Computer methods and programs in biomedicine最新文献

{"title":"Pattern formation of network epidemic model and its application in oral medicine","authors":"Linhe Zhu ,&nbsp;Yue Li ,&nbsp;Le He ,&nbsp;Shuling Shen","doi":"10.1016/j.cmpb.2025.108688","DOIUrl":"10.1016/j.cmpb.2025.108688","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>The prevention and control of infectious diseases is one of the major public safety issues in the 21 st century. In this paper, a Susceptible–Infected–Recovered (SIR) epidemic model with disease recurrence behavior is established based on continuous space and network environment. The Turing pattern, optimal control and parameter identification of infectious disease models under different network structures are studied.</div></div><div><h3>Methods:</h3><div>We analyze the sufficient conditions for the existence of the disease equilibrium point of the system, and discuss the necessary conditions of Turing instability of the system on homogeneous and heterogeneous networks, respectively. Our work further derives the global optimal solution of the parameters under the target pattern based on optimal control theorem.</div></div><div><h3>Results:</h3><div>The validity of the theoretical analysis is verified by a series of numerical simulations. Meanwhile, we have explored the impact of disease recurrence rate on the spread of infectious diseases on three network structures. It is found that when the recurrence rate <span><math><mi>α</mi></math></span> increases, it will result in a decrease in the recovered population <span><math><mi>R</mi></math></span> as well as an increase in the infected population <span><math><mi>I</mi></math></span>. Furthermore, the public Corona Virus Disease 2019 data are used for fitting verification. The verification results are basically consistent with the development trend of the epidemic, as well as the validity of the model is visually demonstrated.</div></div><div><h3>Conclusions:</h3><div>The complex network model can more accurately simulate the dynamic propagation process of infectious diseases. Combined with optimal control and parameter identification methods, it can provide theoretical support for public health departments to prevent and control infectious diseases. In particular, optimization parameter identification technology can be successfully applied to oral image recognition and adjuvant therapy.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108688"},"PeriodicalIF":4.9,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578502","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":"Targeted drug delivery to the deviated regions of the human nasal cavities: An in silico investigation and in vitro validation","authors":"Kartika Chandra Tripathy,&nbsp;Ajay Bhandari","doi":"10.1016/j.cmpb.2025.108706","DOIUrl":"10.1016/j.cmpb.2025.108706","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Delivering drugs to the deviated regions in patients with nasal septal deviation is vital for the treatment but challenging due to the complex shape of the nasal cavity and the intersubject variability in the nasal anatomies. While previous studies have focused on drug delivery to standard areas like the olfactory region, none have specifically looked at how drugs are deposited in the deviated regions. The current study numerically investigates six drug administration parameters aiming to control and maximize drug deposition in the deviated regions of the nasal cavity in three types of septal deviations.</div></div><div><h3>Methods</h3><div>Three-dimensional models are created using CT scans from three patients, with S-shaped, C-shaped, and reverse C-shaped septal deviations, and the deviated regions are identified by the detailed slice-by-slice inspection method. Eulerian and Lagrangian simulations are performed for the fluid flow and drug delivery, incorporating all six drug administration parameter variations. Further, in-house experiments are performed on a three-dimensional printed transparent nasal cavity to validate the pressure drop and drug deposition patterns.