{"id":"https://openalex.org/W6999614739","doi":null,"title":"Dealing with Small Datasets in Artificial Intelligence: focus on Medical Imaging","display_name":"Dealing with Small Datasets in Artificial Intelligence: focus on Medical Imaging","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6999614739"},"language":"en","primary_location":{"id":"pmh:oai:flore.unifi.it:2158/1319711","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1319711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2158/1319711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058175158","display_name":"Stefano Piffer","orcid":"https://orcid.org/0000-0002-6474-2885","observed_orcids":["https://orcid.org/0000-0002-6474-2885"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stefano Piffer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5058175158"],"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":true,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.004600000102072954,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/small-medical-image-datasets","display_name":"small medical image datasets","score":0.781000018119812},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.5899999737739563},{"id":"https://openalex.org/keywords/data-sharing","display_name":"data sharing","score":0.7039999961853027},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.6209999918937683},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.7900000214576721},{"id":"https://openalex.org/keywords/unsupervised-hierarchical-clustering","display_name":"unsupervised hierarchical clustering","score":0.7630000114440918},{"id":"https://openalex.org/keywords/rare-diseases","display_name":"rare diseases","score":0.5849999785423279},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.7490000128746033},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8100000023841858},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.800000011920929},{"id":"https://openalex.org/keywords/radiomics","display_name":"radiomics","score":0.6460000276565552},{"id":"https://openalex.org/keywords/medical-image-segmentation","display_name":"medical image segmentation","score":0.4860000014305115},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.5550000071525574},{"id":"https://openalex.org/keywords/data-silos","display_name":"data silos","score":0.43700000643730164}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.804099977016449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652999877929688},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46140000224113464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4523000121116638},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4124999940395355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C10511746","wikidata":"https://www.wikidata.org/wiki/Q899388","display_name":"Data security","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:flore.unifi.it:2158/1319711","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1319711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"}],"best_oa_location":{"id":"pmh:oai:flore.unifi.it:2158/1319711","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2158/1319711","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.46810001134872437}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405580953","https://openalex.org/W4412209027","https://openalex.org/W4399163592","https://openalex.org/W3099081599","https://openalex.org/W3007935259","https://openalex.org/W4313312686","https://openalex.org/W6889782727","https://openalex.org/W4385877222","https://openalex.org/W4391553302","https://openalex.org/W3175382607"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"(AI)":[2],"will":[3],"likely":[4],"affect":[5],"healthcare":[6,61],"systems":[7,470],"significantly":[8],"and":[9,24,36,80,106,111,120,145,156,202,224,244,252,287,295,338,372,409,417,481,541,548,550,558],"it":[10,292,552],"could":[11],"play":[12],"a":[13,239,352,430,450],"key":[14],"role":[15],"in":[16,20,60,166,170,173,246,275,318,329,341,425,525,553],"clinical":[17,203,235,454,482],"decision":[18],"making":[19],"future.":[21],"Deep":[22],"learning":[23,31,43,340,382,469],"radiomics":[25],"methods":[26,406],"are":[27,89,139,163,205,377,489],"extremely":[28,475],"promising":[29],"machine":[30,42,468],"tools":[32,492],"to":[33,67,76,91,101,142,151,186,194,207,279,321,369,407,413,418,429,447,493,500,503,514,535,562],"analyze":[34],"complex":[35],"high-dimensional":[37],"medical":[38,97,102,179,226,479,545],"images.":[39],"But":[40],"unfortunately,":[41],"models":[44,390,458],"that":[45,380,533],"work":[46,309,521],"with":[47,358,495,506],"imaging":[48,153,180,480],"data":[49,129,154,162,191,228,259,284,327,362,371,436,462,546],"require":[50],"massive":[51],"amounts":[52],"of":[53,70,82,96,113,122,128,148,176,189,220,242,254,271,305,313,325,344,361