[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-456219-105":59,"doc-detail-456219-en":134},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","radiomics-driven-classification-of-small-white-matter-hyperintensities-and-perivascular-spaces-on-t1-weighted-mri-poster-presentation","Radiomics-Driven Classification of Small White Matter Hyperintensities and Perivascular Spaces on T1-Weighted MRI - Poster Presentation","","Background: This study develops a radiomics-based classifier integrating features of shape, texture, and intensity uniformity from T1W-MRI to distinguish perivascular spaces (PVS) from small white matter hyperintensity (WMH) lesions on T1-MRI. Method: From ADNI-3, 1270 WMH and 2976 PVS lesions were extracted and segmented; lesions with voxel count >500 were excluded, then 1223 radiomic features were reduced to 282 using a high-correlation filter (0.8) and refined with LASSO. Results: Wavelet frequency features, elongation/sphericity, and GLRLM/GLDM homogeneity differed significantly (p\u003C0.0001). The RF model achieved 0.95 accuracy, 0.96 sensitivity, and 0.90 specificity on testing. Conclusion: Accurate differentiation is feasible even without T2-FLAIR, using specific T1-MRI radiomics features.",{"@graph":69,"@context":126},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/radiomics-driven-classification-of-small-white-matter-hyperintensities-and-perivascular-spaces-on-t1-weighted-mri-poster-presentation/456219/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/radiomics-driven-classification-of-small-white-matter-hyperintensities-and-perivascular-spaces-on-t1-weighted-mri-poster-presentation/456219.png","ImageObject",300,407,{"name":92,"@type":93},"Jasmine","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-07","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of this study?","Question",{"text":112,"@type":113},"To develop a radiomics-based classifier using T1W-MRI features to accurately differentiate perivascular spaces (PVS) from small white matter hyperintensity (WMH) lesions on T1-MRI.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were the training data and lesions prepared?",{"text":117,"@type":113},"The study extracted 1270 WMH and 2976 PVS lesions from the ADNI-3 dataset, segmented them with a validated workflow, and excluded lesions with voxel count beyond 500 to focus on more challenging cases.",{"name":119,"@type":110,"acceptedAnswer":120},"Which features were most important for distinguishing PVS and WMH?",{"text":121,"@type":113},"Wavelet first-order frequency decomposition features showed significant differences, along with two shape-related measures (elongation and sphericity) and two texture/homogeneity features from GLRLM and GLDM.",{"name":123,"@type":110,"acceptedAnswer":124},"How did the final classifier perform on the test set?",{"text":125,"@type":113},"The random forest (RF) classifier outperformed other models, achieving 0.95 accuracy, 0.96 sensitivity, and 0.90 specificity on the test dataset.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},456219,1791022732,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":14,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":147,"read_time":24},2336478487870,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","DOI: 10. 1002/alz70856_105126  \nBIOMARKERS  \nPOSTER PRESENTATION  \nNEUROIMAGING  \nRadiomics-Driven Classification of Small White Matter  \nHyperintensities and Perivascular Spaces on T1-Weighted MRI  \nMaryam Fotouhi1  Fardin Samadi Khoshe Mehr2  Bino Varghese3  Nasim Sheikh-Bahaei3  Jeiran Choupan 1  \n1 Laboratory of Neuroimaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA  \n2 Laboratory of Neuroimaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angles, CA, USA  \n3 Keck School of Medicine, University of Southern California, Los Angeles, CA, USA  \nCorrespondence  \nMaryam Fotouhi, Laboratory of Neuroimaging, USC Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.  \n[Email:](Email: fotouhi@usc.edu)[ fotouhi@usc.edu](Email: fotouhi@usc.edu)  \nAbstract  \nBackground: This study aims to develop a radiomics-based classifier that integrates features related to shape, texture and intensity uniformity from T1W-MRI scans to accurately differentiate between perivascular spaces (PVS) and small white matter hyperintensity (WMH) lesions on T1-MRI.  \nMethod: A cohort of 1270 WMH and 2976 PVS lesions was extracted from theADNI- 3 dataset and segmented using our previously validated workflow. We excluded PVSand WMH lesions with a voxel count beyond 500 to refine our model for the more challenging lesions. A total of 1223 radiomic characteristics were retrieved followed by feature selection approach, implementing a high-correlation filter with a threshold of 0.8, yielding 282 remaining features. Subsequently, the LASSO technique was used to ascertain the ten most significant features. We used an ordinary least squares regression model to evaluate the importance of the chosen characteristics. Lesions were split across 80% training and 20% testing datasets. The classifier’s optimum parameters were determined by 5-fold cross-validation, and the selected models were then assessed on the test dataset.  \nResult: The first six features belong to first-order frequency decompositions of the wavelet and showed significant differenceswithin PVSsandWMHs(p-value \u003C 0.0001), suggesting that WMH lesions are denser than PVS lesions. The two shape-related features, including elongation and sphericity, suggest significant differences in the growth pattern across each class (p-value \u003C 0.0001). The two selected features from GLRLMand GLDM indicate that PVS lesions have amore homogenous tissue structure compared to WMH lesions (p-value\u003C0.0001). The RF classifier outperformed other models, showed potency in the test dataset, achieving an accuracy of 0.95, sensitivity of 0. 96, and specificity of 0.90.  \nConclusion: Differentiation of PVS and WMH lesions on T1W images can be challenging, particularly in the absence of T2-FLAIR, due to their similar hypointense  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2025 The Alzheimer’s Association. Alzheimer’s & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer’s Association.  \nAlzheimer’s Dement. 2025;21(Suppl. 2):e105126.  \n[https://doi.org/10.1002/alz70856_105126](https://doi.org/10.1002/alz70856_105126)  \nwi[leyonlinelibrary.com/journal/alz](leyonlinelibrary.com/journal/alz)  \n1of2  \nBIOMARKERS  \nappearance. Our study aimed to bridge this gap, revealing that beyond the wellestablished shape markers like elongation and sphericity, the homogeneity of intensity and variations in tissue texture also emerge as critical features in distinguishing these lesions. These findings suggest that a training classifier with the specific radiomics features from T1-MRI could achieve high a","cbCaivxKKedEbpO6","https://ap.wps.com/l/cbCaivxKKedEbpO6","pdf",88419,"English","# Abstract\n## Background\n## Method\n## Result\n## Conclusion","[{\"question\":\"What is the main goal of this study?\",\"answer\":\"To develop a radiomics-based classifier using T1W-MRI features to accurately differentiate perivascular spaces (PVS) from small white matter hyperintensity (WMH) lesions on T1-MRI.\"},{\"question\":\"How were the training data and lesions prepared?\",\"answer\":\"The study extracted 1270 WMH and 2976 PVS lesions from the ADNI-3 dataset, segmented them with a validated workflow, and excluded lesions with voxel count beyond 500 to focus on more challenging cases.\"},{\"question\":\"Which features were most important for distinguishing PVS and WMH?\",\"answer\":\"Wavelet first-order frequency decomposition features showed significant differences, along with two shape-related measures (elongation and sphericity) and two texture/homogeneity features from GLRLM and GLDM.\"},{\"question\":\"How did the final classifier perform on the test set?\",\"answer\":\"The random forest (RF) classifier outperformed other models, achieving 0.95 accuracy, 0.96 sensitivity, and 0.90 specificity on the test dataset.\"}]","Radiomics-Driven Classification of Small White Matter Hyperintensities and Perivascular Spaces on T1-Weighted MRI - Poster Presentation | PDF",1790745363]