{"id":"https://openalex.org/W4415539325","doi":"https://doi.org/10.1145/3746027.3755187","title":"MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks","display_name":"MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539325","doi":"https://doi.org/10.1145/3746027.3755187"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5120132054","display_name":"Wenqi Zeng","orcid":"https://orcid.org/0009-0008-5535-4128"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqi Zeng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-5535-4128","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110574075","display_name":"Yuqi Sun","orcid":"https://orcid.org/0000-0002-7179-5045"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Sun","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7179-5045","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233215","display_name":"Chenxi Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Ma","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5577-5773","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048621299","display_name":"Weimin Tan","orcid":"https://orcid.org/0000-0001-7677-4772"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Tan","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7677-4772","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081115024","display_name":"Bo Yan","orcid":"https://orcid.org/0000-0003-0256-9682"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yan","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0256-9682","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120132054"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.9166,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81427251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3769","last_page":"3778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9843000173568726,"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"}},{"id":"https://openalex.org/T13953","display_name":"Digital Imaging in Medicine","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5199999809265137},{"id":"https://openalex.org/keywords/skin-lesion","display_name":"Skin lesion","score":0.3734000027179718},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.33469998836517334},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.3264000117778778},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.31119999289512634},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.30079999566078186},{"id":"https://openalex.org/keywords/clinical-practice","display_name":"Clinical Practice","score":0.28700000047683716}],"concepts":[{"id":"https://openalex.org/C16005928","wikidata":"https://www.wikidata.org/wiki/Q171171","display_name":"Dermatology","level":1,"score":0.5896999835968018},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.45879998803138733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4059999883174896},{"id":"https://openalex.org/C2988168687","wikidata":"https://www.wikidata.org/wiki/Q949302","display_name":"Skin lesion","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C3018082644","wikidata":"https://www.wikidata.org/wiki/Q5259911","display_name":"Skin type","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2779231881","wikidata":"https://www.wikidata.org/wiki/Q5977147","display_name":"Medical literature","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2983449737","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Clinical diagnosis","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5648685701","display_name":null,"funder_award_id":"24ZR1490400","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2963946669","https://openalex.org/W3164654615","https://openalex.org/W3165058054","https://openalex.org/W3175183715","https://openalex.org/W3203635737","https://openalex.org/W4290852327","https://openalex.org/W4295917908","https://openalex.org/W4311027007","https://openalex.org/W4386566421","https://openalex.org/W4387740436","https://openalex.org/W4389520259","https://openalex.org/W4393158476","https://openalex.org/W4399567248","https://openalex.org/W4400362569","https://openalex.org/W4402727764","https://openalex.org/W4404567871"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"have":[4],"shown":[5],"promise":[6],"as":[7],"clinical":[8,162],"assistants":[9],"across":[10,128],"various":[11],"medical":[12,144],"fields.":[13],"However,":[14],"specialized":[15,32],"dermatology":[16,37,51,92,163],"VLM":[17,105,145,164],"capable":[18],"of":[19,89,117,149,161],"delivering":[20],"professional":[21,71],"and":[22,61,63,98,109,124,143,151,167],"detailed":[23],"diagnostic":[24],"analysis":[25],"remains":[26],"underdeveloped,":[27],"primarily":[28],"due":[29],"to":[30,140,157],"less":[31],"text":[33],"descriptions":[34],"in":[35,138],"current":[36,90],"multimodal":[38,50],"datasets.":[39],"To":[40],"address":[41],"this":[42],"issue,":[43],"we":[44,75,100],"propose":[45],"MM-Skin,":[46,99],"the":[47,87,159],"first":[48],"large-scale":[49],"dataset":[52,168],"that":[53],"encompasses":[54],"3":[55],"imaging":[56],"modalities,":[57],"including":[58],"clinical,":[59],"dermoscopic,":[60],"pathological":[62],"nearly":[64],"10k":[65],"high-quality":[66],"image-text":[67],"pairs":[68],"collected":[69],"from":[70],"textbooks.":[72],"In":[73],"addition,":[74],"generate":[76],"over":[77],"27k":[78],"diverse,":[79],"instruction-following":[80],"vision":[81],"question":[82],"answering":[83],"(VQA)":[84],"samples":[85],"(9\u00d7":[86],"size":[88],"largest":[91],"VQA":[93],"dataset).":[94],"Leveraging":[95],"public":[96],"datasets":[97],"developed":[101],"SkinVL,":[102],"a":[103,154],"dermatology-specific":[104],"designed":[106],"for":[107,135],"precise":[108],"nuanced":[110],"skin":[111,136],"disease":[112],"interpretation.":[113],"Comprehensive":[114],"benchmark":[115],"evaluations":[116],"SkinVL":[118,152],"on":[119],"VQA,":[120],"supervised":[121],"fine-tuning":[122],"(SFT)":[123],"zero-shot":[125],"classification":[126],"tasks":[127],"8":[129],"datasets,":[130],"reveal":[131],"its":[132],"exceptional":[133],"performance":[134],"diseases":[137],"comparison":[139],"both":[141],"general":[142],"models.":[146],"The":[147],"introduction":[148],"MM-Skin":[150],"offers":[153],"meaningful":[155],"contribution":[156],"advancing":[158],"development":[160],"assistants.":[165],"Code":[166],"are":[169],"available":[170],"at":[171],"https://github.com/ZwQ803/MM-Skin.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}