{"id":"https://openalex.org/W4415237794","doi":"https://doi.org/10.48550/arxiv.2508.11864","title":"Impact of Clinical Image Quality on Efficient Foundation Model Finetuning","display_name":"Impact of Clinical Image Quality on Efficient Foundation Model Finetuning","publication_year":2025,"publication_date":"2025-08-16","ids":{"openalex":"https://openalex.org/W4415237794","doi":"https://doi.org/10.48550/arxiv.2508.11864"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.11864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11864","pdf_url":"https://arxiv.org/pdf/2508.11864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.11864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101653641","display_name":"Yucheng Tang","orcid":"https://orcid.org/0000-0003-0110-2466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002599364","display_name":"Pawe\u0142 Rajwa","orcid":"https://orcid.org/0000-0003-4073-6584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajwa, Pawel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091804752","display_name":"Alexander Ng","orcid":"https://orcid.org/0000-0001-5441-2017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101401275","display_name":"Yipei Wang","orcid":"https://orcid.org/0000-0002-9589-7177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yipei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700428","display_name":"Yan Wen","orcid":"https://orcid.org/0000-0002-3962-5994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100493992","display_name":"Natasha Thorley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thorley, Natasha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073962086","display_name":"Aqua Asif","orcid":"https://orcid.org/0000-0003-3233-7428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asif, Aqua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109393541","display_name":"Clare Allen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Allen, Clare","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030165549","display_name":"Louise Dickinson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dickinson, Louise","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032180724","display_name":"Francesco Giganti","orcid":"https://orcid.org/0000-0001-5218-6431"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giganti, Francesco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113046248","display_name":"Shonit Punwani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Punwani, Shonit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033449704","display_name":"Daniel C. Alexander","orcid":"https://orcid.org/0000-0003-2439-350X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander, Daniel C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114228650","display_name":"Veeru Kasivisvanathan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kasivisvanathan, Veeru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hu, Yipeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9787999987602234,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9787999987602234,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.977400004863739,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5062999725341797},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49390000104904175},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4569000005722046},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.3815000057220459},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.3736000061035156},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5062999725341797},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4366999864578247},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.11864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11864","pdf_url":"https://arxiv.org/pdf/2508.11864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.11864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.11864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.11864","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11864","pdf_url":"https://arxiv.org/pdf/2508.11864","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1,225],"in":[2,33,92,133,144,222],"medical":[3],"imaging":[4],"have":[5],"shown":[6],"promising":[7],"label":[8,202],"efficiency,":[9],"achieving":[10],"high":[11],"performance":[12],"on":[13,50,63],"downstream":[14,134,166],"tasks":[15],"using":[16,40],"only":[17],"a":[18,42,77],"fraction":[19],"of":[20,36,59,71,80,87,119,140,157,207],"the":[21,34,57,64,69,72,85,93,117,145,155,196,208],"annotated":[22],"data":[23,189],"otherwise":[24],"required.":[25],"In":[26,113],"this":[27,31,201],"study,":[28],"we":[29,214],"evaluate":[30],"potential":[32],"context":[35],"prostate":[37,52,174],"multiparametric":[38],"MRI":[39,53],"ProFound,":[41],"recently":[43],"developed":[44],"domain-specific":[45],"vision":[46],"foundation":[47],"model":[48,111],"pretrained":[49],"large-scale":[51],"datasets.":[54],"We":[55,75],"investigate":[56],"impact":[58],"variable":[60],"image":[61,102,209],"quality":[62,103,197,210],"label-efficient":[65],"finetuning,":[66,223],"by":[67,82],"quantifying":[68],"generalisability":[70],"finetuned":[73,224],"models.":[74],"conduct":[76],"comprehensive":[78],"set":[79,147],"experiments":[81],"systematically":[83],"varying":[84],"ratios":[86],"high-":[88,120],"and":[89,95,105,126,136,160,173],"low-quality":[90,122],"images":[91,123,143,221],"finetuning":[94,125,146,159,184],"evaluation":[96],"sets.":[97],"Our":[98],"findings":[99],"indicate":[100],"that":[101],"distribution":[104,162],"its":[106],"finetune-and-test":[107],"mismatch":[108],"significantly":[109,186],"affect":[110],"performance.":[112],"particular:":[114],"a)":[115],"Varying":[116],"ratio":[118,198],"to":[121,130,191,228],"between":[124,164],"test":[127],"sets":[128],"leads":[129],"notable":[131],"differences":[132],"performance;":[135],"b)":[137],"The":[138],"presence":[139],"sufficient":[141,219],"high-quality":[142,220],"is":[148,199,204],"critical":[149],"for":[150],"maintaining":[151],"strong":[152],"performance,":[153],"whilst":[154],"importance":[156],"matched":[158],"testing":[161],"varies":[163],"different":[165],"tasks,":[167],"such":[168],"as":[169],"automated":[170],"radiology":[171],"reporting":[172],"cancer":[175],"detection.":[176],"Importantly,":[177],"experimental":[178],"results":[179],"also":[180],"show":[181,215],"that,":[182,217],"although":[183],"requires":[185],"less":[187],"labeled":[188],"compared":[190],"training":[192],"from":[193],"scratch":[194],"when":[195],"consistent,":[200],"efficiency":[203],"not":[205],"independent":[206],"distribution.":[211],"For":[212],"example,":[213],"cases":[216],"without":[218,231],"may":[226],"fail":[227],"outperform":[229],"those":[230],"pretraining.":[232]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-16T00:00:00"}