear aggregation-based differentiation. The proposed computational framework supports automated RCC diagnosis and improves histopathological assessment, demonstrating the potential of topological data analysis and graph theory in medical imaging.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108930"},"PeriodicalIF":4.9,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mimicking cancer therapy in an agent-based model: The case of hepatoblastoma","authors":"Alessandro Ravoni ,&nbsp;Enrico Mastrostefano ,&nbsp;Roland Kappler ,&nbsp;Carolina Armengol ,&nbsp;Filippo Castiglione ,&nbsp;Christine Nardini","doi":"10.1016/j.cmpb.2025.108917","DOIUrl":"10.1016/j.cmpb.2025.108917","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Hepatoblastoma is the most common pediatric liver cancer and represents a serious clinical challenge as no effective therapies have yet been found for advanced states and relapses of the disease.</div></div><div><h3>Methods:</h3><div>In this work, we use a well-established agent-based model of the immune response now equipped with anti-cancer therapy response to study the evolution of the disease and the role of the immune system in its containment.</div></div><div><h3>Results:</h3><div>We simulate the course of hepatoblastoma over three years in a population of virtual patients, successfully mimicking clinical mortality and symptom onset rates, as well as observations on the main tumor transcriptomic subtypes.</div></div><div><h3>Conclusions:</h3><div>The capacity of the introduced framework to reproduce clinical data and the heterogeneity of hepatoblastoma, combined with the possibility of observing the dynamics of cellular entities at the microscopic scale and the key chemical signals involved in disease progression, makes the model a promising resource for future research on in silico trials.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"269 ","pages":"Article 108917"},"PeriodicalIF":4.9,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the heterogeneous chemo-mechano-biological degeneration of cartilage using 3-D biphasic finite elements.","authors":"Muhammed Masudur Rahman, Paul N Watton, Corey P Neu, David M Pierce","doi":"10.1016/j.cmpb.2025.108902","DOIUrl":"https://doi.org/10.1016/j.cmpb.2025.108902","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background and objective: &lt;/strong&gt;Osteoarthritis (OA), a debilitating joint disease, involves progressive cartilage degeneration and altered biomechanics. We established a novel chemo-mechano-biological (CMB) modeling framework that integrates biphasic mechanics with biochemical and biological processes to predict cartilage degeneration (i.e. loss of masses of constituents presenting as loss of thickness) under pathological conditions. Our framework captures time-dependent remodeling of cartilage constituents in 3-D driven by mechanical loading, biochemical signaling, and cellular metabolism.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We formulated a nonlinear, large-strain biphasic constitutive model coupled with a biochemical model of signaling pathways. Our framework incorporates depth-dependent metabolic activity, explicitly linking availability of oxygen to chondrocyte behavior and extracellular matrix (ECM) remodeling. We included interactions among mechanical stimuli, growth factors, pro-inflammatory cytokines, enzymes (collagenases and aggrecanases), and inhibitors (TIMP). We conducted nonlinear, biphasic finite element (FE) simulations in 3-D, allowing for realistic representations of intra-cartilage heterogeneity. We simulated cyclic, confined compression of full-thickness cartilage, a scenario mimicking conditions in vivo during walking or running.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Our simulations spanning 24 months presented realistic patterns of cartilage degeneration including zonal variations in matrix composition and thickness loss. In healthy cartilage, interstitial fluid pressure resisted mechanical loading, maintaining ECM integrity. However, in degenerative overloading conditions, enzymatic activity and altered metabolic functions led to increased porosity, reduced fluid pressure, and heterogeneous degradation of ECM. Incorporating depth-dependent metabolic activity revealed pronounced degeneration in the superficial zone (SZ) and progressively reduced loss toward the deep zone (DZ). This outcome aligns with experimental evidence on progression of OA. Oxygen availability played a critical role, with higher levels exacerbating degradation, consistent with findings linking oxidative stress to cartilage degeneration.