{"id":"https://openalex.org/W7140805634","doi":"https://doi.org/10.48550/arxiv.2603.23794","title":"Sparse Autoencoders for Interpretable Medical Image Representation Learning","display_name":"Sparse Autoencoders for Interpretable Medical Image Representation Learning","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140805634","doi":"https://doi.org/10.48550/arxiv.2603.23794"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23794","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.23794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019675338","display_name":"Philipp Wesp","orcid":"https://orcid.org/0000-0001-7356-3371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wesp, Philipp","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081687968","display_name":"Robbie Holland","orcid":"https://orcid.org/0000-0001-8373-8390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holland, Robbie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130670295","display_name":"Vasiliki Sideri-Lampretsa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sideri-Lampretsa, Vasiliki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130663501","display_name":"Sergios Gatidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gatidis, Sergios","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.32910001277923584,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.32910001277923584,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.17569999396800995,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08619999885559082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6062999963760376},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.538100004196167},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4860000014305115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46950000524520874},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45419999957084656},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7157999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148000001907349},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.538100004196167},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4860000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42980000376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28060001134872437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23794","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":"doi:10.48550/arxiv.2603.23794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23794","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Vision":[0],"foundation":[1],"models":[2],"(FMs)":[3],"achieve":[4],"state-of-the-art":[5],"performance":[6,92],"in":[7,14,104,117,133],"medical":[8,149],"imaging.":[9],"However,":[10],"they":[11],"encode":[12],"information":[13],"abstract":[15,130],"latent":[16,131],"representations":[17,40,132],"that":[18,70,113],"clinicians":[19],"cannot":[20],"interrogate":[21],"or":[22],"verify.":[23],"The":[24],"goal":[25],"of":[26,90],"this":[27],"study":[28],"is":[29],"to":[30,83,88,110],"investigate":[31],"Sparse":[32],"Autoencoders":[33],"(SAEs)":[34],"for":[35],"replacing":[36],"opaque":[37],"FM":[38],"image":[39,62,105,136],"with":[41,78],"human-interpretable,":[42],"sparse":[43,72],"features.":[44],"We":[45,68],"train":[46],"SAEs":[47,141],"on":[48],"embeddings":[49,77],"from":[50,64],"BiomedParse":[51],"(biomedical)":[52],"and":[53,59,85,129],"DINOv3":[54],"(general-purpose)":[55],"using":[56,93,119],"909,873":[57],"CT":[58],"MRI":[60],"2D":[61],"slices":[63],"the":[65],"TotalSegmentator":[66],"dataset.":[67],"find":[69],"learned":[71],"features:":[73],"(a)":[74],"reconstruct":[75],"original":[76],"high":[79],"fidelity":[80,103],"(R2":[81],"up":[82,87],"0.941)":[84],"recover":[86],"87.8%":[89],"downstream":[91],"only":[94],"10":[95],"features":[96],"(99.4%":[97],"dimensionality":[98],"reduction),":[99],"(b)":[100],"preserve":[101],"semantic":[102],"retrieval":[106],"tasks,":[107],"(c)":[108],"correspond":[109],"specific":[111],"concepts":[112],"can":[114],"be":[115],"expressed":[116],"language":[118,121,128],"large":[120],"model":[122],"(LLM)-based":[123],"auto-interpretation.":[124],"(d)":[125],"bridge":[126],"clinical":[127],"zero-shot":[134],"language-driven":[135],"retrieval.":[137],"Our":[138],"work":[139],"indicates":[140],"are":[142],"a":[143],"promising":[144],"pathway":[145],"towards":[146],"interpretable,":[147],"concept-driven":[148],"vision":[150],"systems.":[151],"Code":[152],"repository:":[153],"https://github.com/pwesp/sail.":[154]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-27T00:00:00"}