Brain Informatics最新文献

{"title":"U-Net-based transfer learning for automated tumour segmentation enabling fully automated [¹⁸F]F-DOPA PET analysis in paediatric gliomas.","authors":"Michele Mureddu, Rosella Trò, Federico Giovanni Garau, Nicolò Trebino, Andrea Bianconi, Andrea Rossi, Antonia Ramaglia, Antonio Verrico, Claudia Milanaccio, Giovanni Morana, Massimiliano Iacozzi, Francesco Fiz, Arnoldo Piccardo, Marco Massimo Fato","doi":"10.1186/s40708-026-00296-z","DOIUrl":"10.1186/s40708-026-00296-z","url":null,"abstract":"<p><strong>Background: </strong>PET imaging with [¹⁸F]F-DOPA shows great promise for assessing paediatric gliomas. Manual tumour delineation and parameter extraction are time-consuming and prone to inter-operator variability.</p><p><strong>Methods: </strong>We evaluated whether a deep learning model, leveraging transfer learning from adult glioma datasets, could enable a fully automated pipeline for tumour segmentation and PET parameter extraction. Static and dynamic parameters were compared across three approaches: (i) automatic vs semi-automatic, (ii) automatic vs manual, and (iii) manual vs. semi-automatic. Data from 103 paediatric patients (median age 11 years; 54 females, 49 males) with static and/or dynamic [¹⁸F]F-DOPA PET scans (2011-2024) were retrospectively included for fine-tuning the deep learning model. Statistical and survival analyses were performed on 90 subjects; dynamic analysis included 32 patients.</p><p><strong>Results: </strong> The best model achieved a Dice score of 0.82 ± 0.11 and was integrated into the pipeline for extracting static and dynamic indices. Automatic Tumour-to-Striatum ratio showed high reproducibility across comparisons ((i) p = 0.660, (ii) p = 0.342, (iii) p = 0.639), while Tumour-to-Background differed significantly when comparing manual delineations (p < 0.01). Dynamic parameters demonstrated good reproducibility with the automatic method (p > 0.05). Importantly, both automated static indices correlate significantly with tumour grade, with the overall and progression-free survival (p < 0.05).</p><p><strong>Conclusions: </strong> Transfer learning enabled a fully automatic [¹⁸F]F-DOPA PET pipeline for paediatric gliomas, providing reproducible static and dynamic parameter extraction and correlating with clinically relevant outcomes. This approach reduces operator dependence and streamlines analysis, supporting potential integration into routine clinical practice.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083549/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147515416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perivascular fluid clearance links choroid plexus changes to cognitive performance in cerebral small vessel disease.","authors":"Dan Luo, Bin Yang, Lisha Nie, Peng Zeng, Bang Zeng, Binglan Li, Xiaojuan Dong, Tianyou Luo, Yongmei Li","doi":"10.1186/s40708-026-00297-y","DOIUrl":"10.1186/s40708-026-00297-y","url":null,"abstract":"<p><p>Choroid plexus (CP) dysfunction may impair cerebrospinal fluid (CSF) turnover and perivascular glymphatic clearance, but whether CP microstructural injury correlates to cerebral small vessel disease (CSVD)-related brain alteration and cognitive performance remains unclear. We investigated whether imaging markers of perivascular fluid transport mediate the associations between CP alterations and CSVD pathology. CP microstructure was assessed by mean apparent propagator (MAP) diffusion imaging and χ-separation susceptibility mapping in 139 CSVD patients and 52 healthy controls. Perivascular clearance measures included the diffusion tensor image-along perivascular space (DTI-ALPS) index, basal ganglia free-water fraction (FW-BG), and perivascular space volume fraction (PVSVF-BG). Compared with controls, CSVD patients showed CP microstructural abnormalities and altered perivascular clearance markers, which was identified by random-forest model as predictors of CSVD severity (OOB-AUC = 0.755, 95%CI: 0.641-0.836). Mediation analysis revealed that imaging markers of perivascular fluid clearance significantly mediated the associations between CP alterations and structural brain injury (average causal mediation effect , ACME=-110.118 to 80.121, FDR-p < 0.05). Notably, PVSVF-BG was the only glymphatic imaging metric mediating the links of both CP volume and susceptibility with cognitive performance (ACME=-142.474 to 67.351, FDR-p < 0.05). These findings indicate that CP microstructural injury are present in mild CSVD with the absence of CP volumetric enlargement, and are associated with CSVD markers and cognitive performance, which are mediated by disrupted perivascular fluid transport, highlighting the CP-glymphatic axis as a candidate pathway for further longitudinal and mechanistic investigation.