{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T07:29:23Z","timestamp":1781508563277,"version":"3.54.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Early diagnosis of neurodegenerative diseases remains a formidable challenge in modern neuroimaging, due to subtle and heterogeneous brain deterioration patterns in early disease stages. Integrating artificial intelligence and radiomic analysis has emerged as a powerful paradigm for non-invasive biomarker discovery and precision diagnostics. In alignment with trends emphasizing cross-modality analysis, interpretability, and demographic generalization, this study introduces a novel approach leveraging object detection and disentangled representation learning to improve early detection sensitivity and reliability. Traditional radiomics frameworks often suffer from limited generalizability, rigid feature engineering, and confounding variability from age, imaging protocol, or anatomical variations, undermining clinical robustness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Our method addresses these limitations through a three-pronged strategy. We construct a hybrid representation framework separating age-related morphometric changes from disease-specific alterations. We introduce NeuroFact-Net, a dual-path variational encoder-decoder architecture supervised along anatomical and diagnostic axes, enhancing interpretability and facilitating trajectory analysis. Wedevise a Causal Disease-Aware Alignment (CDAA) strategy imposing population-level invariance and disease-specific consistency using contrastive learning, adversarial subgroup confusion, and maximum mean discrepancy constraints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and discussion<\/jats:title>\n                    <jats:p>Experiments across multi-site MRl and PET datasets demonstrate superior diagnostic accuracy, domain transferability, and latent biomarker interpretability, validating its potential for clinical deployment in early-stage screening. This work contributes a scalable, interpretable, and causally grounded computational framework aligned with Al-enhanced neuroimaging advancements.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2025.1645118","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:40:19Z","timestamp":1769496019000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging object detection for early diagnosis of neurodegenerative diseases through radiomic analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Wenhong","family":"Zhi","sequence":"first","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjian","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaoran","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijian","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xuzhou Central Hospital Affiliated to Southeast University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00116","article-title":"\u201cTransfusion: Robust LIDAR-camera fusion for 3D object detection with transformers,\u201d","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Bai","year":"2022"},{"key":"B2","doi-asserted-by":"publisher","first-page":"42449","DOI":"10.1109\/ACCESS.2021.3066213","article-title":"Computational modeling of dementia prediction using deep neural network: analysis on oasis dataset","volume":"9","author":"Basheer","year":"2021","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/MeMeA60663.2024.10596885","article-title":"\u201cComparative analysis of cross-validation methods on PPMI dataset,\u201d","volume-title":"2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","author":"Calomino","year":"2024"},{"key":"B4","unstructured":"\u201cEnd-to-end object detection with transformers,\u201d\n          \n          \n            \n              Carion\n              N.\n            \n            \n              Massa\n              F.\n            \n            \n              Synnaeve\n              G.\n            \n            \n              Usunier\n              N.\n            \n            \n              Kirillov\n              A.\n            \n            \n              Zagoruyko\n              S.\n            \n          \n          European Conference on Computer Vision\n          \n          2020"},{"key":"B5","article-title":"\u201cDiffusionDet: diffusion model for object detection,\u201d","volume-title":"IEEE International Conference on Computer Vision","author":"Chen","year":"2022"},{"key":"B6","unstructured":"\u201cOpen-vocabulary object detection via vision and language knowledge distillation,\u201d\n          \n          \n            \n              Gu\n              X.\n            \n            \n              Lin\n              T.-Y.\n            \n            \n              Kuo\n              W.\n            \n            \n              Cui\n              Y.\n            \n          \n          International Conference on Learning Representations\n          \n          2021"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.00577","article-title":"\u201cTowards open world object detection,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Joseph","year":"2021"},{"key":"B8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICSES52305.2021.9633834","article-title":"\u201cEvolution of YOLO-v5 algorithm for object detection: automated detection of library books and performace validation of dataset,\u201d","volume-title":"2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES)","author":"Karthi","year":"2021"},{"key":"B9","unstructured":"\u201cGeneralized focal loss: Learning qualified and distributed bounding boxes for dense object detection,\u201d\n          \n          \n            \n              Li\n              X.\n            \n            \n              Wang\n              W.\n            \n            \n              Wu\n              L.\n            \n            \n              Chen\n              S.\n            \n            \n              Hu\n              X.\n            \n            \n              Li\n              J.\n            \n          \n          Neural Information Processing Systems\n          \n          2020"},{"key":"B10","unstructured":"\u201cBEVDepth: Acquisition of reliable depth for multi-view 3D object detection,\u201d\n          \n          \n            \n              Li\n              Y.\n            \n            \n              Ge\n              Z.\n            \n            \n              Yu\n              G.\n            \n            \n              Yang\n              J.