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;Our nonlinear, biphasic FE framework offers a robust tool for investigating mechanisms of cartilage degeneration and OA, and advancing therapeutic strategies. It uniquely integrates biphasic mechanics, signaling pathways, and metabolic activity in 3-D, providing insights into patterns of cartilage degeneration. We previously developed automated and publicly available tools to generate patient-specific knee models from MR Images, altogether enabling personalized diagnostics/prognostics and pre-/post-operative planning. Our CMB framework is also publicly available as a plugin for FEBio at https://github.uconn.edu/imLab/FEVGnR-Plugin, supporting broader research on OA and cartilage biom","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":" ","pages":"108902"},"PeriodicalIF":4.9,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144526668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new statistical reconstruction method with rebinning as a technique for reducing the dose in CT scanners utilizing a flying focal spot","authors":"P. Pluta ,&nbsp;R. Cierniak ,&nbsp;M. Waligóra","doi":"10.1016/j.cmpb.2025.108903","DOIUrl":"10.1016/j.cmpb.2025.108903","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>In this paper, we present an original concept for image reconstruction in spiral CT scanners, incorporating Flying Focal Spot technology. The primary goal of this work is to explore the feasibility of using Model-Based Iterative Reconstruction methods for CT scanners with the Flying Focal Spot technique, aiming to reduce the X-ray dose absorbed by patients during examinations. The geometry of the projection lines in these scanners significantly impedes the use of traditional reconstruction methods, as well as the application of statistical approaches that rely on a discrete-to-discrete data model. This challenge is the primary motivation for our proposed reconstruction method, which is based on a rebinning strategy and a continuous-to-continuous data model.</div></div><div><h3>Methods:</h3><div>Experiments performed using artificial data revealed that, at different noise levels, our approach outperforms the traditional reference method in terms of objective measures of image quality. Similarly, for physical projections acquired from a commercial scanner, we conducted a comparative study of our method with a traditional filtration algorithm, using objective quality measures for quarter-dose projections. Finally, a practical assessment by a highly experienced radiologist was conducted to verify the usefulness of our innovative approach in reducing the dose absorbed by patients, supported by objective classification measures.</div></div><div><h3>Results:</h3><div>The experiments demonstrate that our approach addresses the drawbacks of traditional methods in terms of image quality and offers the potential to significantly reduce the X-ray dose required for completing examination procedures. Thanks to the statistical underpinnings of our approach, the X-ray dose absorbed by patients during examinations can be reduced by up to 75% compared to the full-dose procedure.</div></div><div><h3>Conclusion:</h3><div>Our original method combines a rebinning strategy with a novel statistical iterative reconstruction procedure. This approach enables a significant reduction in the dose absorbed by patients. Additionally, our reconstruction algorithm is extremely fast, taking approximately 26 s for all operations on a mid-range GPU. This efficiency is primarily due to the implementation of an FFT algorithm during the most computationally demanding calculations (convolutions) involved in the iterative reconstruction procedure. This feature is particularly valuable in ambulatory diagnostics.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108903"},"PeriodicalIF":4.9,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AReS: A patient simulator to facilitate testing of automated anesthesia","authors":"Sara Hosseinirad ,&nbsp;Manuela Merlo ,&nbsp;Francesco Trovò ,&nbsp;Emiliano Tognoli ,&nbsp;Alberto M. Metelli ,&nbsp;Guy A. Dumont","doi":"10.1016/j.cmpb.2025.108901","DOIUrl":"10.1016/j.cmpb.2025.108901","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>This paper presents the Anesthesia Response Simulator, a novel, open-source patient simulator developed to replicate physiological responses to four commonly used drugs: propofol, remifentanil, norepinephrine, and rocuronium during anesthesia. It models depth of hypnosis, cardiac output, mean arterial pressure, heart rate, stroke volume, and neuromuscular blockade. Developed through integrated clinical practice, literature models, and medical expertise, it aims to facilitate the development of decision-making systems for anesthesia.