</div></div><div><h3>Results</h3><div>It is observed that increasing the spray half-cone angle decreases the targeted deposition in the C, reverse C, and left side of the S-shaped models. On the contrary, a wider half-cone angle (20°) and cone radius (2 mm) enhances targeted deposition on the right side of the S-shaped model. The ideal particle size range for all models is 10 to 16 µm. Lower initial particle velocities (1 m/s and 3 m/s) lead to maximum targeted deposition in the C and left side of the S-shaped models, while higher ones (14 m/s and 8m/s) enhance targeted deposition in the reverse C and right side of the S-shaped model, respectively. Optimized administration angles accurately direct particles to deviated regions, with patient-specific adjustments achieving better outcomes. Increased flow rates enhance both total and targeted depositions. Head orientation adjustments are effective for deviations in the middle and lower regions but have a limited impact when deviation presents in the anterior regions.</div></div><div><h3>Conclusions</h3><div>The study's findings help unveil the effective targeted drug delivery strategies, provide insights for the better design of the nasal spray device, and improve personalized treatment efficacy for patients with septal deviations.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108706"},"PeriodicalIF":4.9,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601084","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":"Natural Language Processing and soft data for motor skill assessment: A case study in surgical training simulations","authors":"Arash Iranfar ,&nbsp;Mohammad Soleymannejad ,&nbsp;Behzad Moshiri ,&nbsp;Hamid D. Taghirad","doi":"10.1016/j.cmpb.2025.108686","DOIUrl":"10.1016/j.cmpb.2025.108686","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Automated surgical skill assessment using kinematic and video data (hard data) sources has been widely adopted in the literature. However, experts’ opinions (soft data) in the form of free-text could be an invaluable source for evaluating one’s skill level since the availability and semantic richness of the soft data are both higher than the hard data. In this paper, the feasibility of using soft data as a single source of skill assessment is analyzed with various Natural Language Processing (NLP) algorithms of different levels of complexity.</div></div><div><h3>Methods:</h3><div>An experiment named “Vertex Pursuit” was designed to address the absence of a dataset with free-text soft data in synchronization with hard data. This experiment challenges participants’ hand-eye coordination, both-hand coordination, precision, and dexterity by tracking haptic device movements along a star pentagon shape. Top-performing participants receive additional training to provide expert feedback through free-text comments evaluating their peers’ trials. Traditional machine learning approaches are employed, including various word and sentence embedding techniques combined with a diverse set of classifiers, to assess skill levels based on this soft data. Additionally, encoder-only and decoder-only large language models (LLMs) are applied to the data, with the latter leveraging three prompt engineering techniques.</div></div><div><h3>Results:</h3><div>The task of skill assessment using soft data is demonstrated to be a complex NLP task, and as the complexity of the method increases, the results improve. The top performance was achieved with the decoder-only LLMs and the rule-based prompting strategy.</div></div><div><h3>Conclusion:</h3><div>This paper studied the feasibility of using soft data in a simulated surgical skill assessment scenario. While further research is needed, the proposed methods can reduce subjectivity, alleviate the burden on human experts, and enable more widespread, scalable skill evaluation in surgical training programs.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108686"},"PeriodicalIF":4.9,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601085","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":"Evaluating nebulisation and nasal irrigation efficiency in post-operative chronic rhinosinusitis patients through computational fluid dynamics simulation","authors":"Oveis Pourmehran ,&nbsp;Alkis Psaltis ,&nbsp;Sarah Vreugde ,&nbsp;Kavan Zarei ,&nbsp;Yidan Shang ,&nbsp;Kiao Inthavong ,&nbsp;Peter-John Wormald","doi":"10.1016/j.cmpb.2025.108697","DOIUrl":"10.1016/j.cmpb.2025.108697","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Chronic rhinosinusitis (CRS) is a prevalent inflammatory condition that substantially affects patients’ quality of life. Functional endoscopic sinus surgery (FESS) is commonly performed in cases where medical therapy fails. Effective post-operative drug delivery is crucial for improving outcomes. This study uses computational fluid dynamics (CFD) to compare nebulisation and nasal irrigation (bottle wash) in post-operative sinonasal models and to evaluate how anatomical alterations affect drug deposition across various paranasal sinuses.