\n            \n            \n              Wang\n              Z.\n            \n            \n              Shi\n              Y.\n            \n          \n          AAAI Conference on Artificial Intelligence"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01540","article-title":"\u201cLarge selective kernel network for remote sensing object detection,\u201d","volume-title":"IEEE International Conference on Computer Vision","author":"Li","year":"2023"},{"key":"B12","unstructured":"\u201cExploring plain vision transformer backbones for object detection,\u201d\n          \n          \n            \n              Li\n              Y.\n            \n            \n              Mao\n              H.\n            \n            \n              Girshick\n              R. B.\n            \n            \n              He\n              K.\n            \n          \n          European Conference on Computer Vision"},{"key":"B13","unstructured":"\u201cTarget-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection,\u201d\n          \n          \n            \n              Liu\n              J.\n            \n            \n              Fan\n              X.\n            \n            \n              Huang\n              Z.\n            \n            \n              Wu\n              G.\n            \n            \n              Liu\n              R.\n            \n            \n              Zhong\n              W.\n            \n          \n          New Orleans, LA\n          IEEE\n          2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)\n          \n          2022"},{"key":"B14","article-title":"\u201cGrounding DINO: marrying DINO with grounded pre-training for open-set object detection,\u201d","author":"Liu","year":"2023","journal-title":"European Conference on Computer Vision"},{"key":"B15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.53388\/TMR20221113001","article-title":"Research trends of machine learning in traditional medicine: a big-data based ten-year bibliometric analysis","volume":"8","author":"Liu","year":"2023","journal-title":"Traditional Med. Res"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1142796","DOI":"10.3389\/fendo.2023.1142796","article-title":"A practical dynamic nomogram model for predicting bone metastasis in patients with thyroid cancer","volume":"14","author":"Liu","year":"2023","journal-title":"Front. Endocrinol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"922510","DOI":"10.3389\/fpubh.2022.922510","article-title":"Using machine learning methods to predict bone metastases in breast infiltrating ductal carcinoma patients","volume":"10","author":"Liu","year":"2022","journal-title":"Fron. Public Health"},{"key":"B18","unstructured":"\u201cPETR: Position embedding transformation for multi-view 3D object detection,\u201d\n          \n          \n            \n              Liu\n              Y.\n            \n            \n              Wang\n              T.\n            \n            \n              Zhang\n              X.\n            \n            \n              Sun\n              J.\n            \n          \n          European Conference on Computer Vision\n          \n          2022"},{"key":"B19","article-title":"\u201cUnbiased teacher for semi-supervised object detection,\u201d","author":"Liu","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.3390\/electronics12102323","article-title":"DC-YOLOv8: Small-size object detection algorithm based on camera sensor","volume":"12","author":"Lou","year":"2023","journal-title":"Electronics"},{"key":"B21","article-title":"\u201cDETRs beat YOLOs on real-time object detection,\u201d","volume-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lv","year":"2023"},{"key":"B22","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/ICCMC51019.2021.9418274","article-title":"\u201cFaster r-CNN and YOLO based vehicle detection: a survey,\u201d","volume-title":"2021 5th international conference on computing methodologies and communication (ICCMC)","author":"Maity","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1503806","DOI":"10.3389\/fnagi.2024.1503806","article-title":"Transcriptional patterns of brain structural abnormalities in csvd-related cognitive impairment","volume":"16","author":"Mao","year":"2024","journal-title":"Front. Aging Neurosci"},{"key":"B24","unstructured":"\u201cScaling open-vocabulary object detection,\u201d\n          \n          \n            \n              Minderer\n              M.\n            \n            \n              Gritsenko\n              A.\n            \n            \n              Houlsby\n              N.\n            \n          \n          Neural Information Processing Systems\n          \n          2023"},{"key":"B25","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s00530-021-00797-3","article-title":"Transfer learning using freeze features for alzheimer neurological disorder detection using adni dataset","volume":"28","author":"Naz","year":"2022","journal-title":"Multimedia Syst"},{"key":"B26","doi-asserted-by":"publisher","first-page":"107404","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-net: going deeper with nested U-structure for salient object detection","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognition"},{"key":"B27","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1186\/s12911-021-01556-0","article-title":"Developing automated methods for disease subtyping in uk biobank: an exemplar study on stroke","volume":"21","author":"Rannikm\u00e4e","year":"2021","journal-title":"BMC Med. Inform. Decisi. Making"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.4251\/wjgo.v16.i4.1256","article-title":"Computed tomography-based radiomics diagnostic approach for differential diagnosis between early-and late-stage pancreatic ductal adenocarcinoma","volume":"16","author":"Ren","year":"2024","journal-title":"World J. Gastrointest. Oncol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s11596-022-2535-2","article-title":"Application of unenhanced computed tomography texture analysis to differentiate pancreatic adenosquamous carcinoma from pancreatic ductal adenocarcinoma","volume":"42","author":"Ren","year":"2022","journal-title":"Curr. Med. Sci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1007\/s00261-020-02506-6","article-title":"Diagnostic accuracy of unenhanced ct texture analysis to differentiate mass-forming pancreatitis from pancreatic ductal adenocarcinoma","volume":"45","author":"Ren","year":"2020","journal-title":"Abdom. Radiol"},{"key":"B31","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.00727","article-title":"\u201cFsce: