Computers in biology and medicine最新文献

{"title":"Quantifying the frequency modulation in electrograms during simulated atrial fibrillation in 2D domains.","authors":"Juan P Ugarte, Alejandro Gómez-Echavarría, Catalina Tobón","doi":"10.1016/j.compbiomed.2024.109228","DOIUrl":"10.1016/j.compbiomed.2024.109228","url":null,"abstract":"<p><p>Atrial fibrillation (AF) affects millions of people in the world, causing increased morbidity and mortality. Treatment involves antiarrhythmic drugs and catheter ablation, showing high success for paroxysmal AF but challenges for persistent AF. Experimental evidence suggests reentrant waves and rotors contribute to AF substrates. Ablation procedures rely on electroanatomical maps and electrogram (EGM) signals; however, current methods used in clinical practice lack consideration for time-frequency varying EGM components. The fractional Fourier transform (FrFT) can be adopted to capture time-varying frequency components, thereby enhancing the comprehension of arrhythmogenic substrates during AF for improved ablation strategies. To this end, a FrFT-based algorithm is developed to characterize non-stationary components in EGM signals from simulated AF episodes. The proposed algorithm comprises a pre-processing step to enhance the coarser features of the EGM waveform, a windowing process for dynamic assessment of the EGM, and a FrFT order optimization stage that seeks compact signal representations in fractional Fourier domains. The resulting order is related to the rate of frequency change in the signal, making it a useful indicator for frequency-modulated components. The FrFT-based algorithm is implemented on EGM signals from AF simulations in 2D domains representing a region of the atrial tissue. Consequently, the computed optimum FrFT orders are used to build maps that are spatially correlated to the underlying propagation dynamics of the simulated AF episode. The results evince that the extreme values in the optimum orders map pinpoint the localization of fibrillatory mechanisms, generating EGM activation waveforms with varying frequency content over time.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"182 ","pages":"109228"},"PeriodicalIF":7.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142371210","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":"Towards dental diagnostic systems: Synergizing wavelet transform with generative adversarial networks for enhanced image data fusion.","authors":"Abdullah A Al-Haddad, Luttfi A Al-Haddad, Sinan A Al-Haddad, Alaa Abdulhady Jaber, Zeashan Hameed Khan, Hafiz Zia Ur Rehman","doi":"10.1016/j.compbiomed.2024.109241","DOIUrl":"10.1016/j.compbiomed.2024.109241","url":null,"abstract":"<p><p>The advent of precision diagnostics in pediatric dentistry is shifting towards ensuring early detection of dental diseases, a critical factor in safeguarding the oral health of the younger population. In this study, an innovative approach is introduced, wherein Discrete Wavelet Transform (DWT) and Generative Adversarial Networks (GANs) are synergized within an Image Data Fusion (IDF) framework to enhance the accuracy of dental disease diagnosis through dental diagnostic systems. Dental panoramic radiographs from pediatric patients were utilized to demonstrate how the integration of DWT and GANs can significantly improve the informativeness of dental images. In the IDF process, the original images, GAN-augmented images, and wavelet-transformed images are combined to create a comprehensive dataset. DWT was employed for the decomposition of images into frequency components to enhance the visibility of subtle pathological features. Simultaneously, GANs were used to augment the dataset with high-quality, synthetic radiographic images indistinguishable from real ones, to provide robust data training. These integrated images are then fed into an Artificial Neural Network (ANN) for the classification of dental diseases. The utilization of the ANN in this context demonstrates the system's robustness and culminates in achieving an unprecedented accuracy rate of 0.897, 0.905 precision, recall of 0.897, and specificity of 0.968. Additionally, this study explores the feasibility of embedding the diagnostic system into dental X-ray scanners by leveraging lightweight models and cloud-based solutions to minimize resource constraints. Such integration is posited to revolutionize dental care by providing real-time, accurate disease detection capabilities, which significantly reduces diagnostical delays and enhances treatment outcomes.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"182 ","pages":"109241"},"PeriodicalIF":7.