{"authors":[{"id":null,"fullName":"Lapenna M.","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-5293-9499"},"provenance":null}},{"id":"orcid_______::a7bf69e0e8517d09644eb5ab02911481","fullName":"Tsamos A.","name":null,"surname":null,"rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0002-4645-090x"},"provenance":null}},{"id":null,"fullName":"Faglioni F.","name":null,"surname":null,"rank":3,"pid":null},{"id":null,"fullName":"Fioresi R.","name":null,"surname":null,"rank":4,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-4075-7641"},"provenance":null}},{"id":null,"fullName":"Zanchetta F.","name":null,"surname":null,"rank":5,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-2294-2755"},"provenance":null}},{"id":null,"fullName":"Bruno G.","name":null,"surname":null,"rank":6,"pid":null}],"openAccessColor":"hybrid","publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"IT","label":"Italy","provenance":null}],"subjects":[{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Cartan Geometry"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null}],"mainTitle":"Vision GNN (ViG) architecture for a fine-tuned segmentation of a complex Al–Si metal matrix composite XCT volume","subTitle":null,"descriptions":["<jats:title>Abstract</jats:title>           <jats:p>In this paper, we implement a vision graph neural network (ViG) architecture to segment microstructures in X-ray computed tomography 3D data. Our ViG architecture is first trained on a synthetic augmented dataset, and then fine-tuned on experimental data to obtain an improved segmentation. Successively, we assess the accuracy of the segmentation on manually-labeled experimental slices. We exemplarily use the approach on a complex microstructure: a metal matrix composite, reinforced with two ceramic phases, intermetallic inclusions and a silicon network, in order to show the generality of our method. ViG model proves to be more efficient than U-Nets in adapting to new data when fine-tuned on a small portion of the experimental data. The fine-tuned ViG shows comparable performance to U-Nets, while largely reducing the number of trainable parameters, with the potential of greater adaptability and efficiency.</jats:p>"],"publicationDate":"2025-04-01","publisher":"Springer Science and Business Media LLC","embargoEndDate":null,"sources":["Crossref"],"formats":["application/pdf"],"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Journal of Materials Science","issnPrinted":"0022-2461","issnOnline":"1573-4803","issnLinking":null,"ep":"6921","iss":null,"sp":"6907","vol":"60","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::488fd60929a068be451c29edf692f2b2","originalIds":["10834","10.1007/s10853-025-10834-5","50|doiboost____|488fd60929a068be451c29edf692f2b2","50|od______4094::7c12ef2349734ca1601599d69eaa4b03","oai:cris.unibo.it:11585/1047124"],"pids":[{"scheme":"doi","value":"10.1007/s10853-025-10834-5"},{"scheme":"handle","value":"11585/1047124"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":2.0,"influence":2.3930913E-9,"popularity":3.7145937E-9,"impulse":2.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C4"}},"projects":[{"id":"corda_____he::c394b22545d1ed08771bdd1fd77c4280","code":"101086123","acronym":"CaLIGOLA","title":"Cartan geometry, Lie and representation theory, Integrable Systems, quantum Groups and quantum computing towards the understanding of the geometry of deep Learning and its Applications","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101086123"}]}],"organizations":[{"legalName":"Alma Mater Studiorum University of Bologna","acronym":"UNIBO","id":"openorgs____::b5ca9d4340e26454e367e2908ef3872f","pids":[{"scheme":"mag_id","value":"9360294"},{"scheme":"OrgReg","value":"IT0009"},{"scheme":"ROR","value":"https://ror.org/01111rn36"},{"scheme":"wikidata","value":"Q131262"},{"scheme":"fundref","value":"501100005969"},{"scheme":"OrgRef","value":"263329"},{"scheme":"PIC","value":"999993953"},{"scheme":"ISNI","value":"0000000417571758"},{"scheme":"FundRef","value":"501100005969"},{"scheme":"Wikidata","value":"Q131262"},{"scheme":"GRID","value":"grid.6292.f"},{"scheme":"RRID","value":"RRID:SCR_011610"}]},{"legalName":"Federal Institute For Materials Research and Testing","acronym":"BAM","id":"openorgs____::00c4fbf54ec77a86bcbbc4ce612a36ee","pids":[{"scheme":"OrgRef","value":"7711116"},{"scheme":"PIC","value":"999507692"},{"scheme":"FundRef","value":"100009553"},{"scheme":"GRID","value":"grid.71566.33"},{"scheme":"ROR","value":"https://ror.org/03x516a66"},{"scheme":"OrgReg","value":"DE3020"},{"scheme":"fundref","value":"100009553"},{"scheme":"ISNI","value":"0000000406035458"},{"scheme":"Wikidata","value":"Q1005540"},{"scheme":"wikidata","value":"Q1005540"},{"scheme":"mag_id","value":"1330165540"}]},{"legalName":"University of Potsdam","acronym":"UP","id":"openorgs____::a6c374b8c2f669bc81d647d4bbd16c4d","pids":[{"scheme":"ISNI","value":"0000000109421117"},{"scheme":"FundRef","value":"501100004238"},{"scheme":"Wikidata","value":"Q153012"},{"scheme":"fundref","value":"501100004238"},{"scheme":"VIAF","value":"VIAF:134924875"},{"scheme":"GRID","value":"grid.11348.3f"},{"scheme":"wikidata","value":"Q153012"},{"scheme":"OrgReg","value":"DE0039"},{"scheme":"ROR","value":"https://ror.org/03bnmw459"},{"scheme":"PIC","value":"999854855"},{"scheme":"OrgRef","value":"4039448"},{"scheme":"mag_id","value":"176453806"}]}],"communities":null,"collectedFrom":[{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"opendoar____::64c53a52cb3bd1a01c03a64db985c0cc","value":"Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1007/s10853-025-10834-5"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"hybrid"},"type":"Article","urls":["https://doi.org/10.1007/s10853-025-10834-5"],"publicationDate":"2025-04-01","refereed":"peerReviewed","hostedBy":{"key":"issn___print::44a4b9067d9fd287dd525660d16f6774","value":"Journal of Materials Science"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"handle","value":"11585/1047124"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/s10853-025-10834-5"},{"scheme":"urn","value":"2-s2.0-105003710577"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Article","urls":["https://link.springer.com/article/10.1007/s10853-025-10834-5","https://doi.org/10.1007/s10853-025-10834-5","https://hdl.handle.net/11585/1047124"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::64c53a52cb3bd1a01c03a64db985c0cc","value":"Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna"},"collectedFrom":{"key":"opendoar____::64c53a52cb3bd1a01c03a64db985c0cc","value":"Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::c394b22545d1ed08771bdd1fd77c4280","relatedRecordType":"project","relationProvenance":"iis","trust":"0.897"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"Cartan geometry, Lie and representation theory, Integrable Systems, quantum Groups and quantum computing towards the understanding of the geometry of deep Learning and its Applications","code":"101086123","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-AG-UN","description":"HORIZON Unit Grant","name":"HORIZON-AG-UN"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2023-01-01","endDate":"2026-12-31"}],"otherTitles":null,"inDiamondJournal":false,"green":false,"isGreen":false,"isInDiamondJournal":false}