</div></div><div><h3>Methods</h3><div>Eight post-FESS models were generated from the CT scans of a 29-year-old female CRS patient. These models included variations in maxillary ostium sizes, both with and without partial middle turbinectomy. Using 3D Slicer®, images were segmented, and Ansys SpaceClaim® prepared the final geometries. CFD simulations then examined drug delivery efficiency for both nebulisation and nasal irrigation.</div></div><div><h3>Results</h3><div>Nebulisation faces considerable challenges due to sinus complexity; however, surgical modifications improved nebuliser deposition in the maxillary and sphenoid sinuses. In contrast, nasal irrigation showed higher efficiency in delivering drugs to the frontal sinuses. The residual liquid layer on sinus walls after irrigation significantly impacts comparative evaluations of these methods.</div></div><div><h3>Conclusions</h3><div>These findings emphasise the importance of adapting drug delivery strategies to specific surgical and anatomical factors. Tailored post-operative protocols may enhance outcomes in CRS, potentially improving patient comfort and compliance, and reducing recurrence rates. Further investigations are warranted to precisely quantify the liquid layer thickness remaining after irrigation, particularly as head movements can result in medication flowing back from sinuses into the nasal cavity.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108697"},"PeriodicalIF":4.9,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal radiomics based on lesion connectome predicts stroke prognosis","authors":"Ning Wu ,&nbsp;Wei Lu ,&nbsp;Mingze Xu","doi":"10.1016/j.cmpb.2025.108701","DOIUrl":"10.1016/j.cmpb.2025.108701","url":null,"abstract":"<div><h3>Background</h3><div>Stroke significantly contributes to global mortality and disability, emphasizing the critical need for effective prognostic evaluations. Connectome-based lesion-symptom mapping (CLSM) identifies structural and functional connectivity disruptions related to the lesion, while radiomics extracts high-dimensional quantitative data from multimodal medical images. Despite the potential of these methodologies, no study has yet integrated CLSM and multimodal radiomics for acute ischemic stroke (AIS).</div></div><div><h3>Methods</h3><div>This retrospective study analyzed lesion, structural disconnection (SDC), and functional disconnection (FDC) maps of 148 patients with AIS and assessed their association with the National Institutes of Health Stroke Scale (NIHSS) score at admission and prognostic outcomes, measured by the modified Rankin Scale at six months. Additionally, an innovative approach was proposed by utilizing the SDC map as mask, and radiomic features were extracted and selected from T1-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient, susceptibility-weighted imaging, and fluid-attenuated inversion recovery images. Five machine learning classifiers were then used to predict the prognosis of AIS.</div></div><div><h3>Results</h3><div>This study constructed lesion, SDC and FDC maps to correlate with NIHSS scores and prognostic outcomes, thereby revealing the neuroanatomical mechanisms underlying neural damage and prognosis. Poor prognosis was associated with distal cortical dysfunction and fiber disconnection. Fifteen radiomic features within SDC maps from multimodal imaging were selected as inputs for machine learning models. Among the five classifiers tested, Categorical Boosting achieved the highest performance (AUC = 0.930, accuracy = 0.836).</div></div><div><h3>Conclusion</h3><div>A novel model integrating CLSM and multimodal radiomics was proposed to predict long-term prognosis in AIS, which would be a promising tool for early prognostic evaluation and therapeutic planning. Further investigation is needed to assess its robustness in clinical application.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108701"},"PeriodicalIF":4.9,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551622","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 parametric study of motion and attachment to capillary walls of circulating tumor cells (CTCs) interacting with non-activated and activated platelets","authors":"Vladimir Simic ,&nbsp;Aleksandar Nikolic ,&nbsp;Shao Ning ,&nbsp;Miljan Milosevic ,&nbsp;Fransisca Leonard ,&nbsp;Xuewu Liu ,&nbsp;Milos Kojic","doi":"10.1016/j.cmpb.2025.108699","DOIUrl":"10.1016/j.cmpb.2025.108699","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Background and objective&lt;/h3&gt;&lt;div&gt;Our previous research examined the biophysical conditions