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142371211","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":"Effective deep-learning brain MRI super resolution using simulated training data","authors":"Aymen Ayaz ,&nbsp;Rien Boonstoppel ,&nbsp;Cristian Lorenz ,&nbsp;Juergen Weese ,&nbsp;Josien Pluim ,&nbsp;Marcel Breeuwer","doi":"10.1016/j.compbiomed.2024.109301","DOIUrl":"10.1016/j.compbiomed.2024.109301","url":null,"abstract":"<div><h3>Background:</h3><div>In the field of medical imaging, high-resolution (HR) magnetic resonance imaging (MRI) is essential for accurate disease diagnosis and analysis. However, HR imaging is prone to artifacts and is not universally available. Consequently, low-resolution (LR) MRI images are typically acquired. Deep learning (DL)-based super-resolution (SR) techniques can transform LR images into HR quality. However, these techniques require paired HR-LR data for training the SR networks.</div></div><div><h3>Objective:</h3><div>This research aims to investigate the potential of simulated brain MRI data to train DL-based SR networks.</div></div><div><h3>Methods:</h3><div>We simulated a large set of anatomically diverse, voxel-aligned, and artifact-free brain MRI data at different resolutions. We utilized this simulated data to train four distinct DL-based SR networks and augment their training. The trained networks were then evaluated using real data from various sources.</div></div><div><h3>Results:</h3><div>With our trained networks, we produced <span><math><mrow><mn>0</mn><mo>.</mo><mn>7</mn><mspace></mspace><mi>mm</mi></mrow></math></span> SR images from standard <span><math><mrow><mn>1</mn><mspace></mspace><mi>mm</mi></mrow></math></span> resolution multi-source T1w brain MRI. Our experimental results demonstrate that the trained networks significantly enhance the sharpness of LR input MR images. For single-source images, the performance of networks trained solely on simulated data is slightly inferior to those trained solely on real data, with an average structural similarity index (SSIM) difference of 0.025. However, networks augmented with simulated data outperform those trained on single-source real data when evaluated across datasets from multiple sources.</div></div><div><h3>Conclusion:</h3><div>Paired HR-LR simulated brain MRI data is suitable for training and augmenting diverse brain MRI SR networks. Augmenting the training data with simulated data can enhance the generalizability of the SR networks across real datasets from multiple sources.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109301"},"PeriodicalIF":7.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561299","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":"Refining ADHD diagnosis with EEG: The impact of preprocessing and temporal segmentation on classification accuracy","authors":"Sandra García-Ponsoda ,&nbsp;Alejandro Maté ,&nbsp;Juan Trujillo","doi":"10.1016/j.compbiomed.2024.109305","DOIUrl":"10.1016/j.compbiomed.2024.109305","url":null,"abstract":"<div><h3>Background:</h3><div>EEG signals are commonly used in ADHD diagnosis, but they are often affected by noise and artifacts. Effective preprocessing and segmentation methods can significantly enhance the accuracy and reliability of ADHD classification.</div></div><div><h3>Methods:</h3><div>We applied filtering, ASR, and ICA preprocessing techniques to EEG data from children with ADHD and neurotypical controls. The EEG recordings were segmented, and features were extracted and selected based on statistical significance. Classification was performed using various EEG segments and channels with Machine Learning models (SVM, KNN, and XGBoost) to identify the most effective combinations for accurate ADHD diagnosis.</div></div><div><h3>Results:</h3><div>Our findings show that models trained on later EEG segments achieved significantly higher accuracy, indicating the potential role of cognitive fatigue in distinguishing ADHD. The highest classification accuracy (86.1%) was achieved using data from the P3, P4, and C3 channels, with key features such as Kurtosis, Katz fractal dimension, and power spectrums in the Delta, Theta, and Alpha bands contributing to the results.</div></div><div><h3>Conclusion:</h3><div>This study highlights the importance of preprocessing and segmentation in improving the reliability of ADHD diagnosis through EEG. The results suggest that further research on cognitive fatigue and segmentation could enhance diagnostic accuracy in ADHD patients.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109305"},"PeriodicalIF":7.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553596","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":"Hybrid offline and self-knowledge distillation for acute ischemic stroke lesion segmentation from non-contrast CT scans","authors":"Ziying Wang ,&nbsp;Hongqing Zhu ,&nbsp;Jiahao Liu ,&nbsp;Ning Chen ,&nbsp;Bingcang Huang ,&nbsp;Weiping Lu ,&nbsp;Ying Wang","doi":"10.1016/j.compbiomed.2024.109312","DOIUrl":"10.1016/j.compbiomed.2024.109312","url":null,"abstract":"<div><div>Diagnosing and treating Acute Ischemic Stroke (AIS) within 0-24 h of onset is critical for patient recovery. While Diffusion-Weighted Imaging (DWI) and Computed Tomography Perfusion (CTP) are effective for early infarction identification, Non-Contrast CT (NCCT) remains the first-line