[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86036-en":3,"doc-seo-86036-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86036,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","RED-Sphere Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization","Medical image classifiers trained on a single source population often fail when deployed to patients with different appearance, acquisition styles, and disease prevalence. Many existing fairness and robustness approaches need group supervision or treat appearance variation as generic nuisance, which overlooks population-correlated low-level cues intertwined with lesion evidence. RED-Sphere studies a strict source-only cross-population setting and proposes a plug-and-play robustness framework that estimates shortcut-sensitive nuisance responses, attenuates them via residual soft gating, and preserves lesion structure for improved external semantic alignment.","RED-Sphere: Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization  \n1 Newcastle University Newcastle upon Tyne, UK  \n2 King Abdullah University of Science and Technology (KAUST) Thuwal, Saudi Arabia  \n3 Durham University Durham, UK  \n12 Jul  \narXiv :2607 . 10777v1 [ cs .CV]  \nAbstract  \nMedical image classifiers are often trained within one source population, yet clinical deployment requires robustness to patients whose appearance, acquisition style, and disease prevalence differ from the source cohort. Existing fairness and robustness methods often require group supervision or treat appearance variation as an undifferentiated nuisance, which is insufficient when population-correlated low-level cues and lesion evidence share edge and texture structure. We study a strict source only cross population setting, where external populations are unseen during optimization, validation, scheduling, hyperparameter selection, and model selection. We propose RED-Sphere, a plug-andplay robustness framework for image classification under unseen population shifts. This estimates shortcut-sensitive nuisance responses with an edge and feature energy prior, attenuates dominant responses through residual soft gating, regularizes masked nuisance views with counterfactual inspired consistency and separation losses, and predicts labels with normalized spherical prototypes. The framework promotes angular semantic evidence over source correlated activation magnitude while preserving lesion related structure. Although demonstrated on 2D Scanning Laser Ophthalmoscopy (SLO) fundus classification for Age-Related Macular Degeneration (AMD) and Diabetic Retinopathy (DR), RED-Sphere is not tied to retinal anatomy because the same principle can be adapted with modality specific nuisance priors to classification settings where appearance shortcuts and semantic evidence are entangled. Under a strict White-only HarvardFairVision protocol, RED-Sphere improves held out macro-F1 across all 20 task and backbone comparisons, with average gains of 1.28 and 2.98 F1 points on AMD and DR. Improvements in AUC and PR-AUC, together with visual diagnostics, ablations, and sensitivity analyses, further support stronger external semantic alignment and more stable angular disease geometry.  \n© 2026 . The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.  \n2 LINETAL.: RED-SPHERE  \nFigure 1: Source only cross population fundus disease classification. Training and modelselection use one source cohort while external populations remain unseen until testing.  \n1 Introduction  \nMedical image classifiers are increasingly expected to operate beyond the population from which their training data are collected. A model trained within one source cohort may encounter patients with different acquisition protocols, appearance statistics, disease prevalence, and clinical workflows. Such source to external population shift is especially consequential in screening, where strong aggregate performance can coexist with poor sensitivity to clinically important minority categories. In ophthalmic imaging, Harvard-FairVision exposes demographic performance gaps in eye disease screening [26] . Retinal images can also encode population information through pigmentation, luminance, color statistics, and vessel maps [2, 33] . A robust classifier should therefore avoid treating cohort correlated appearance as disease evidence.  \nExisting fairness and generalization methods address related forms of distribution shift, but source-only deployment remains a more restrictive and practically important setting, as external populations are unavailable during training, validation, and model selection. Demographic fairness objectives such as equality of opportunity [11], counterfactual fairness [19], group distributional robustness [34], and adversarial debiasing [47] rely on sensitive labels, multiple obs","cbCaiitth3cQjPkH","https://ap.wps.com/l/cbCaiitth3cQjPkH","pdf",18864334,4,1,21,"English","en",105,"# Abstract\n# Introduction\n## Problem: Source-to-external population shift\n## Limitations of existing fairness and robustness methods\n## Proposed approach: RED-Sphere framework","[{\"question\":\"What problem does RED-Sphere address in medical image domain generalization?\",\"answer\":\"It targets cross-population robustness when training, validation, scheduling, and model selection occur on a single source cohort, while external populations remain unseen until testing.\"},{\"question\":\"How does RED-Sphere reduce reliance on shortcut-sensitive nuisance cues?\",\"answer\":\"It estimates shortcut-sensitive nuisance responses using an edge and feature energy prior, then attenuates dominant nuisance responses through residual soft gating.\"},{\"question\":\"How is lesion-relevant evidence preserved despite debiasing?\",\"answer\":\"It regularizes masked nuisance views with counterfactual inspired consistency and separation losses and predicts using normalized spherical prototypes to promote angular semantic evidence while preserving lesion related structure.\"}]",1784207990,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"red-sphere-hyperspherical-residual-edge-debiasing-for-cross-population-fundus-disease-domain-generalization","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/red-sphere-hyperspherical-residual-edge-debiasing-for-cross-population-fundus-disease-domain-generalization/86036/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does RED-Sphere address in medical image domain generalization?","Question",{"text":75,"@type":76},"It targets cross-population robustness when training, validation, scheduling, and model selection occur on a single source cohort, while external populations remain unseen until testing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does RED-Sphere reduce reliance on shortcut-sensitive nuisance cues?",{"text":80,"@type":76},"It estimates shortcut-sensitive nuisance responses using an edge and feature energy prior, then attenuates dominant nuisance responses through residual soft gating.",{"name":82,"@type":73,"acceptedAnswer":83},"How is lesion-relevant evidence preserved despite debiasing?",{"text":84,"@type":76},"It regularizes masked nuisance views with counterfactual inspired consistency and separation losses and predicts using normalized spherical prototypes to promote angular semantic evidence while preserving lesion related structure.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]