required for CTC arrest using a custom-built solid–fluid 2D axisymmetric computational model. Application of that model resulted in calculating the limiting conditions under which a CTC can pass through a narrowed capillary with a platelet attached to the capillary wall. This paper is a step forward in determining the effects of a selected set of parameters: number of platelets, CTC diameter, stiffness, and ligand-receptor bond stiffness of the CTC (with or without attached platelets) on the CTC trajectory, its axial position, and its attachment to the wall. Consideration of a single CTC provides the “net” effects of platelets on CTC attachment, although, in reality, there can be many configurations of cells and platelets, leading to additional interactions and outcomes regarding metastasis.&lt;/div&gt;&lt;div&gt;We consider cases where platelets are resting and when they are activated. The effects of platelet activation on cell attachment to the wall—and hence on metastasis—are among the main goals of this paper. Quantification of platelet activation is achieved through an original concept that connects our computational model with data from a unique experimental investigation. The selected parameters provide&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;&lt;strong&gt;:&lt;/strong&gt; The modeling concept of the motion of the CTC and platelets within the fluid relies on a strong coupling approach with a remeshing procedure. Additionally, a 1D FE truss (rope) element is implemented to simulate active ligand-receptor bonds, including the correction of platelet-cell adhesion forces due to platelet activation, as determined experimentally.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;&lt;strong&gt;:&lt;/strong&gt; We have experimentally determined the attractive forces between cells and both non-activated and thrombin-activated platelets. The experimental results are incorporated into our computational models. This parametric study provides insight into the biomechanical conditions for CTC motion and arrest, contributing to the predictive capabilities for metastasis initiation and progression. Relationships are established between the properties of CTCs (size and stiffness), platelet size and stiffness, and ligand-receptor interaction intensity on one side, and the time in contact between CTCs and platelets, as well as the conditions for cell arrest, on the other side.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Conclusions&lt;/h3&gt;&lt;div&gt;&lt;strong&gt;:&lt;/strong&gt; It is found that the number of platelets enhances the adhesion of the CTC to the wall due to effects on the fluid flow field and the overall increase in adhesion force with a higher number of platelets. Furthermore, it was found that adherence (metastasis), under otherwise identical conditions, is enhanced in the case of a softer cell. Although the 2D model simplifies real 3D conditions, it provides insight into the effects of geometrical and material parameters relevant to meta","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108699"},"PeriodicalIF":4.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intra-clustering analysis reveals tissue-specific mutational patterns","authors":"Stamatis Choudalakis ,&nbsp;George A. Kastis ,&nbsp;Nikolaos Dikaios","doi":"10.1016/j.cmpb.2025.108681","DOIUrl":"10.1016/j.cmpb.2025.108681","url":null,"abstract":"<div><h3>Background and objective:</h3><div>The identification of tissue-specific mutational patterns associated with cancer is challenging due to the low frequency of certain mutations and the high variability among tumors within the same cancer type. To address the inter-tumoral heterogeneity issue, our study aims to uncover infrequent mutational patterns by proposing a novel intra-clustering analysis.</div></div><div><h3>Methods:</h3><div>A Network Graph of 8303 patients and 198 genes was constructed using single-point-mutation data from The Cancer Genome Atlas (TCGA). Patient-gene groups were retrieved with the parallel use of two separate methodologies based on the: (a) Barber’s modularity index, and (b) network dynamics. An intra-clustering analysis was employed to explore the patterns within smaller patient subgroups in two phases: i) to determine the significant presence of a gene with a cancer type using the Fisher’s exact test and ii) to determine gene-to-gene patterns using multiple correspondence analysis and DISCOVER. The results are followed by a Benjamini–Hochberg false discovery rate of 5%.