imaging modality in emergency settings due to its efficiency and cost-effectiveness. In this work, to enhance lesion segmentation in NCCT using multi-modal information, we propose OS-AISeg, which integrates Offline knowledge distillation with Self-knowledge distillation to realize AIS segmentation. Initially, we trained a multi-modality teacher network by introducing uncertainty through Subjective Logic (SL) theory to reduce prediction errors and stabilize the training process. Subsequently, during student network training, we integrate confidence region knowledge guided by uncertainty weights and feature structure information guided by brain asymmetry. The former facilitates the acquisition of effective contextual information from paired predictions, while the latter leverages asymmetric activation maps to extract high-level structural content from multi-modality images. In self-knowledge distillation, we enhance the student network’s learning of consistent global feature distributions by introducing mirrored NCCT images, thereby aiding the network in extracting knowledge directly from the modality. OS-AISeg was evaluated through five-fold cross-validation on two publicly available datasets, achieving a Dice value of 0.6196 on AISD and 0.4841 on ISLES2018. Additionally, experiments were also conducted on an external dataset, BraTS2019, as well as on a private stroke dataset named GLis. Strong correlations were observed between segmented Early Infarct (EI) and ground truth in volume analysis, validating the effectiveness of the proposed method in AIS diagnosis. The code for this project is available at <span><span>https://github.com/Uni-Summer/OS-AISeg</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109312"},"PeriodicalIF":7.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553597","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":"Automated detection and labeling of posterior teeth in dental bitewing X-rays using deep learning","authors":"Mashail Alsolamy ,&nbsp;Farrukh Nadeem ,&nbsp;Amr Ahmed Azhari ,&nbsp;Wafa Alsolami ,&nbsp;Walaa Magdy Ahmed","doi":"10.1016/j.compbiomed.2024.109262","DOIUrl":"10.1016/j.compbiomed.2024.109262","url":null,"abstract":"<div><div>Standardized tooth numbering is crucial in dentistry for accurate recordkeeping, targeted procedures, and effective communication in both clinical and forensic contexts. However, conventional manual methods are prone to errors, time-consuming, and susceptible to inconsistencies. This study presents an artificial intelligence (AI)-powered system that uses a deep learning-based object detection approach to automate tooth numbering in bitewing radiographs (BRs). The system follows the widely accepted FDI two-digit notation system and employs a state-of-the-art YOLO architecture. This one-stage model provides fast inference by simultaneously performing object detection and classification. A comprehensive dataset of 3000 adult digital BRs was used for training and evaluation, covering various scenarios to improve the robustness of the tooth numbering approach. Performance was assessed based on precision, recall, and mean average precision (mAP). The proposed method showcases the potential of AI-powered systems utilizing sophisticated YOLO architectures to automatically detect and label teeth in dental X-rays. It achieved impressive results, demonstrating a precision of 0.99 and 0.963, recall of 0.995 and 0.965, and mAP of 0.99 and 0.963 for tooth detecting and tooth numbering, respectively. With an average inference time of 303 ms per BR when using a central processing unit (CPU) and 9.1 ms when using a graphics processing unit (GPU), the system seamlessly integrates into clinical workflows without sacrificing efficiency. This results in significant time savings for dental professionals while maintaining productivity in fast-paced clinical environments.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109262"},"PeriodicalIF":7.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142544183","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":"Biomechanics and clinical implications of Fontan upsizing","authors":"Vijay Govindarajan ,&nbsp;Akshita Sahni ,&nbsp;Emily Eickhoff ,&nbsp;Peter Hammer ,&nbsp;David M. Hoganson ,&nbsp;Rahul H. Rathod ,&nbsp;Pedro J. del Nido","doi":"10.1016/j.compbiomed.2024.109317","DOIUrl":"10.1016/j.compbiomed.2024.109317","url":null,"abstract":"<div><h3>Background</h3><div>The Fontan operation, a palliative procedure for single ventricle patients, has evolved to improve outcomes and reduce complications. While extracardiac conduit (ECC) is favored for its simplicity and potential hemodynamic benefits, concerns arise about conduit size adequacy over time. Undersized ECC conduits may cause hemodynamic inefficiencies and long-term complications, while oversizing can lead to flow disturbances, stagnation, and thrombosis, necessitating surgical revision or upsizing to optimize hemodynamics.