{"id":"https://openalex.org/W7147253393","doi":"https://doi.org/10.48550/arxiv.2603.28057","title":"Physics-Embedded Feature Learning for AI in Medical Imaging","display_name":"Physics-Embedded Feature Learning for AI in Medical Imaging","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147253393","doi":"https://doi.org/10.48550/arxiv.2603.28057"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28057","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":null,"license_id":null,"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.2603.28057","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101296418","display_name":"Pulock Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Pulock","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132726027","display_name":"Al Amin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amin, Al","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132709507","display_name":"Md Kamrul Hasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasan, Kamrul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042448095","display_name":"Rohan Thompson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thompson, Rohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121639178","display_name":"Azubike Okpalaeze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Okpalaeze, Azubike D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132641317","display_name":"Liang Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Liang","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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.2745000123977661,"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"}},"topics":[{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.2745000123977661,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1501999944448471,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.06369999796152115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6711000204086304},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5770000219345093},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.569599986076355},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5562000274658203},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5022000074386597},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.4943999946117401},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4578000009059906}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7541000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405999898910522},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6711000204086304},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.569599986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5640000104904175},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5022000074386597},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27250000834465027}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28057","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.28057","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28057","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":[1,56,102,202],"(DL)":[2],"models":[3],"have":[4],"achieved":[5],"strong":[6],"performance":[7],"in":[8],"an":[9],"intelligence":[10],"healthcare":[11],"setting,":[12],"yet":[13],"most":[14],"existing":[15],"approaches":[16],"operate":[17],"as":[18,203],"black":[19],"boxes":[20],"and":[21,33,111,119,170,177,189,210],"ignore":[22],"the":[23,54,74],"physical":[24,70,114],"processes":[25],"that":[26,47,68,159,193],"govern":[27],"tumor":[28,49,84,99,105,117,148],"growth,":[29],"limiting":[30],"interpretability,":[31],"robustness,":[32],"clinical":[34],"trust.":[35],"To":[36],"address":[37],"this":[38],"limitation,":[39],"we":[40],"propose":[41],"PhysNet,":[42],"a":[43,59,79,91,103,153,204],"physics-embedded":[44,200],"DL":[45,164],"framework":[46],"integrates":[48],"growth":[50,85,120],"dynamics":[51],"directly":[52],"into":[53,147],"feature":[55,88],"process":[57],"of":[58,83,90],"convolutional":[60],"neural":[61],"network":[62],"(CNN).":[63],"Unlike":[64],"conventional":[65],"physics-informed":[66],"methods":[67],"impose":[69],"constraints":[71],"only":[72],"at":[73],"output":[75],"level,":[76],"PhysNet":[77,160,184],"embeds":[78],"reaction":[80],"diffusion":[81,118],"model":[82],"within":[86],"intermediate":[87],"representations":[89,188],"ResNet":[92],"backbone.":[93],"The":[94],"architecture":[95],"jointly":[96],"performs":[97],"multi-class":[98],"classification":[100,175],"while":[101],"latent":[104,187],"density":[106],"field,":[107],"its":[108],"temporal":[109],"evolution,":[110],"biologically":[112],"meaningful":[113,212],"parameters,":[115],"including":[116,166],"rates,":[121],"through":[122],"end-to-end":[123],"training.":[124],"This":[125],"design":[126],"is":[127],"necessary":[128],"because":[129],"purely":[130],"data-driven":[131],"models,":[132,172],"even":[133],"when":[134],"highly":[135],"accurate":[136],"or":[137,144],"ensemble-based,":[138],"cannot":[139],"guarantee":[140],"physically":[141],"consistent":[142],"predictions":[143],"provide":[145],"insight":[146],"behavior.":[149],"Experimental":[150],"results":[151],"on":[152],"large":[154],"brain":[155],"MRI":[156],"dataset":[157],"demonstrate":[158],"outperforms":[161],"multiple":[162],"state-of-the-art":[163],"baselines,":[165],"MobileNetV2,":[167],"VGG16,":[168],"VGG19,":[169],"ensemble":[171],"achieving":[173],"superior":[174],"accuracy":[176],"F1-score.":[178],"In":[179],"addition":[180],"to":[181],"improved":[182],"performance,":[183],"produces":[185],"interpretable":[186],"learned":[190],"bio-physical":[191],"parameters":[192],"align":[194],"with":[195],"established":[196],"medical":[197,213],"knowledge,":[198],"highlighting":[199],"representation":[201],"practical":[205],"pathway":[206],"toward":[207],"more":[208],"trustworthy":[209],"clinically":[211],"AI":[214],"systems.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}