</div></div><div><h3>Methods:</h3><div>The simulator integrates population-based and subject-specific pharmacokinetics-pharmacodynamics models, a target-controlled infusion system, and a novel approach to simulate surgical stimuli based on drug concentrations. Both surgical stimuli and intravascular volume status are modeled as disturbances to the anesthesia state. The simulator was evaluated through a series of experiments. The median absolute error between the simulated response and clinical recordings from 10 patients is compared with each output’s maximum reasonable measurement errors. To ensure that the model’s response aligns with existing literature and clinical practice, we analyzed the output sensitivities to drug infusion rates and illustrated the output responses to the simulated disturbances.</div></div><div><h3>Results:</h3><div>For most patients, the median absolute errors between simulated and clinical recordings were within reasonable measurement ranges for each output. Although we incorporate inter-individual variability using subject-specific pharmacokinetics-pharmacodynamics models, the median response accurately reflected clinical trends for depth of hypnosis, cardiac output, mean arterial pressure, heart rate, and stroke volume. This finding validates the simulator’s representation of the median population response. The output sensitivity analysis, conducted across various drug infusion rates, identifies the impact of each drug on each output. Finally, the sensitivity analysis and illustration of disturbance effects confirm that the simulator’s performance is consistent with the literature and clinical practice.</div></div><div><h3>Conclusion:</h3><div>This simulator models median responses of the population to four drugs, inter-individual variability, and disturbances according to current literature and expert knowledge. This open-source tool is suitable for various objectives in developing and evaluating multi-variable closed-loop controllers and decision support systems for anesthesia. We also identify limitations that encourage future work on improving the simulator.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"269 ","pages":"Article 108901"},"PeriodicalIF":4.9,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel dura mater cutting simulation model based on fracture mechanics and PBD constraints","authors":"Quan Shi ,&nbsp;Peter Xiaoping Liu ,&nbsp;Yanni Zou","doi":"10.1016/j.cmpb.2025.108926","DOIUrl":"10.1016/j.cmpb.2025.108926","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Virtual reality-based neurosurgical simulators show increasing potential for surgical training and preoperative planning. However, existing cutting models often lack a physics-based rupture mechanism and fail to preserve the biomechanical characteristics of soft tissue incisions, limiting their applicability to dura mater cutting simulations. Given the thin structure of the dura mater and its proximity to soft brain tissues, predicting rupture occurrences is essential. To address these challenges, this study presents a novel dura mater cutting model that enhances rupture prediction, incision realism, and simulation visualization.</div></div><div><h3>Methods</h3><div>A novel approach integrating Position-Based Dynamics with fracture mechanics to model dura mater cutting is introduced. The model employs the von Mises stress threshold criterion to estimate rupture initiation and location. Incision smoothing and mass redistribution techniques are employed to enhance incision geometry while preserving mass conservation. Additionally, adaptive constraints are used to simulate the post-cutting shrinkage effect of the dura mater.</div></div><div><h3>Results</h3><div>The presented model provides stable and realistic results during dura mater cutting simulation. The physics-based rupture results achieved are well aligned with those from ABAQUS finite element software, with a maximum discrepancy of 11.3%, while enabling real-time fracture prediction. Validation through stress distribution and cutting force analysis confirms the accuracy of the model, which in the meantime preserves computational efficiency and supports interactive visualization. Furthermore, the incision optimization and shrinkage simulation reproduce smooth incision and characteristic shrinkage behavior of the dura mater.</div></div><div><h3>Conclusions</h3><div>The presented model offers a new approach to the simulation of dura mater cutting, integrating rupture prediction, incision optimization, and post-incision shrinkage. This is very important and meaningful in virtual neurosurgical simulation, enhancing surgical training and planning.