</div></div><div><h3>Results:</h3><div>This analysis was applied over 24 statistically meaningful groups of 2619 patients spanning 21 cancer types and it recovered 42 mutational patterns that are not reported in the TCGA consortium publications. Notably, our findings: (i) suggest that AMER1 mutations are a putative separative element between colon and rectal adenocarcinomas, (ii) highlight the significant presence of RAC1 in head and neck squamous cell carcinoma (iii) suggest that EP300 mutations in head and neck squamous cell carcinoma are irrelevant of the HPV status of the patients and (iv) show that mutational-based clusters can contain patients with contrasting genetic alterations.</div></div><div><h3>Conclusions:</h3><div>The proposed intra-clustering analysis extracted statistically significant relationships within clusters, uncovering putative clinically relevant connections and disentangling mutational heterogeneity.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108681"},"PeriodicalIF":4.9,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143572261","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":"Enhancing atrial fibrillation detection in PPG analysis with sparse labels through contrastive learning","authors":"Hong Wu ,&nbsp;Qihan Hu ,&nbsp;Daomiao Wang ,&nbsp;Shiwei Zhu ,&nbsp;Cuiwei Yang","doi":"10.1016/j.cmpb.2025.108698","DOIUrl":"10.1016/j.cmpb.2025.108698","url":null,"abstract":"<div><h3>Background</h3><div>With the advancements in wearable technology, photoplethysmography (PPG) has emerged as a promising technique for detecting atrial fibrillation (AF) due to its ability to capture cardiovascular information. However, current deep learning-based methods has strict requirements on the quantity of labeled data. To overcome this limitation, we explore the performance of self-supervised contrastive learning in PPG-based AF detection.</div></div><div><h3>Methods</h3><div>Our method initially utilizes 1,209 h of unlabeled PPG data from the VitalDB database, conducting self-supervised pretraining using two contrastive learning frameworks, SimCLR and BYOL. Subsequently, the weights of the encoder are transferred and fine-tuned on a small amount of labeled PPG data to complete the AF detection task, including the selected MIMIC III, UMass, and DeepBeat datasets. In the realm of contrastive learning, we investigated seven data augmentation operations to explore their composite and preferred combinations, as well as the effects of double-sided and single-sided transformations.</div></div><div><h3>Results</h3><div>Our research ultimately demonstrated that the preferred combination, incorporating single-sided transformation with the Drift operation, is most suitable for PPG data. Notably, even with only 1 %, 20 %, and 1 % of the training data from the three datasets used for fine-tuning, our approach achieves better F1 scores compared to supervised learning on the respective complete training sets. Additionally, on the 0.01 % DeepBeat training set, fine-tuning still showed a clear advantage over supervised learning.</div></div><div><h3>Conclusion</h3><div>Appropriate self-supervised contrastive pretraining effectively leverages a substantial amount of existing unlabeled PPG data, thus reducing the reliance on labeled data for AF detection, and offering a possible solution to address the limitations posed by the scarcity of labels.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108698"},"PeriodicalIF":4.9,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549324","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":"AutoDPS: An unsupervised diffusion model based method for multiple degradation removal in MRI","authors":"Arunima Sarkar ,&nbsp;Ayantika Das ,&nbsp;Keerthi Ram ,&nbsp;Sriprabha Ramanarayanan ,&nbsp;Suresh Emmanuel Joel ,&nbsp;Mohanasankar Sivaprakasam","doi":"10.1016/j.cmpb.2025.108684","DOIUrl":"10.1016/j.cmpb.2025.108684","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Diffusion models have demonstrated their ability in image generation and solving inverse problems like restoration. Unlike most existing deep-learning based image restoration techniques which rely on unpaired or paired data for degradation awareness, diffusion models offer an unsupervised degradation independent alternative. This is well-suited in the context of restoring artifact-corrupted Magnetic Resonance Images (MRI), where it is impractical to exactly model the degradations apriori. In MRI, multiple corruptions arise, for instance, from patient movement compounded by undersampling artifacts from the acquisition settings.