{"id":"https://openalex.org/W7133339180","doi":"https://doi.org/10.48550/arxiv.2603.00060","title":"Learning Under Extreme Data Scarcity: Subject-Level Evaluation of Lightweight CNNs for fMRI-Based Prodromal Parkinsons Detection","display_name":"Learning Under Extreme Data Scarcity: Subject-Level Evaluation of Lightweight CNNs for fMRI-Based Prodromal Parkinsons Detection","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7133339180","doi":"https://doi.org/10.48550/arxiv.2603.00060"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127994097","display_name":"Naimur Rahman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rahman, Naimur","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5127994097"],"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/T10919","display_name":"Neurological disorders and treatments","score":0.27730000019073486,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"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/T10919","display_name":"Neurological disorders and treatments","score":0.27730000019073486,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.1670999974012375,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.1607999950647354,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6141999959945679},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5792999863624573},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.4738999903202057},{"id":"https://openalex.org/keywords/neuroimaging","display_name":"Neuroimaging","score":0.45249998569488525},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42260000109672546},{"id":"https://openalex.org/keywords/extreme-learning-machine","display_name":"Extreme learning machine","score":0.38989999890327454}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.718999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063999772071838},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5454000234603882},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.4738999903202057},{"id":"https://openalex.org/C58693492","wikidata":"https://www.wikidata.org/wiki/Q551875","display_name":"Neuroimaging","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.38989999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00060","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1,59,63,234],"is":[2,30,131,205],"often":[3],"applied":[4],"in":[5,112,184],"settings":[6],"where":[7,34],"data":[8,66,70,94,238],"are":[9,37,87,149],"limited,":[10],"correlated,":[11],"and":[12,39,79,89,115,123,141,158,190,214,228],"difficult":[13],"to":[14,110,119,207],"obtain,":[15],"yet":[16],"evaluation":[17,188],"practices":[18],"do":[19],"not":[20,216],"always":[21],"reflect":[22],"these":[23],"constraints.":[24],"Neuroimaging":[25],"for":[26,231],"prodromal":[27,50,76],"Parkinsons":[28,51,77],"disease":[29],"one":[31],"such":[32],"case,":[33],"subject":[35,109],"numbers":[36],"small":[38],"individual":[40],"scans":[41],"produce":[42],"many":[43],"highly":[44],"related":[45],"samples.":[46],"This":[47],"work":[48],"examines":[49],"detection":[52],"from":[53,71,106],"resting-state":[54],"fMRI":[55,69],"as":[56],"a":[57,127,194,208,224],"machine":[58],"problem":[60],"centered":[61],"on":[62,197],"under":[64,91,236],"extreme":[65,185],"scarcity.":[67,239],"Using":[68],"40":[72,212],"subjects,":[73],"including":[74,151],"20":[75,80],"cases":[78],"healthy":[81],"controls,":[82],"ImageNet-pretrained":[83],"convolutional":[84],"neural":[85],"networks":[86],"fine-tuned":[88],"evaluated":[90],"two":[92],"different":[93,146],"partitioning":[95],"strategies.":[96],"Results":[97],"show":[98],"that":[99,183],"commonly":[100],"used":[101],"image-level":[102],"splits":[103],"allow":[104],"slices":[105],"the":[107,159,168,203],"same":[108],"appear":[111],"both":[113],"training":[114],"test":[116,137],"sets,":[117],"leading":[118],"severe":[120,237],"information":[121],"leakage":[122],"near-perfect":[124],"accuracy.":[125],"When":[126],"strict":[128],"subject-level":[129,164],"split":[130],"enforced,":[132],"performance":[133,198],"drops":[134],"substantially,":[135],"yielding":[136],"accuracies":[138],"between":[139],"60":[140],"81":[142],"percent.":[143],"Models":[144],"with":[145],"capacity":[147,192],"profiles":[148],"compared,":[150],"VGG19,":[152],"Inception":[153,155],"V3,":[154],"ResNet":[156],"V2,":[157],"lightweight":[160],"MobileNet":[161,166],"V1.":[162],"Under":[163],"evaluation,":[165],"demonstrates":[167],"most":[169],"reliable":[170],"generalization,":[171],"outperforming":[172],"deeper":[173],"architectures":[174],"despite":[175],"having":[176],"significantly":[177],"fewer":[178],"parameters.":[179],"These":[180],"results":[181],"indicate":[182],"low-data":[186],"regimes,":[187],"strategy":[189],"model":[191],"have":[193],"greater":[195],"impact":[196],"than":[199],"architectural":[200],"depth.":[201],"Although":[202],"analysis":[204],"limited":[206],"single":[209],"cohort":[210],"of":[211],"subjects":[213],"does":[215],"include":[217],"external":[218],"validation":[219],"or":[220],"cross-validation,":[221],"it":[222],"provides":[223],"concrete":[225],"case":[226],"study":[227],"practical":[229],"recommendations":[230],"evaluating":[232],"deep":[233],"models":[235]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}