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108926"},"PeriodicalIF":4.9,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty-based cardiac image registration using variational autoencoder with nonuniformly spaced control points","authors":"Yong Hua,&nbsp;Haosheng Su,&nbsp;Xuan Yang","doi":"10.1016/j.cmpb.2025.108904","DOIUrl":"10.1016/j.cmpb.2025.108904","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>The Variational Bayesian (VB) image registration model has garnered recent attention for its ability to offer uncertainty, particularly in the context of cardiac motion estimation. Nonetheless, several challenges have plagued VB image registration. Firstly, the Convolutional Neural Networks (CNNs) in VB excel with grid-based image features make it challenging to extract features from non-uniformly located points located at tissue boundaries. Secondly, the underutilization of VB-provided uncertainty and the misfocus of the regions of interest (ROIs) lead to misleading generative likelihoods. Lastly, existing VB prior distributions struggle to balance the posterior-prior gap and reconstruction accuracy.</div></div><div><h3>Methods:</h3><div>To address these concerns, we extend the VB image registration model by incorporating non-uniformly spaced control points that specifically target displacements at object boundaries. We develop a network capable of concurrently extracting image and spatial features from non-uniformly spaced control points. The uncertainty of the Displacement Vector Field (DVF) is integrated to prioritize matching ROIs in two images and enhance generative likelihood. Additionally, Our VB model employs a factorized prior to regularize the posterior distribution. Theoretical analysis shows that the factorized prior reduces the KL divergence between the posterior and the prior.</div></div><div><h3>Results:</h3><div>Results on four public datasets demonstrate that our network outperforms state-of-the-art registration networks while providing valuable uncertainty information on registration outcomes.</div></div><div><h3>Conclusions:</h3><div>Experiments confirm that our VB image registration utilizing non-uniformly spaced control points effectively extracts features from boundary, and the uncertainty-based generative likelihood guides the DVF to match ROIs accurately across images. The factorized prior significantly improves reconstruction accuracy compared to existing priors.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"269 ","pages":"Article 108904"},"PeriodicalIF":4.9,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Expanding point cloud statistical shape model applications: Generalized vascular modeling for population-level hemodynamic simulations","authors":"Yao Zeng ,&nbsp;Zheng Sun ,&nbsp;Mengfei Wang ,&nbsp;Zhuo Li ,&nbsp;Ao Liu ,&nbsp;Meixiu Pan ,&nbsp;Haifeng Zhao ,&nbsp;Yuehua Li","doi":"10.1016/j.cmpb.2025.108924","DOIUrl":"10.1016/j.cmpb.2025.108924","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Population-scale hemodynamic research faces limitations due to the trade-off between computationally expensive patient-specific Computational Fluid Dynamics (CFD) and overly idealized cylindrical models. To overcome this, we propose a novel Tier-2 workflow that integrates point-cloud statistical shape modeling (Pcd-SSM) with HDBSCAN clustering. This approach aims to efficiently characterize the C1 geometries of the internal carotid artery (ICA) and analyze their corresponding flow patterns.</div></div><div><h3>Materials and Methods</h3><div>Time-of-flight Magnetic Resonance Angiography (TOF-MRA) data from 229 ICAs (171 normal, 58 with 30–50 % stenosis) were converted into 1024-point correspondences using Point2SSM. Principal Component Analysis (PCA), retaining 95 % variance, was applied before unsupervised clustering. A bootstrap-FDR test on 97 normal cases established the global replacement limit, <em>Ncrit</em> = 40. Cluster mean models were then meshed and evaluated using steady, non-Newtonian CFD simulations. The results were benchmarked against individual simulations and diameter-based models.</div></div><div><h3>Results</h3><div>This framework significantly enhances the accuracy (error reduction of 77–95 %) and efficiency (computational cost reduced by approximately 65 times) of hemodynamic simulations in medium-to-large cohorts (Tier 2). Applied to stenosed arterial segments, the model successfully captured approximately 91 % of velocity increases and 51 % of pressure drops, accurately revealing high wall shear stress distributions.</div></div><div><h3>Conclusion</h3><div>Our \"tier-and-cluster\" generalization framework, driven by deep learning Pcd-SSM, provides a unified and transferable paradigm for analyzing complex vascular morphology and blood flow. It offers a robust tool for population-level blood flow studies, individualized risk stratification, exploration of pathological mechanisms, and evaluation of intervention timing for vascular stenosis.