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13018506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147515429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cognitive architecture and behavioral model based on social evidence and resource constraints.","authors":"Anton Kolonin","doi":"10.1186/s40708-026-00294-1","DOIUrl":"10.1186/s40708-026-00294-1","url":null,"abstract":"<p><p>The cognitive architecture presented in this paper is expected to be able to explain certain aspects of human behavior, guide the development of artificial intelligence agents, and align the behavioral patterns of the latter with the former. The architecture is based on the principle of social proof or social evidence, including the principle of resource constraints. It includes the concept of a hybrid knowledge graph that encompasses both symbolic and sub-symbolic knowledge. This knowledge is divided into functional segments for fundamental, social, evidential, and imaginary knowledge, and is processed by an inference engine and a memory storage system that are aware of and manage resource constraints. The architecture and behavioral model derived on its basis are expected to be used to design artificial intelligence agents and decision support systems that are consistent with human values and experiences based on the alignment of their belief systems, capable of implementing decision support systems for practical applications. It can also be proposed for modeling human behavior individually or in a group, for psychological treatment, online security, and community management.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12988104/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147356951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability of electric field simulations in different age groups: impact of data quality metrics.","authors":"Dayana Hayek, Axel Thielscher, Ulrike Grittner, Agnes Flöel, Daria Antonenko","doi":"10.1186/s40708-026-00293-2","DOIUrl":"10.1186/s40708-026-00293-2","url":null,"abstract":"<p><p>Electric field simulations based on individualized Magnetic Resonance Imaging (MRI)-derived head models are increasingly used to optimize non-invasive brain stimulation (NIBS) protocols, enabling individualized dose adjustments to achieve a desired current flow at cortical targets. However, the quality of structural MRI data-affected by motion artefacts, tissue contrast, and scanner-related noise-may influence the accuracy of these simulations, an issue possibly exacerbated in older adults who often exhibit lower image quality. If reduced image quality compromises electric field estimation, it could limit the feasibility of individualized dosing in aging populations. In this study, we examined whether standardized image quality metrics-entropy focus criterion (EFC), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), spatial resolution (FWHM), and intensity non-uniformity (INU)-systematically relate to the magnitude of simulated electric fields in young and older adults. We analysed MRI and simulation data of a focal C3 montage from 106 healthy adults, 47 young adults (mean age: 24.8, age range: 20-35 years) and 59 older adults (mean age: 69.5 years, age range: 60-79) using SimNIBS for computational modelling of the electric fields and MRIQC for image quality assessment. Structural equation modelling was used to quantify direct and indirect effects of age group on electric field magnitude, with image quality as a mediating factor. Head volume was included in extended models to control for anatomical variation. Our findings demonstrate that MR image quality is associated with simulated electric field magnitude, with higher EFC, lower SNR, lower CNR, and higher INU associated with reduced field estimates, and older adults showing generally lower simulated electric fields compared to younger adults. While image quality accounted for some of the age-related differences in electric field strength, group differences remained even after controlling for EFC, SNR and head volume. Critically, electric field simulations remained sufficiently reliable despite lower image quality in older adults, supporting their use for individualized dose adjustment across the lifespan.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12988111/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147272315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal fusion and explainability of artificial intelligence models in Alzheimer's Disease detection.","authors":"Vimbi Viswan, Noushath Shaffi, E Malathy, G Chemmalar Selvi, B R Kavitha, Abdelhamid Abdesselam, Shuqiang Wang, Ponnuthurai N Suganthan, Ibrahim Al Shezawi, Mufti Mahmud","doi":"10.1186/s40708-025-00291-w","DOIUrl":"10.1186/s40708-025-00291-w","url":null,"abstract":"<p><p>The integration of multimodal data has emerged as a powerful strategy for enhancing the accuracy and interpretability of artificial intelligence (AI) models in the diagnosis and prognosis of Alzheimer's Disease (AD). This systematic