{"id":"https://openalex.org/W4415111767","doi":"https://doi.org/10.48550/arxiv.2506.12492","title":"Comparative Analysis of Deep Learning Strategies for Hypertensive Retinopathy Detection from Fundus Images: From Scratch and Pre-trained Models","display_name":"Comparative Analysis of Deep Learning Strategies for Hypertensive Retinopathy Detection from Fundus Images: From Scratch and Pre-trained Models","publication_year":2025,"publication_date":"2025-06-14","ids":{"openalex":"https://openalex.org/W4415111767","doi":"https://doi.org/10.48550/arxiv.2506.12492"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.12492","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12492","pdf_url":"https://arxiv.org/pdf/2506.12492","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/2506.12492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015101640","display_name":"Yanqiao Zhu","orcid":"https://orcid.org/0000-0003-2205-5304"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Yanqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5015101640"],"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T12599","display_name":"Retinal and Optic Conditions","score":0.9157999753952026,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"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/deep-learning","display_name":"Deep learning","score":0.6995000243186951},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5789999961853027},{"id":"https://openalex.org/keywords/hypertensive-retinopathy","display_name":"Hypertensive retinopathy","score":0.4936000108718872},{"id":"https://openalex.org/keywords/fundus","display_name":"Fundus (uterus)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.39809998869895935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/diabetic-retinopathy","display_name":"Diabetic retinopathy","score":0.3379000127315521},{"id":"https://openalex.org/keywords/retinopathy","display_name":"Retinopathy","score":0.3154999911785126}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741000175476074},{"id":"https://openalex.org/C2776004912","wikidata":"https://www.wikidata.org/wiki/Q425811","display_name":"Hypertensive retinopathy","level":4,"score":0.4936000108718872},{"id":"https://openalex.org/C2776391266","wikidata":"https://www.wikidata.org/wiki/Q9612","display_name":"Fundus (uterus)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2779829184","wikidata":"https://www.wikidata.org/wiki/Q631361","display_name":"Diabetic retinopathy","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C2778313320","wikidata":"https://www.wikidata.org/wiki/Q550455","display_name":"Retinopathy","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.31150001287460327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C2780623050","wikidata":"https://www.wikidata.org/wiki/Q837188","display_name":"Ophthalmoscopy","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.12492","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12492","pdf_url":"https://arxiv.org/pdf/2506.12492","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.2506.12492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.12492","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:2506.12492","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12492","pdf_url":"https://arxiv.org/pdf/2506.12492","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":{"This":[0,174],"paper":[1],"presents":[2],"a":[3,17,29,32,45,126,157],"comparative":[4],"analysis":[5],"of":[6,34,57,89,166],"deep":[7],"learning":[8],"strategies":[9],"for":[10,147,190],"detecting":[11],"hypertensive":[12],"retinopathy":[13],"from":[14,97],"fundus":[15],"images,":[16],"central":[18],"task":[19],"in":[20],"the":[21,55,82,87,98,105,134,144,164,180],"HRDC":[22],"challenge~\\cite{qian2025hrdc}.":[23],"We":[24,107],"investigate":[25],"three":[26],"distinct":[27],"approaches:":[28],"custom":[30],"CNN,":[31],"suite":[33],"pre-trained":[35],"transformer-based":[36],"models,":[37,92],"and":[38,78,187],"an":[39],"AutoML":[40],"solution.":[41],"Our":[42],"findings":[43],"reveal":[44],"stark,":[46],"architecture-dependent":[47],"response":[48],"to":[49,67,74,150],"data":[50,148,185],"augmentation.":[51],"Augmentation":[52],"significantly":[53],"boosts":[54],"performance":[56,88],"pure":[58],"Vision":[59],"Transformers":[60],"(ViTs),":[61],"which":[62],"we":[63,123],"hypothesize":[64],"is":[65,139],"due":[66],"their":[68],"weaker":[69],"inductive":[70],"biases,":[71],"forcing":[72],"them":[73],"learn":[75],"robust":[76],"spatial":[77],"structural":[79],"features.":[80],"Conversely,":[81],"same":[83],"augmentation":[84],"strategy":[85],"degrades":[86],"hybrid":[90],"ViT-CNN":[91],"whose":[93],"stronger,":[94],"pre-existing":[95],"biases":[96],"CNN":[99],"component":[100],"may":[101],"be":[102],"\"confused\"":[103],"by":[104,141],"transformations.":[106],"show":[108,160],"that":[109,125],"smaller":[110,172],"patch":[111],"sizes":[112],"(ViT-B/8)":[113],"excel":[114],"on":[115,133,170],"augmented":[116],"data,":[117],"enhancing":[118],"fine-grained":[119],"detail":[120],"capture.":[121],"Furthermore,":[122],"demonstrate":[124],"powerful":[127],"self-supervised":[128],"model":[129,159,183],"like":[130],"DINOv2":[131],"fails":[132],"original,":[135],"limited":[136],"dataset":[137,188],"but":[138],"\"rescued\"":[140],"augmentation,":[142,186],"highlighting":[143],"critical":[145,177],"need":[146],"diversity":[149],"unlock":[151],"its":[152],"potential.":[153],"Preliminary":[154],"tests":[155],"with":[156],"ViT-Large":[158],"poor":[161],"performance,":[162],"underscoring":[163],"risk":[165],"using":[167],"overly-capacitive":[168],"models":[169],"specialized,":[171],"datasets.":[173],"work":[175],"provides":[176],"insights":[178],"into":[179],"interplay":[181],"between":[182],"architecture,":[184],"size":[189],"medical":[191],"image":[192],"classification.":[193]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-13T00:00:00"}