{"id":"https://openalex.org/W7171981362","doi":"https://doi.org/10.1145/3774521.3774618","title":"DWT-Mamba: A Spatially-Aware State Space Model for Medical Image Classification","display_name":"DWT-Mamba: A Spatially-Aware State Space Model for Medical Image Classification","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171981362","doi":"https://doi.org/10.1145/3774521.3774618"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774618","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774618","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041713014","display_name":"Moumita Dholey","orcid":"https://orcid.org/0000-0001-7983-702X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Moumita Dholey","raw_affiliation_strings":["Advanced Technology Development Centre, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0001-7983-702X","affiliations":[{"raw_affiliation_string":"Advanced Technology Development Centre, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005402352","display_name":"Rosina Ahmed","orcid":"https://orcid.org/0000-0002-8760-3458"},"institutions":[{"id":"https://openalex.org/I4210089010","display_name":"Tata Medical Center","ror":"https://ror.org/006vzad83","country_code":"IN","type":"funder","lineage":["https://openalex.org/I4210089010"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rosina Ahmed","raw_affiliation_strings":["Tata Medical Center Kolkata, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-8760-3458","affiliations":[{"raw_affiliation_string":"Tata Medical Center Kolkata, Kolkata, India","institution_ids":["https://openalex.org/I4210089010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085420736","display_name":"Sanjoy Chatterjee","orcid":"https://orcid.org/0000-0001-7402-8645"},"institutions":[{"id":"https://openalex.org/I4210089010","display_name":"Tata Medical Center","ror":"https://ror.org/006vzad83","country_code":"IN","type":"funder","lineage":["https://openalex.org/I4210089010"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjoy Chatterjee","raw_affiliation_strings":["Tata Medical Center Kolkata, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0001-7402-8645","affiliations":[{"raw_affiliation_string":"Tata Medical Center Kolkata, Kolkata, India","institution_ids":["https://openalex.org/I4210089010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037492743","display_name":"Jayanta Mukhopadhyay","orcid":"https://orcid.org/0000-0002-2491-6860"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayanta Mukhopadhyay","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-2491-6860","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6488999724388123},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5127000212669373},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.460099995136261},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45339998602867126},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44839999079704285},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.43459999561309814},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4284000098705292},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.40779998898506165},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7190999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.39079999923706055},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C2780423554","wikidata":"https://www.wikidata.org/wiki/Q766198","display_name":"Haar wavelet","level":5,"score":0.36340001225471497},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.33719998598098755},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.33059999346733093},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3018999993801117},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.27869999408721924},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2784999907016754},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C187029792","wikidata":"https://www.wikidata.org/wiki/Q2179112","display_name":"Haar","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774618","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774618","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2964024268","https://openalex.org/W4213186648","https://openalex.org/W4234971943","https://openalex.org/W4317436377","https://openalex.org/W4324144441","https://openalex.org/W4403365605","https://openalex.org/W4404132547","https://openalex.org/W4410054108","https://openalex.org/W4413146579","https://openalex.org/W7160089931"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"DWT-Mamba,":[3],"a":[4,47,53,58,83,92,151,168],"spatially":[5],"aware":[6],"deep":[7],"learning":[8],"architecture":[9],"designed":[10],"for":[11,172,182],"medical":[12,176],"image":[13,33,177],"classification":[14,120,137],"by":[15,46],"integrating":[16],"the":[17,105,118,131,156,183],"discrete":[18],"wavelet":[19],"transform":[20],"(DWT)":[21],"and":[22,56,114,146,158,174],"state-space":[23],"modelling":[24],"(SSM).":[25],"The":[26,108,164,179],"proposed":[27,132,165,184],"methodology":[28],"initially":[29],"decomposes":[30],"each":[31],"input":[32],"into":[34],"multiscale":[35],"frequency":[36,77],"subbands":[37],"using":[38,82],"Haar":[39],"wavelets.":[40],"Each":[41],"subband":[42],"is":[43,186],"independently":[44],"processed":[45],"custom":[48],"hierarchical":[49],"backbone":[50],"that":[51,130],"integrates":[52],"convolutional":[54],"branch":[55],"Mamba,":[57],"selective":[59],"SSM":[60],"channel":[61],"augmented":[62],"with":[63],"Squeeze-and-Excitation":[64],"(SE)":[65],"attention":[66],"mechanisms":[67],"to":[68,99,140],"enhance":[69],"feature":[70,95],"selectivity":[71],"(SpaSE-SSM).":[72],"Feature":[73],"representations":[74],"from":[75,104],"all":[76],"branches":[78],"are":[79],"subsequently":[80],"fused":[81],"novel":[84],"Multi-Branch":[85],"Gated":[86],"Shuffle":[87],"Fusion":[88],"(MB-GSF)":[89],"module,":[90],"while":[91],"compact":[93],"latent":[94],"encoder":[96],"operates":[97],"concurrently":[98],"extract":[100],"global":[101,115],"contextual":[102],"information":[103],"original":[106],"image.":[107],"adaptive":[109],"integration":[110],"of":[111,125,161],"these":[112],"local":[113,152],"features":[116],"determines":[117],"final":[119],"output.":[121],"An":[122],"experimental":[123],"evaluation":[124,149],"five":[126],"MedMNIST2D":[127],"datasets":[128],"demonstrates":[129],"DWT-Mamba":[133,166],"technique":[134],"achieves":[135],"superior":[136],"accuracy":[138],"compared":[139],"reference":[141],"models,":[142],"such":[143],"as":[144],"MedViT":[145],"ResNet.":[147],"Furthermore,":[148],"on":[150],"PET/CT":[153],"dataset":[154],"substantiates":[155],"generalizability":[157],"clinical":[159],"applicability":[160],"this":[162],"approach.":[163],"establishes":[167],"new":[169],"technical":[170],"benchmark":[171],"interpretable":[173],"reliable":[175],"analysis.":[178],"source":[180],"code":[181],"method":[185],"publicly":[187],"available":[188],"at":[189],"https://github.com/MoumitaDholey/DWT-Mamba.":[190]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}