review presents a comprehensive synthesis of recent advances in AI-driven multimodal fusion approaches for AD prediction. A detailed examination of widely used datasets-including their modalities, preprocessing pipelines, and accessibility-is provided to aid reproducibility and methodological transparency. We analyze and categorize the various data harmonization and preprocessing techniques employed across neuroimaging (e.g., fMRI, sMRI, PET), electrophysiological (EEG), and genomic modalities, highlighting domain-specific practices and challenges. Furthermore, fusion strategies are classified into data-level, feature-level, decision-level, and temporal (early, intermediate, and late) paradigms, offering insights into their implementation and diagnostic impact. The review also investigates the adoption of explainable AI (XAI) techniques across studies and identifies a significant underrepresentation of works that simultaneously emphasize multimodality, explainability, and methodological rigor. By adhering to both PRISMA and Kitchenham's guidelines, this review ensures transparency and replicability in evidence synthesis. Compared to existing reviews, our work uniquely focuses on the intersection of multimodal integration and explainability within a systematically validated framework. The review concludes with recommendations for future research aimed at developing robust, interpretable, and clinically relevant AI models for AD.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":"5"},"PeriodicalIF":4.5,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12876535/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146107785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling 3D mesoscaled neuronal complexity through learning-based dynamic morphometric convolution.","authors":"Yik San Cheng, Runkai Zhao, Heng Wang, Hanchuan Peng, Wojciech Chrzanowski, Weidong Cai","doi":"10.1186/s40708-025-00288-5","DOIUrl":"10.1186/s40708-025-00288-5","url":null,"abstract":"<p><p>Accurate reconstruction of neuronal morphology from three-dimensional (3D) light microscopy is fundamental to neuroscience. Nevertheless, neuronal arbors intrinsically exhibit slender, tortuous geometries with high orientation variability, posing significant challenges for standard 3D convolutions whose static, axis-aligned receptive fields lack adaptability to such complex morphology. To address this, we propose the Dynamic Morph-Aware Convolution (DMAC) framework, which incorporates inherent geometric priors into convolution by jointly adapting both the shape and orientation of the kernel. This enables morphology-aware feature extraction tailored to arborized and variably oriented neuronal trajectories. Specifically, we first apply dynamic tubular convolutions to bridge the structural mismatch between isotropic convolution kernels and the slender morphology of neurons. To sufficiently accommodate the 3D orientation variability of neuronal branches, we further introduce a rotation mechanism that dynamically reorients the tubular kernel via two learnable angles (elevation and azimuth), enabling precise alignment with local neuronal directions. We validate our method through extensive experiments on four mesoscaled neuronal imaging datasets, including two from the BigNeuron project (Drosophila and Mouse) and two additional benchmarks (NeuroFly and CWMBS). Our approach consistently outperforms state-of-the-art methods, achieving average improvements of 5.4% in Entire Structure Average (ESA), 6.9% in Different Structure Average (DSA), and 7.5% in Percentage of Different Structure (PDS). These results demonstrate the effectiveness of our proposed DMAC in capturing complex morphological variations and enhancing structural fidelity across diverse mesoscaled neuronal morphologies.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":"4"},"PeriodicalIF":8.3,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12876509/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146087421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable artificial intelligence in air traffic control: effects of expertise on workload, acceptance, and usage intentions.","authors":"Giulia Cartocci, Alexandre Veyrié, Nicola Cavagnetto, Christophe Hurter, Augustin Degas, Ana Ferreira, Mobyen Uddin Ahmed, Shahina Begum, Shaibal Barua, Bianca Maria Serena Inguscio, Vincenzo Ronca, Gianluca Borghini, Gianluca Di Flumeri, Fabio Babiloni, Pietro Aricò","doi":"10.1186/s40708-025-00287-6","DOIUrl":"10.1186/s40708-025-00287-6","url":null,"abstract":"<p><p>Explainability is crucial for establishing user trust in Artificial Intelligence (AI), particularly within safety-critical domains such as Air Traffic Management (ATM) and Air Traffic Control (ATC). This study empirically investigates the effects of Explainable AI (XAI), specifically HeatMap-based visual explanations, on cognitive workload, user