{"id":"https://openalex.org/W7126113569","doi":"https://doi.org/10.1109/bibm66473.2025.11356963","title":"CellVLM: Hierarchical Text-Guided Vision Transformers for Cell Segmentation and Classification","display_name":"CellVLM: Hierarchical Text-Guided Vision Transformers for Cell Segmentation and Classification","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126113569","doi":"https://doi.org/10.1109/bibm66473.2025.11356963"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124181605","display_name":"Yazeed Alrubyli","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Yazeed Alrubyli","raw_affiliation_strings":["University of Bologna,Department of Computer Science and Engineering,Bologna,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Computer Science and Engineering,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124235731","display_name":"Alessandro Bevilacqua","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Bevilacqua","raw_affiliation_strings":["University of Bologna,Department of Computer Science and Engineering,Bologna,Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna,Department of Computer Science and Engineering,Bologna,Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124181605"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82488994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3432","last_page":"3435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.6965000033378601,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.6965000033378601,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.08760000020265579,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.062199998646974564,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7354999780654907},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6173999905586243},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.535099983215332},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4814999997615814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38449999690055847},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.37459999322891235},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3458000123500824}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7354999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6863999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6855999827384949},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5623999834060669},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.535099983215332},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4814999997615814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5606479048728943},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4585720896720886}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2592905743","https://openalex.org/W2592929672","https://openalex.org/W2760946358","https://openalex.org/W2948930564","https://openalex.org/W2955737766","https://openalex.org/W2956228567","https://openalex.org/W2999219213","https://openalex.org/W3089090082","https://openalex.org/W4365143687","https://openalex.org/W4392883923"],"related_works":[],"abstract_inverted_index":{"Cell":[0],"segmentation":[1],"and":[2,13,42,71,100],"classification":[3],"in":[4,17,98],"microscopy":[5],"images":[6],"remain":[7],"challenging":[8],"due":[9],"to":[10,53,82],"diverse":[11],"morphologies":[12],"limited":[14],"semantic":[15,55],"context":[16],"vision-only":[18],"models.":[19],"We":[20,62],"present":[21],"CellVLM,":[22],"a":[23,38],"text-guided":[24],"vision":[25],"transformer":[26,51],"that":[27,106],"augments":[28],"CelIViT":[29],"with":[30,68,93],"multimodal":[31],"capabilities":[32],"by":[33],"integrating":[34],"morphological":[35],"descriptions":[36],"through":[37],"biomedical":[39],"text":[40],"encoder":[41],"multi-scale":[43],"cross-attention.":[44],"Text":[45],"guidance":[46],"is":[47,120],"injected":[48],"at":[49,122],"several":[50],"levels":[52],"enhance":[54],"discrimination":[56],"among":[57],"visually":[58],"similar":[59],"cell":[60],"types.":[61],"evaluate":[63],"on":[64],"the":[65],"PanNuke":[66],"dataset":[67],"3-fold":[69],"crossvalidation":[70],"observe":[72],"consistent":[73],"improvements":[74],"over":[75],"CellViT":[76],"baselines:":[77],"multi-class":[78],"panoptic":[79],"quality":[80],"improves":[81],"0.517":[83],"(SAM<tex":[84],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{H}":[86],"\\boldsymbol{;}":[87],"\\mathbf{+":[88],"3.":[89],"7":[90],"\\%}$</tex>":[91],"relative),":[92],"small":[94],"but":[95],"positive":[96],"changes":[97],"Dice":[99],"detection":[101],"F1.":[102],"These":[103],"findings":[104],"demonstrate":[105],"lightweight":[107],"textual":[108],"priors":[109],"can":[110],"improve":[111],"cell-type":[112],"understanding":[113],"while":[114],"preserving":[115],"established":[116],"architectural":[117],"benefits.":[118],"Code":[119],"available":[121],"https://github.com/yazeedalrubyli/CellVLM.":[123]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}