Few-shot object detection via contrastive proposal encoding,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sun","year":"2021"},{"key":"B32","doi-asserted-by":"publisher","first-page":"20939","DOI":"10.1007\/s00521-023-08809-1","article-title":"An improved fire detection approach based on YOLO-v8 for smart cities","volume":"35","author":"Talaat","year":"2023","journal-title":"Neural Comp. Appl"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-021-01691-8","article-title":"Comparison of retinanet, ssd, and YOLO v3 for real-time pill identification","volume":"21","author":"Tan","year":"2021","journal-title":"BMC Med. Inform. Decisi. Making"},{"key":"B34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/DELCON54057.2022.9753272","article-title":"\u201cDetecting covid-19 opacity in x-ray images using YOLO and retinanet ensemble,\u201d","volume-title":"2022 IEEE Delhi Section Conference (DELCON)","author":"Tiwari","year":"2022"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/ADICS58448.2024.10533619","article-title":"\u201cYOLOv8: A novel object detection algorithm with enhanced performance and robustness,\u201d","volume-title":"2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)","author":"Varghese","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","first-page":"115","DOI":"10.18127\/j00338486-202109-11","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","volume":"85","author":"Virasova","year":"2021","journal-title":"Radioengineering"},{"key":"B37","unstructured":"\u201cYOLOv10: Real-time end-to-end object detection,\u201d\n          \n          \n            \n              Wang\n              A.\n            \n            \n              Chen\n              H.\n            \n            \n              Liu\n              L.\n            \n            \n              Chen\n              K.\n            \n            \n              Lin\n              Z.\n            \n            \n              Han\n              J.\n            \n          \n          Neural Information Processing Systems\n          \n          2024"},{"key":"B38","unstructured":"\u201cUAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios,\u201d\n          \n          \n            \n              Wang\n              G.\n            \n            \n              Chen\n              Y.\n            \n            \n              An\n              P.\n            \n            \n              Hong\n              H.\n            \n            \n              Hu\n              J.\n            \n            \n              Huang\n              T.\n            \n          \n          37631727\n          Italian National Conference on Sensors\n          \n          2023"},{"key":"B39","unstructured":"\u201cFCOS3D: fully convolutional one-stage monocular 3D object detection,\u201d\n          \n          \n            \n              Wang\n              T.\n            \n            \n              Zhu\n              X.\n            \n            \n              Pang\n              J.\n            \n            \n              Lin\n              D.\n            \n          \n          Montreal, BC\n          IEEE\n          2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)\n          \n          2021"},{"key":"B40","article-title":"\u201cDETR3D: 3D object detection from multi-view images via 3D-to-2D queries,\u201d","author":"Wang","year":"2021","journal-title":"Conference on Robot Learning"},{"key":"B41","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00350","article-title":"\u201cOriented R-CNN for object detection,\u201d","volume-title":"IEEE International Conference on Computer Vision","author":"Xie","year":"2021"},{"key":"B42","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00305","article-title":"\u201cEnd-to-end semi-supervised object detection with soft teacher,\u201d","volume-title":"IEEE International Conference on Computer Vision","author":"Xu","year":"2021"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1504733","DOI":"10.3389\/fnagi.2025.1504733","article-title":"Individualized diagnosis of Parkinson's disease based on multivariate magnetic resonance imaging radiomics and clinical indexes","volume":"17","author":"Ye","year":"2025","journal-title":"Front. Aging Neurosci"},{"key":"B44","article-title":"\u201cCenter-based 3D object detection and tracking,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Yin","year":"2020"},{"key":"B45","first-page":"106","article-title":"\u201cOpen-vocabulary DETR with conditional matching,\u201d","volume-title":"European Conference on Computer Vision","author":"Zang","year":"2022"},{"key":"B46","article-title":"\u201cDINO: DETR with improved denoising anchor boxes for end-to-end object detection,\u201d","author":"Zhang","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1513930","DOI":"10.3389\/fnagi.2024.1513930","article-title":"Association between alzheimer's disease pathologic products and age and a pathologic product-based diagnostic model for alzheimer's disease","volume":"16","author":"Zhen","year":"2024","journal-title":"Front. Aging Neurosci"},{"key":"B48","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW54120.2021.00312","article-title":"\u201cTPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios,\u201d","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","author":"Zhu","year":"2021"},{"key":"B49","unstructured":"\u201cDeformable DETR: Deformable transformers for end-to-end object detection,\u201d\n          \n          \n            \n              Zhu\n              X.\n            \n            \n              Su\n              W.\n            \n            \n              Lu\n              L.\n            \n            \n              Li\n              B.\n            \n            \n              Wang\n              X.\n            \n            \n              Dai\n              J.\n            \n          \n          International Conference on Learning Representations\n          \n          2020"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1645118\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:40:31Z","timestamp":1769496031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1645118\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,27]]},"references-count":49,"alternative-id":["10.3389\/fnagi.2025.1645118"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1645118","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,27]]},"article-number":"1645118"}}