[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86009-en":3,"doc-seo-86009-105":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},86009,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","HyperBank: A Differentiable Bank of Classical Priors for Few-Shot Spheroid Microscopy Segmentation","Few-shot spheroid segmentation adapts to new cell lines, microscopes, and illumination using only a small annotated set, yet explainability remains limited in foundation-style segmenters with large opaque backbones. HyperBank addresses this by learning a compact, differentiable bank of classical operators—Frangi vesselness, Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. It is fitted on annotated support images and evaluated on held-out data across three independently acquired datasets, using operator-family ablations to reveal which cues drive the few-shot signal.","HYPERBANK: A DIFFERENTIABLE BANK OF CLASSICAL PRIORS FOR FEW-SHOT  \nSPHEROID MICROSCOPY SEGMENTATION  \nM. Pru˚ˇsek 1 ,2 A. Novoza´msk´y 1 ,∗ F. ˇSroubek 1 T. Volfova´ 3 ,4 V. Svobodova´ Pavlı´cˇkova´ 3 S. Rimpelova´ 3 ,∗∗  \n1The Czech Academy of Sciences, Institute of Information Theory and Automation, Prague, Czechia  \n2 Czech Technical University in Prague, Faculty of Nuclear Sciences and Physical Engineering, Prague, Czechia  \n3University of Chemistry and Technology Prague, Department of Biochemistry and Microbiology, Prague, Czechia  \n4 Charles University, Faculty of Science, BIOCEV, Vestec, Czechia  \narXiv :2607 . 10684v1 [ cs .CV] 12 Jul 2026  \nABSTRACT  \nFew-shot spheroid segmentation must adapt to new cell lines, microscopes, and illumination conditions from only a small set of annotated images. While foundation few-shot segmenters can be accurate, their large opaque backbones make it difficult to understand which visual cues drive success or failure. We study this question with HyperBank, a differentiable bank of classical image-processing operators combining Frangi vesselness, a Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. HyperBank is fitted on the annotated support images and evaluated on disjoint held-out images across three independently acquired spheroid datasets. We treat it not as a general replacement for foundation models, but as a compact, interpretable few-shot microscopy pipeline and an analytic-prior probe of which classical cues carry the few-shot signal. The results show that, adapted on the same few annotated support images, a compact bank of analytic priors is competitive with—and on smallcluster, contrast-driven data can outperform—much larger foundation models, while those models remain stronger on externally sourced, texture-dominated spheroids. Leave-onefamily-out ablations indicate that the useful few-shot signal is distributed across operator families and strengthened by support-set-tuned morphology.  \nIndex Terms— few-shot segmentation, microscopy, handcrafted features, robust statistics  \nThis work was supported by the Czech Science Foundation grant GA25-15933S and CTU student competition grant SGS24/141/OHK4/3T/14 .  \n* Corresponding author for the computer science part (novozam[sky@utia.cas.cz](sky@utia.cas.cz)). ** Corresponding author for the biology part (sil[vie.rimpelova@vscht.cz](vie.rimpelova@vscht.cz)).  \n© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Accepted for publication in the IEEE Xplore ICIP 2026 Workshop Proceedings, at the Computational Optical Microscopy Satellite Workshop of the 2026 IEEE International Conference on Image Processing (ICIP), Tampere, Finland.  \n1. INTRODUCTION  \nTumour spheroids are three-dimensional multicellular aggregates used as in vitro models of tumour growth. Although spheroids are 3D structures, they are usually monitored in 2D bright-field or phase-contrast images, which must be segmented before phenotypes such as area, eccentricity, growth, or necrotic core can be quantified [1, 2] . Since each plate may vary in cell line, microscope, illumination, contrast, or morphology, the practical setting is few-shot adaptation from a small annotated support set to the remaining images from the same acquisition regime. Foundation few-shot segmenters such as SegGPT [3] and DCAMA [4] can achieve strong accuracy but their large pretrained backbones make it difficult to interpret which visual cues drive a particular result. Classical methods such as Sauvola thresholding [5], Otsu thresholding [6], and pixel-classifier random forests [7] are more transparent but each","cbCaiezGL0JU0ukf","https://ap.wps.com/l/cbCaiezGL0JU0ukf","pdf",7118552,2,1,7,"English","en",105,"# Abstract\n# Introduction\n# Related Work\n# Method\n# Experiments\n# Results and Analysis\n# Conclusion","[{\"question\":\"What problem does HyperBank target in few-shot spheroid microscopy segmentation?\",\"answer\":\"HyperBank targets the need to segment tumor spheroids when adapting to new cell lines, microscopes, and illumination using only a small annotated support set, while keeping the contributing visual cues interpretable.\"},{\"question\":\"How is HyperBank constructed and trained?\",\"answer\":\"HyperBank is a differentiable bank of classical image-processing operators, combining Frangi vesselness, a Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. It is fitted on the annotated support images and evaluated on disjoint held-out images.\"},{\"question\":\"How does HyperBank compare with foundation few-shot segmenters?\",\"answer\":\"On adapted data derived from the same few annotated support images, HyperBank’s compact analytic-prior bank can be competitive and may outperform much larger foundation models on small-cluster, contrast-driven spheroids, while foundation models remain stronger on externally sourced, texture-dominated spheroids.\"}]",1784207754,18,{"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},"hyperbank-a-differentiable-bank-of-classical-priors-for-few-shot-spheroid-microscopy-segmentation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/hyperbank-a-differentiable-bank-of-classical-priors-for-few-shot-spheroid-microscopy-segmentation/86009/",4,{"url":51,"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","2026-07-26","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 HyperBank target in few-shot spheroid microscopy segmentation?","Question",{"text":75,"@type":76},"HyperBank targets the need to segment tumor spheroids when adapting to new cell lines, microscopes, and illumination using only a small annotated support set, while keeping the contributing visual cues interpretable.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is HyperBank constructed and trained?",{"text":80,"@type":76},"HyperBank is a differentiable bank of classical image-processing operators, combining Frangi vesselness, a Sauvola threshold pyramid, structure-tensor responses, gradient magnitude, and Laplacian-of-Gaussian filters. It is fitted on the annotated support images and evaluated on disjoint held-out images.",{"name":82,"@type":73,"acceptedAnswer":83},"How does HyperBank compare with foundation few-shot segmenters?",{"text":84,"@type":76},"On adapted data derived from the same few annotated support images, HyperBank’s compact analytic-prior bank can be competitive and may outperform much larger foundation models on small-cluster, contrast-driven spheroids, while foundation models remain stronger on externally sourced, texture-dominated spheroids.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"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":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]