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"269 ","pages":"Article 108924"},"PeriodicalIF":4.9,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fine-grained image generation with EEG multi-level semantics","authors":"Wenjie Cheng ,&nbsp;Jun Tan ,&nbsp;Lizhi Wang ,&nbsp;María Trinidad Herrero ,&nbsp;Hong Zeng","doi":"10.1016/j.cmpb.2025.108909","DOIUrl":"10.1016/j.cmpb.2025.108909","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Decoding visual information from electroencephalography (EEG) signals is crucial in neuroscience and artificial intelligence. While existing methods have been able to extract high-level features such as object categories, the capability of extracting fine-grained attributes, such as color distribution, remains insufficient. In this work, we propose EEG2IM, a novel framework that integrates multi-level EEG semantic features to guide a diffusion model for fine-grained image generation.</div></div><div><h3>Methods:</h3><div>In EEG2IM, high-level semantic features are extracted by using a high-level semantic encoder, trained via knowledge distillation, and learnt from the ResNet50 network by response-based and feature-based methods, respectively; and low-level features, i.e., fine-grained attributes, are extracted by using a low-level semantic encoder and aligned with image features from an autoencoder via joint training. These multi-level features are incorporated into a diffusion model using Feature-wise Linear Modulation (FiLM), which enables precise control over image synthesis while preserving both semantic consistency and fine-grained details.</div></div><div><h3>Results and Conclusions:</h3><div>EEG2IM was validated on ImageNet-40 and ImageNet-4, demonstrating superior performance in classification and image generation. It achieved 99.95% accuracy on ImageNet-40 and 92.55% accuracy on ImageNet-4. For image generation, EEG2IM outperformed existing methods, achieving an Inception Score (IS) of 17.58 and Fréchet Inception Distance (FID) of 52.84 on ImageNet-40, and an IS of 8.79 with an FID of 19.49 on ImageNet-4. These results highlight EEG2IM’s ability to capture both high-level semantics and low-level details, advancing fine-grained EEG-based image generation.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"269 ","pages":"Article 108909"},"PeriodicalIF":4.9,"publicationDate":"2025-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiating characteristics of EMG signals in pediatric muscle tone disorders in the aspect of evaluating postural control","authors":"Aleksandra Tuszy ,&nbsp;Patrycja Romaniszyn-Kania ,&nbsp;Damian Kania ,&nbsp;Andrzej Myśliwiec ,&nbsp;Andrzej Mitas","doi":"10.1016/j.cmpb.2025.108910","DOIUrl":"10.1016/j.cmpb.2025.108910","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Abnormalities in muscle tone, such as postural hypotonia, can significantly affect motor development and postural control in children, often presenting with unclear origins and subtle clinical manifestations. These disturbances may also be associated with broader musculoskeletal dysfunctions. The presented research aims to examine whether electromyographic signal analysis can support the objective evaluation of muscle tone abnormalities in children.</div></div><div><h3>Methods:</h3><div>Electromyography (EMG) signals were recorded from the sternocleidomastoid and rectus abdominis muscles during the Neck Flexor Endurance Test in 31 children. Time-domain and frequency-domain characteristics were analyzed using statistical methods to differentiate groups classified by physiotherapy experts. Machine learning methods were used to objectively verify the usefulness of the collected data in classification tasks. Statistical analysis included group comparison using Student’s t-test or non-parametric Mann–Whitney U test, where applicable.</div></div><div><h3>Results:</h3><div>Compensatory mechanisms were observed in children with reduced muscle tone, with increased activation of the rectus abdominis muscles. EMG analysis revealed that the rectus abdominis muscles exhibited 25 statistically important features. Feature selection methods like RefielF presented the most differentiating set from sternocleidomastoid muscles (20 features). The Support Vector Machine showed the best overall performance (78.8%) with mean value data set.</div></div><div><h3>Conclusions:</h3><div>The EMG signal analysis revealed significant differences between children with reduced muscle tone and those with normal tone, emphasizing its clinical relevance for pediatric rehabilitation. The promising performance of the tested models suggests that this line of research may be warranted. These findings lay the groundwork for future work and underscore the need for further research on a larger sample to confirm and refine these observations.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"270 ","pages":"Article 108910"},"PeriodicalIF":4.9,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}