,388,401,422,433,474,509,517,528,539,556],"data.":[54,249,434],"For":[55],"this":[56],"reason,":[57],"their":[58],"implementation":[59],"settings":[62],"remains":[63,104],"limited,":[64],"mostly":[65],"due":[66],"the":[68,78,83,99,107,118,126,146,174,218,269,272,276,282,302,306,314,319,323,342,359,386,396,472,490,510,515,518,526,529,537,554],"lack":[69,112],"very":[71],"large":[72,178,187],"datasets":[73,95,366,393],"on":[74,391,460,544],"which":[75,169,424],"test":[77],"generalizability":[79,119],"reliability":[81],"trained":[84,355],"models.":[85],"Although":[86],"many":[87],"institutes":[88],"collaborating":[90],"produce":[92,157],"publicly":[93],"available":[94],"images,":[98],"access":[100,185],"images":[103],"limited":[105,133],"small":[108,326,392,461],"sample":[109],"sizes":[110],"diverse":[114],"geographic":[115],"areas":[116],"hinder":[117],"accuracy":[121],"developed":[123,524],"solutions.":[124],"Moreover,":[125,351,435],"process":[127,219],"acquisition":[130,285],"is":[131,192,442,463,486],"severely":[132],"by":[134,268,394],"different":[135,283,439],"challenges.":[136],"These":[137],"obstacles":[138],"mainly":[140],"related":[141],"privacy":[143,243],"regulations":[144],"effort":[147],"domain":[149],"experts":[150],"assess":[152],"quality":[155],"high-quality":[158],"ground":[159],"truth.":[160],"Medical":[161],"often":[164],"stored":[165],"disparate":[167],"silos":[168],"turn":[171,551],"results":[172,376],"difficulty":[175],"managing":[177,223],"datasets.":[181],"Furthermore,":[182],"simply":[183],"achieving":[184,208],"quantities":[188],"image":[190,227],"insufficient":[193],"allay":[195],"these":[196],"shortcomings.":[197],"Adequate":[198],"curation,":[199],"analysis,":[200],"labeling,":[201,221],"application":[204,312],"critical":[206],"high-impact":[209],"clinically":[210,565],"meaningful":[211],"AI":[212,230],"algorithms.":[213],"This":[214,308,484,520],"Ph.D.":[215],"thesis":[216],"describes":[217],"curating,":[222],"sharing":[225],"for":[229,233,281],"algorithm":[231],"development":[232,555],"optimal":[234],"impact,":[236],"while":[237,367],"maintaining":[238],"high":[240,420],"degree":[241],"security":[245],"exchanging":[247],"sensitive":[248],"The":[250,265,289,375],"pros":[251],"cons":[253],"having":[255],"heterogeneous":[256],"or":[257],"homogeneous":[258],"have":[260,348],"been":[261,349,523],"taken":[262],"into":[263],"consideration.":[264],"first,":[266],"caused":[267],"diversity":[270],"populations":[273],"included":[274],"dataset,":[277],"leads":[278],"incompleteness":[280],"standards":[286],"practices.":[288],"second,":[290],"although":[291],"returns":[293],"complete":[294,451],"uniform":[296],"datasets,":[297],"does":[298],"not":[299],"fully":[300],"consider":[301],"natural":[303,431],"variability":[304],"population.":[307],"provides":[310],"an":[311,444,464],"various":[315],"approaches":[316],"proposed":[317],"literature":[320],"alleviate":[322],"problem":[324],"samples":[328],"AI.":[330],"Well-established":[331],"techniques":[332],"such":[333],"as":[334],"unsupervised":[335],"hierarchical":[336],"clustering":[337,432],"transfer":[339,381],"context":[343],"rare":[345],"diseases":[346],"stratification":[347],"analyzed.":[350],"U-net":[353],"was":[354],"from":[356],"scratch":[357],"help":[360],"augmentation":[363],"merging":[364],"public":[365,440],"trying":[368],"contain":[370],"label":[373],"heterogeneity.":[374],"promising,":[378],"showing":[379],"technique":[383,446],"can":[384],"enable":[385],"training":[387],"custom":[389],"exploiting":[395],"powerful":[397],"feature":[398],"extraction":[399],"modules":[400],"Convolutional":[402],"Neural":[403],"Networks.":[404],"Different":[405],"select":[408],"combine":[410],"features":[411],"allow":[412,471],"incorporate":[414],"more":[415],"information":[416],"reach":[419],"level":[421],"abstraction":[423],"our":[426],"case":[427],"led":[428],"augmentations":[437],"combing":[438],"dataset":[441],"also":[443],"effective":[445,457,559],"carry":[448],"out":[449],"training.":[452],"In":[453],"context,":[455],"build":[456],"based":[459],"urgent":[465],"task":[466],"since":[467],"identification":[473],"difficult":[476],"correlations":[477],"among":[478],"endpoint.":[483],"path":[485],"viable,":[487],"there":[488],"right":[491],"deal":[494],"it,":[496],"but":[497],"one":[498],"need":[499],"know":[501],"how":[502],"use":[504],"them":[505,513],"full":[507],"knowledge":[508],"facts,":[511],"adapting":[512],"needs":[516],"case.":[519],"has":[522],"framework":[527],"INFN-funded":[530],"AIM":[531],"projects,":[532],"aims":[534],"exploit":[536],"expertise":[538],"INFN":[540],"associated":[542],"researchers":[543],"processing":[547],"enhancement,":[549],"advanced":[557],"analysis":[560],"instruments":[561],"be":[563],"eventually":[564],"validated.":[566]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}