acceptance, and intention to use AI-driven decision-support systems among Air Traffic Control Officers (ATCOs). Despite significant theoretical advancements in the broader XAI domain, empirical evidence addressing the specific impact of visual explanations on human-AI interactions in safety-critical environments like ATC remains limited. To address these critical gaps, an experimental comparison was conducted between explainable (HeatMap) and non-explainable (BlackBox) AI conditions, involving two user groups: expert and student ATCOs. Both objective neurophysiological measures (Electroencephalography) and subjective questionnaires were employed to capture comprehensive user responses. Key findings revealed that the presence of visual explanations significantly reduced cognitive workload and enhanced users' willingness to adopt the AI system, regardless of participants' level of expertise. However, explicit perceptions of AI's impact on work performance were predominantly influenced by expertise, with less experienced controllers reporting a greater perceived impact than their expert counterparts. By combining objective neurometrics with subjective user assessments, this research advances methodological rigor in evaluating human-AI interactions and highlights the importance of tailored, user-centric explanations. These findings directly contribute to practical guidelines for designing cognitively compatible and trustworthy AI tools in ATC, providing nuanced insights for targeted training and deployment strategies based on user expertise.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":""},"PeriodicalIF":8.3,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12963558/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146041676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond the lab: real-world benchmarking of wearable EEGs for passive brain-computer interfaces.","authors":"Ronca Vincenzo, Cecchetti Marianna, Capotorto Rossella, Di Flumeri Gianluca, Giorgi Andrea, Germano Daniele, Borghini Gianluca, Babiloni Fabio, Aricò Pietro","doi":"10.1186/s40708-025-00290-x","DOIUrl":"10.1186/s40708-025-00290-x","url":null,"abstract":"<p><strong>Purpose: </strong>Wearable EEG systems are increasingly used for brain-computer interface (BCI) applications beyond controlled laboratory environments. However, there is still limited evidence on their reliability in real-world cognitive monitoring, especially for deriving robust mental-state indicators. This study investigates the signal quality, computational stability, and neurometric consistency of two widely used consumer-grade EEG devices (Emotiv EPOC X and Muse S) compared to a validated research-grade system (Mindtooth Touch) during naturalistic tasks relevant to passive BCIs and brain-machine intelligence.</p><p><strong>Method: </strong>Twenty-four participants completed a multimodal protocol including video observation, multitasking under varying cognitive loads, and a simulated driving task. Each participant used all three EEG systems in a counterbalanced order to avoid any bias induced by the order. Signal quality was assessed through artefact analysis and Power Spectral Density (PSD) stability. Neurometrics, i.e., metrics related to specific mental and emotional states that can be extracted from EEG signal processing (workload, attention, vigilance, and approach-withdrawal) were extracted and compared across devices, conditions, and subjective reports of effort and comfort.</p><p><strong>Finding: </strong>The research grade system demonstrated higher signal stability, fewer artefacts, and more consistent neurometric responses to cognitive variations, with high significant correlation with subjective measures. Post-processing improved data continuity in consumer devices, but neurometrics remained less sensitive to task demands and less aligned with subjective ratings. Each device reflected different trade-offs between data quality, usability, and cost.</p><p><strong>Conclusion: </strong>Research-grade systems remain more reliable for passive BCI applications requiring high-resolution cognitive state monitoring. Nevertheless, consumer-grade headsets may still be appropriate for exploratory studies or non-critical applications. This work highlights key trade-offs between signal quality, usability, and application goals, contributing to the broader integration of wearable neurotechnologies into brain-machine intelligence frameworks.