</div></div><div><h3>Methods:</h3><div>To tackle this scenario, we propose AutoDPS, an unsupervised method for corruption removal in brain MRI based on Diffusion Posterior Sampling. Our method (i) performs motion-related corruption parameter estimation using a blind iterative solver, and (ii) utilizes the knowledge of the undersampling pattern when the corruption consists of both motion and undersampling artifacts. We incorporate this corruption operation during sampling to guide the generation in recovering high-quality images.</div></div><div><h3>Results:</h3><div>Despite being trained to denoise and tested on completely unseen corruptions, our method AutoDPS has shown <span><math><mo>∼</mo></math></span> 1.63 dB of improvement in PSNR over baselines for realistic 3D motion restoration and <span><math><mo>∼</mo></math></span> 0.5 dB of improvement for random motion with undersampling. Additionally, our experiments demonstrate AutoDPS’s resilience to noise and its generalization capability under domain shift, showcasing its robustness and adaptability.</div></div><div><h3>Conclusion:</h3><div>In this paper, we propose an unsupervised method that removes multiple corruptions, mainly motion with undersampling, in MRI images which are essential for accurate diagnosis. The experiments show promising results on realistic and composite artifacts with higher improvement margins as compared to other methods. Our code is available at <span><span>https://github.com/arunima101/AutoDPS/tree/master</span><svg><path></path></svg></span></div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108684"},"PeriodicalIF":4.9,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143527371","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":"Preoperative ECG-assisted feature engineering enhances prediction of new-onset atrial fibrillation after cardiac surgery","authors":"Biqi Tang ,&nbsp;Kang He ,&nbsp;Sen Liu ,&nbsp;Zhong Wu ,&nbsp;Cuiwei Yang","doi":"10.1016/j.cmpb.2025.108696","DOIUrl":"10.1016/j.cmpb.2025.108696","url":null,"abstract":"<div><h3>Background</h3><div>New-onset postoperative atrial fibrillation (POAF) is the most common complication following cardiac surgery, associated with adverse outcomes. However, the predictive accuracy of existing models remains unsatisfactory, primarily due to insufficient utilization of electrocardiogram (ECG) data and limitations in model development methodologies. This study aims to develop an accurate prediction model for POAF by comprehensively analyzing the predictive power of various preoperative ECG features.</div></div><div><h3>Methods</h3><div>This study enrolled 92 cardiac surgery patients with no prior history of atrial fibrillation (AF). One-minute ECG segments, extracted from preoperative long-term ECG recordings, were analyzed for P-wave and short-term heart rate variability (HRV) characteristics. A total of 39 HRV indices and 9 P-wave indices were calculated as ECG features. Additionally, clinical baseline characteristics were incorporated into a multi-modal risk assessment model. Using various feature combinations, six machine learning classifiers were applied to assess the predictive efficacy of various models. Finally, an ensemble strategy was implemented to enhance the model's prediction performance for POAF.</div></div><div><h3>Results</h3><div>Statistical analysis revealed significant differences (<em>p</em> &lt; 0.05) in 15 ECG features between patients with POAF and those without, including RR interval unpredictability and the cardiac sympathetic index. The predictive model based solely on clinical baseline characteristics demonstrated high accuracy (78.26 %), sensitivity (78.57 %), and specificity (78.13 %), with superior sensitivity in identifying patients at high risk for POAF compared to existing models. Furthermore, the multi-modal model, which integrated preoperative ECG features and an ensemble machine learning (EML) strategy, demonstrated a significant improvement in prediction performance, with an average accuracy of 81.52 %, sensitivity of 82.14 %, and specificity of 81.25 %.</div></div><div><h3>Conclusion</h3><div>The integration of P-wave and short-term HRV features holds promise for improving the prediction of new-onset POAF. ECG-assisted analysis is a valuable tool for elucidating the underlying mechanisms of POAF and advancing clinical strategies for its prevention and management.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"264 ","pages":"Article 108696"},"PeriodicalIF":4.9,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562683","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}