</div></div><div><h3>Objectives</h3><div>The study aimed to predict the impact of upsizing by developing a patient-specific workflow using cardiac magnetic resonance-based imaging and computational fluid dynamics to assess Fontan hemodynamic changes and determine the most optimal conduit size.</div></div><div><h3>Methods</h3><div>We simulated upsizing in patient-specific models, computing reduction in power loss (PL), and analyzed pressure gradients, wall shear stress (WSS), and other local flow dynamic parameters such as vorticity and viscous dissipation that influence PL in a Fontan. Additionally, we quantified the impact of upsizing on hepatic flow distribution (HFD).</div></div><div><h3>Results</h3><div>Across the patient cohort, upsizing resulted in a PL reduction of 16 %–63 %, with the greatest reduction observed in patients with the smallest pre-existing conduit sizes (14 mm). The optimal conduit size for minimizing PL was highly patient-specific. For instance, a 20 mm conduit reduced PL by 63 % in one patient, while another patient showed 16 % reduction with upsizing. Pressure gradients decreased by 15 %–35 %, correlating with the reduction in PL, while WSS decreased consistently with upsizing. Vorticity and viscous dissipation exhibited more variability but followed the overall trend of reduced PL. HFD changes were modest with a maximum variation of 30 %.</div></div><div><h3>Conclusions</h3><div>Our findings underscore the importance of individualized approaches in Fontan conduit upsizing. CFD-based quantitative evaluations of PL, pressure gradients, HFD, and WSS can guide optimal conduit sizing, improving long-term outcomes for patients.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109317"},"PeriodicalIF":7.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142544191","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":"Comparative accuracy of artificial intelligence chatbots in pulpal and periradicular diagnosis: A cross-sectional study","authors":"João Daniel Mendonça de Moura ,&nbsp;Carlos Eduardo Fontana ,&nbsp;Vitor Henrique Reis da Silva Lima ,&nbsp;Iris de Souza Alves ,&nbsp;Paulo André de Melo Santos ,&nbsp;Patrícia de Almeida Rodrigues","doi":"10.1016/j.compbiomed.2024.109332","DOIUrl":"10.1016/j.compbiomed.2024.109332","url":null,"abstract":"<div><h3>Objectives</h3><div>This study aimed to evaluate the diagnostic accuracy and treatment recommendation performance of four artificial intelligence chatbots in fictional pulpal and periradicular disease cases. Additionally, it investigated response consistency and the influence of text order and language on chatbot performance.</div></div><div><h3>Methods</h3><div>In this cross-sectional comparative study, eleven cases representing various pulpal and periradicular pathologies were created. These cases were presented to four chatbots (ChatGPT 3.5, ChatGPT 4.0, Bard, and Bing) in both Portuguese and English, with the information order varied (signs and symptoms first or imaging data first). Statistical analyses included the Kruskal-Wallis test, Dwass-Steel-Critchlow-Fligner pairwise comparisons, simple logistic regression, and the binomial test.</div></div><div><h3>Results</h3><div>Bing and ChatGPT 4.0 achieved the highest diagnostic accuracy rates (86.4 % and 85.3 % respectively), significantly outperforming ChatGPT 3.5 (46.5 %) and Bard (28.6 %) (p &lt; 0.001). For treatment recommendations, ChatGPT 4.0, Bing, and ChatGPT 3.5 performed similarly (94.4 %, 93.2 %, and 86.3 %, respectively), while Bard exhibited significantly lower accuracy (75 %, p &lt; 0.001). No significant association between diagnosis and treatment accuracy was found for Bard and Bing, but a positive association was observed for ChatGPT 3.5 and ChatGPT 4.0 (p &lt; 0.05). The overall consistency rate was 98.29 %, with no significant differences related to text order or language. Cases presented in Portuguese prompted significantly more additional information requests than those in English (33.5 % vs. 10.2 %; p &lt; 0.001), with the relevance of this information being higher in Portuguese (29.5 % vs. 8.5 %; p &lt; 0.001).</div></div><div><h3>Conclusions</h3><div>Bing and ChatGPT 4.0 demonstrated superior diagnostic accuracy, while Bard showed the lowest accuracy in both diagnosis and treatment recommendations. However, the clinical application of these tools necessitates critical interpretation by dentists, as chatbot responses are not consistently reliable.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109332"},"PeriodicalIF":7.