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":"3"},"PeriodicalIF":4.5,"publicationDate":"2025-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12779824/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145851115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The independent prognostic value of brain diffusion tensor imaging in comatose patients after cardiac arrest.","authors":"Xuejia Jia, Rui Shao, Yingying Li, Xiuqin Jia, Ziren Tang, Qi Yang","doi":"10.1186/s40708-025-00284-9","DOIUrl":"10.1186/s40708-025-00284-9","url":null,"abstract":"<p><strong>Background/objective: </strong>Predicting neurological outcomes in comatose cardiac arrest survivors remains challenging. Diffusion tensor imaging (DTI) offers potential as an objective biomarker of white matter injury, but its prognostic value needs further validation. We aimed to investigate the predictive value of DTI-derived metrics for six-month neurological outcomes in comatose cardiac arrest patients.</p><p><strong>Methods: </strong>This prospective study enrolled 28 comatose cardiac arrest patients (mean age 54.36 ± 3.01 years; 71% male) and 28 age-/sex-matched healthy controls (HCs). All participants underwent 3T brain MRI (median 4 days post-arrest). DTI parameters (fractional anisotropy [FA], mean diffusivity [MD], axial diffusivity [AD], radial diffusivity [RD]) were analyzed using Tract-based spatial statistics (TBSS) and ROI approaches based on white matter atlas. Neurological outcome was assessed at six months using the modified Rankin Scale (good outcome: mRS 0-2; poor outcome: mRS 3-5). Statistical analyses included voxel-wise comparisons and ROC curve analysis for predictive performance.</p><p><strong>Results: </strong>Compared to HCs, patients showed widespread reductions in FA, MD, AD, and RD (TFCE-corrected p < 0.05). Patients with poor outcomes (n = 18) exhibited significantly lower DTI metrics than those with good outcomes (n = 10) across most white matter tracts. The combination of whole-brain FA and RD demonstrated exceptional prognostic accuracy for good outcome (AUC = 0.984; 95% CI 0.925-1.000; sensitivity 92%, specificity 97.7%), significantly outperforming clinical variables and individual DTI parameters. ROI analysis identified specific tracts (e.g., right cingulum hippocampus, right uncinate fasciculus) with high predictive values. Ventricular fibrillation as initial rhythm was more frequent in the group with good outcomes.</p><p><strong>Conclusions: </strong>DTI metrics, particularly the combination of FA and RD, provided outstanding early prediction of good six-month neurological outcomes after cardiac arrest, surpassing traditional biomarkers. These findings supported integrating DTI into multimodal prognostic models to guide clinical decisions and prevent premature withdrawal of life-sustaining therapy.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":"12 1","pages":"37"},"PeriodicalIF":4.5,"publicationDate":"2025-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12748314/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145851066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning with multitype functional connectivity uncovers whole-brain network disruption in primary angle-closure glaucoma.","authors":"Guangxiang Chen, Dekai Hu, Xin Huang, Zhijiang Wan","doi":"10.1186/s40708-025-00289-4","DOIUrl":"10.1186/s40708-025-00289-4","url":null,"abstract":"<p><p>Primary angle-closure glaucoma (PACG), an irreversible blinding disease characterized by retinal ganglion cell damage and optic nerve atrophy, exerts significant effects on brain functional networks. Using resting-state functional magnetic resonance imaging (rs-fMRI) data from 34 PACG patients and 34 matched healthy controls (HCs), we extracted four types of connectivity features-voxel-wise static functional connectivity (FC), dynamic functional connectivity (dFC), effective connectivity (EC), and dynamic effective connectivity (dEC)-via the AAL90 (Automated Anatomical Labeling 90) atlas following preprocessing. Elastic net feature selection was applied independently to each connectivity type to retain the top 10% most discriminative features. We evaluated the classification performance of ten machine learning models using individual feature types as well as their combined features, with the FC-based logistic regression (LR) model achieving optimal diagnostic efficacy (accuracy = 0.92, AUC = 0.96). SHapley Additive exPlanations (SHAP) of the model identified 20 critical connections, revealing abnormal patterns at both the region of interest (ROI)-level and network-level within brain networks such as the visual network (VSN), dorsal attention network (DAN), and sensorimotor network (SMN). Statistical group comparisons validated reduced connectivity (e.g., VSN-SMN, VSN-DAN) and enhanced DAN-thalamus connectivity in patients, while voxel-wise analyses of key regions confirmed diminished connectivity to visual areas. The results provide insights into how machine learning can be effectively employed to detect PACG-specific brain network disruptions and highlight potential neuroimaging biomarkers.</p>","PeriodicalId":37465,"journal":{"name":"Brain Informatics","volume":" ","pages":"2"},"PeriodicalIF":4.5,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12779822/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}