{"id":"https://openalex.org/W7161805467","doi":"https://doi.org/10.1109/isbi61048.2026.11515464","title":"Otoscopy AI: Deeply Supervised Attention for Otoscopic Image Segmentation","display_name":"Otoscopy AI: Deeply Supervised Attention for Otoscopic Image Segmentation","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7161805467","doi":"https://doi.org/10.1109/isbi61048.2026.11515464"},"language":null,"primary_location":{"id":"doi:10.1109/isbi61048.2026.11515464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136577656","display_name":"Hoang Le","orcid":null},"institutions":[{"id":"https://openalex.org/I2801157765","display_name":"Association of American Universities","ror":"https://ror.org/00tapj019","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801157765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hoang Le","raw_affiliation_strings":["Taureau.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taureau.ai","institution_ids":["https://openalex.org/I2801157765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136594002","display_name":"Quang Do","orcid":null},"institutions":[{"id":"https://openalex.org/I2801157765","display_name":"Association of American Universities","ror":"https://ror.org/00tapj019","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801157765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quang Do","raw_affiliation_strings":["Taureau.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taureau.ai","institution_ids":["https://openalex.org/I2801157765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136601977","display_name":"Thang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I2801157765","display_name":"Association of American Universities","ror":"https://ror.org/00tapj019","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801157765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thang Nguyen","raw_affiliation_strings":["Taureau.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taureau.ai","institution_ids":["https://openalex.org/I2801157765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113671857","display_name":"Hang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I3019271933","display_name":"Nicolaus Copernicus University","ror":"https://ror.org/0102mm775","country_code":"PL","type":"education","lineage":["https://openalex.org/I3019271933"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Hang Nguyen","raw_affiliation_strings":["Torus.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Torus.ai","institution_ids":["https://openalex.org/I3019271933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5136577656"],"corresponding_institution_ids":["https://openalex.org/I2801157765"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93659381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10861","display_name":"Ear Surgery and Otitis Media","score":0.3490999937057495,"subfield":{"id":"https://openalex.org/subfields/2733","display_name":"Otorhinolaryngology"},"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/T10861","display_name":"Ear Surgery and Otitis Media","score":0.3490999937057495,"subfield":{"id":"https://openalex.org/subfields/2733","display_name":"Otorhinolaryngology"},"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/T10860","display_name":"Speech and Audio Processing","score":0.04600000008940697,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10984","display_name":"Sinusitis and nasal conditions","score":0.04100000113248825,"subfield":{"id":"https://openalex.org/subfields/2733","display_name":"Otorhinolaryngology"},"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/segmentation","display_name":"Segmentation","score":0.5166000127792358},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4007999897003174},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3230000138282776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32089999318122864},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5400999784469604},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4007999897003174},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi61048.2026.11515464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2804720282","https://openalex.org/W2896286144","https://openalex.org/W2982297722","https://openalex.org/W3011072089","https://openalex.org/W3014706714","https://openalex.org/W3196075503","https://openalex.org/W4310113652","https://openalex.org/W4319659980","https://openalex.org/W4378907344","https://openalex.org/W4403770406"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"segmentation":[1,75,96],"of":[2,12,26,76],"otoscopic":[3,78],"images":[4],"is":[5,90],"a":[6,10,38,47,52,130,135],"prevalent":[7],"challenge":[8],"and":[9,67,86,119,134],"focus":[11],"active":[13],"research.":[14],"Recent":[15],"works":[16],"in":[17,121],"the":[18,60,74,81,84,91],"field":[19],"adopt":[20],"convolutional":[21,53],"neural":[22],"networks":[23],"(CNNs)":[24],"because":[25],"their":[27],"performance":[28,111],"compared":[29],"to":[30,58,94],"traditional":[31],"methods.":[32,115],"In":[33],"this":[34],"paper,":[35],"we":[36],"introduce":[37],"novel":[39],"deeply":[40],"supervised":[41],"attention":[42,55],"(DSA)":[43],"approach":[44,72],"that":[45],"integrates":[46],"deep":[48],"supervision":[49],"mechanism":[50],"with":[51],"block":[54],"module":[56],"(CBAM)":[57],"enhance":[59],"model":[61],"using":[62],"high-level":[63],"features":[64],"from":[65],"small":[66],"uncertain":[68],"objects.":[69],"The":[70],"proposed":[71],"improves":[73],"11":[77],"features,":[79],"including":[80],"tympanic":[82],"membrane,":[83],"cerumen,":[85],"abnormalities.":[87],"Our":[88],"method":[89],"first":[92],"architecture":[93],"provide":[95],"for":[97],"such":[98],"abnormalities,":[99],"reaching":[100],"0.80":[101],"mAP":[102],"on":[103,129],"average,":[104],"demonstrating":[105],"<tex":[106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$10-20":[108],"\\%$</tex>":[109],"superior":[110],"over":[112],"existing":[113],"state-of-the-art":[114],"To":[116],"ensure":[117],"robustness":[118],"generalization":[120],"real":[122],"world":[123],"settings,":[124],"additional":[125],"evaluations":[126],"were":[127],"performed":[128],"clinical":[131],"test":[132],"dataset":[133],"published":[136],"benchmark.":[137]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2026-05-21T00:00:00"}