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142544192","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":"On efficient expanding training datasets of breast tumor ultrasound segmentation model","authors":"Caicai Zhang ,&nbsp;Mei Mei ,&nbsp;Zhuolin Mei ,&nbsp;Bin Wu ,&nbsp;Shasha Chen ,&nbsp;Minfeng Lu ,&nbsp;Chenglang Lu","doi":"10.1016/j.compbiomed.2024.109274","DOIUrl":"10.1016/j.compbiomed.2024.109274","url":null,"abstract":"<div><div>Automatic segmentation of breast tumor ultrasound images can provide doctors with objective and efficient references for lesions and regions of interest. Both dataset optimization and model structure optimization are crucial for achieving optimal image segmentation performance, and it can be challenging to satisfy the clinical needs solely through model structure enhancements in the context of insufficient breast tumor ultrasound datasets for model training. While significant research has focused on enhancing the architecture of deep learning models to improve tumor segmentation performance, there is a relative paucity of work dedicated to dataset augmentation. Current data augmentation techniques, such as rotation and transformation, often yield insufficient improvements in model accuracy. The deep learning methods used for generating synthetic images, such as GANs is primarily applied to produce visually natural-looking images. Nevertheless, the accuracy of the labels for these generated images still requires manual verification, and the images exhibit a lack of diversity. Therefore, they are not suitable for the training datasets augmentation of image segmentation models. This study introduces a novel dataset augmentation approach that generates synthetic images by embedding tumor regions into normal images. We explore two synthetic methods: one using identical backgrounds and another with varying backgrounds. Through experimental validation, we demonstrate the efficiency of the synthetic datasets in enhancing the performance of image segmentation models. Notably, the synthetic method utilizing different backgrounds exhibits superior improvement compared to the identical background approach. Our findings contribute to medical image analysis, particularly in tumor segmentation, by providing a practical and effective dataset augmentation strategy that can significantly improve the accuracy and reliability of segmentation models.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109274"},"PeriodicalIF":7.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142544193","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":"Plasma protein-based identification of neuroimage-driven subtypes in mild cognitive impairment via protein-protein interaction aware explainable graph propagational network","authors":"Sunghong Park ,&nbsp;Doyoon Kim ,&nbsp;Heirim Lee ,&nbsp;Chang Hyung Hong ,&nbsp;Sang Joon Son ,&nbsp;Hyun Woong Roh ,&nbsp;Dokyoon Kim ,&nbsp;Yonghyun Nam ,&nbsp;Dong-gi Lee ,&nbsp;Hyunjung Shin ,&nbsp;Hyun Goo Woo","doi":"10.1016/j.compbiomed.2024.109303","DOIUrl":"10.1016/j.compbiomed.2024.109303","url":null,"abstract":"<div><div>As an early indicator of dementia, mild cognitive impairment (MCI) requires specialized treatment according to its subtypes for the effective prevention and management of dementia progression. Based on the neuropathological characteristics, MCI can be classified into Alzheimer's disease (AD)-related cognitive impairment (ADCI) and subcortical vascular cognitive impairment (SVCI), being more likely to progress to AD and subcortical vascular dementia (SVD), respectively. For identifying MCI subtypes, plasma protein biomarkers are recently seen as promising tools due to their minimal invasiveness and cost-effectiveness in diagnostic procedures. Furthermore, the application of machine learning (ML) has led the preciseness in the biomarker discovery and the resulting diagnostics. Nevertheless, previous ML-based studies often fail to consider interactions between proteins, which are essential in complex neurodegenerative disorders such as MCI and dementia. Although protein-protein interactions (PPIs) have been employed in network models, these models frequently do not fully capture the diverse properties of PPIs due to their local awareness. This limitation increases the likelihood of overlooking critical components and amplifying the impact of noisy interactions. In this study, we introduce a new graph-based ML model for classifying MCI subtypes, called <em>eXplainable Graph Propagational Network</em> (XGPN). The proposed method extracts the globally interactive effects between proteins by propagating the independent effect of plasma proteins on the PPI network, and thereby, MCI subtypes are predicted by estimation of the risk effect of each protein. Moreover, the process of model training and the outcome of subtype classification are fully explainable due to the simplicity and transparency of XGPN's architecture. The experimental results indicated that the interactive effect between proteins significantly contributed to the distinct differences between MCI subtype groups, resulting in an enhanced classification performance with an average improvement of 10.0 % compared to existing methods, also identifying key biomarkers and their impact on ADCI and SVCI.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"Article 109303"},"PeriodicalIF":7.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142535451","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}