Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage Analysis Article Swipe
Nikhil J. Dhinagar
,
Saket S. Ozarkar
,
Ketaki Buwa
,
Sophia I. Thomopoulos
,
Conor Owens‐Walton
,
Emily Laltoo
,
Chirag Jagad
,
Yao-Liang Chen
,
Philip Cook
,
Corey T. McMillan
,
Chih‐Chien Tsai
,
Julian Wang
,
Yih‐Ru Wu
,
Paul M. Thompson
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.02.15.638442
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.02.15.638442
Recent innovations in artificial intelligence (AI) have increasingly focused on large-scale foundational models that are more general purpose in contrast to conventional models trained to perform specialized tasks. Transformer-based architectures have become the standard backbone in foundation models across data modalities (image, text, audio, video). There has been a keen interest in applying parameter-efficient fine-tuning (PEFT) methods to adapt these models to specialized downstream tasks in language and vision. These methods are particularly essential for medical image analysis where the limited availability of training data could lead to overfitting. In this work, we evaluated different types of PEFT methods on pre-trained vision transformers relative to typical training approaches, such as full fine-tuning and training from scratch. We used a transformer-based masked autoencoder (MAE) framework, to pretrain a vision encoder on T1- weighted (T1-w) brain MRIs. The pretrained vision transformers were then fine-tuned using different PEFT methods that reduced the trainable model parameters to as few as 0.04% of the original model size. Our study shows that: 1. PEFT methods were competitive with or outperformed the reference full fine-tuning approach and outperformed training from scratch, with only a fraction of the trainable parameters; 2. PEFT methods with a 32% reduction in model size boosted Alzheimer’s disease (AD) classification by 3% relative to full fine-tuning and 11% relative to a 3D CNN, with only 258 training scans; and 3. PEFT methods performed well on diverse neuroimaging tasks including AD and Parkinson’s disease (PD) classification, and “brain-age” prediction based on T1-w MRI datasets - a standard benchmark for deep learning models in neuroimaging; 4. smaller model sizes were competitive with larger models in test performance. Our results show the value of adapting foundation models to neuroimaging tasks efficiently and effectively in contrast to training stand- alone special purpose models.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1101/2025.02.15.638442
- OA Status
- green
- Cited By
- 1
- References
- 20
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4407774075
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4407774075Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1101/2025.02.15.638442Digital Object Identifier
- Title
-
Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage AnalysisWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-20Full publication date if available
- Authors
-
Nikhil J. Dhinagar, Saket S. Ozarkar, Ketaki Buwa, Sophia I. Thomopoulos, Conor Owens‐Walton, Emily Laltoo, Chirag Jagad, Yao-Liang Chen, Philip Cook, Corey T. McMillan, Chih‐Chien Tsai, Julian Wang, Yih‐Ru Wu, Paul M. ThompsonList of authors in order
- Landing page
-
https://doi.org/10.1101/2025.02.15.638442Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.ncbi.nlm.nih.gov/pmc/articles/11870613Direct OA link when available
- Concepts
-
Autoencoder, Transformer, Computer science, Resource (disambiguation), Artificial intelligence, Engineering, Electrical engineering, Computer network, Voltage, Deep learningTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- References (count)
-
20Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4407774075 |
|---|---|
| doi | https://doi.org/10.1101/2025.02.15.638442 |
| ids.doi | https://doi.org/10.1101/2025.02.15.638442 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/40027656 |
| ids.openalex | https://openalex.org/W4407774075 |
| fwci | 4.77340731 |
| type | preprint |
| title | Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage Analysis |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9962000250816345 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T12859 |
| topics[1].field.id | https://openalex.org/fields/13 |
| topics[1].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[1].score | 0.9955999851226807 |
| topics[1].domain.id | https://openalex.org/domains/1 |
| topics[1].domain.display_name | Life Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1304 |
| topics[1].subfield.display_name | Biophysics |
| topics[1].display_name | Cell Image Analysis Techniques |
| topics[2].id | https://openalex.org/T10052 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9897000193595886 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Medical Image Segmentation Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C101738243 |
| concepts[0].level | 3 |
| concepts[0].score | 0.703922688961029 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[0].display_name | Autoencoder |
| concepts[1].id | https://openalex.org/C66322947 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6403661966323853 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[1].display_name | Transformer |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5583622455596924 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C206345919 |
| concepts[3].level | 2 |
| concepts[3].score | 0.42822033166885376 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q20380951 |
| concepts[3].display_name | Resource (disambiguation) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3597172796726227 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C127413603 |
| concepts[5].level | 0 |
| concepts[5].score | 0.18404245376586914 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[5].display_name | Engineering |
| concepts[6].id | https://openalex.org/C119599485 |
| concepts[6].level | 1 |
| concepts[6].score | 0.14274239540100098 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[6].display_name | Electrical engineering |
| concepts[7].id | https://openalex.org/C31258907 |
| concepts[7].level | 1 |
| concepts[7].score | 0.08873856067657471 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[7].display_name | Computer network |
| concepts[8].id | https://openalex.org/C165801399 |
| concepts[8].level | 2 |
| concepts[8].score | 0.07693842053413391 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[8].display_name | Voltage |
| concepts[9].id | https://openalex.org/C108583219 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[9].display_name | Deep learning |
| keywords[0].id | https://openalex.org/keywords/autoencoder |
| keywords[0].score | 0.703922688961029 |
| keywords[0].display_name | Autoencoder |
| keywords[1].id | https://openalex.org/keywords/transformer |
| keywords[1].score | 0.6403661966323853 |
| keywords[1].display_name | Transformer |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5583622455596924 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/resource |
| keywords[3].score | 0.42822033166885376 |
| keywords[3].display_name | Resource (disambiguation) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.3597172796726227 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/engineering |
| keywords[5].score | 0.18404245376586914 |
| keywords[5].display_name | Engineering |
| keywords[6].id | https://openalex.org/keywords/electrical-engineering |
| keywords[6].score | 0.14274239540100098 |
| keywords[6].display_name | Electrical engineering |
| keywords[7].id | https://openalex.org/keywords/computer-network |
| keywords[7].score | 0.08873856067657471 |
| keywords[7].display_name | Computer network |
| keywords[8].id | https://openalex.org/keywords/voltage |
| keywords[8].score | 0.07693842053413391 |
| keywords[8].display_name | Voltage |
| language | en |
| locations[0].id | doi:10.1101/2025.02.15.638442 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4306402567 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| locations[0].source.host_organization | https://openalex.org/I2750212522 |
| locations[0].source.host_organization_name | Cold Spring Harbor Laboratory |
| locations[0].source.host_organization_lineage | https://openalex.org/I2750212522 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.1101/2025.02.15.638442 |
| locations[1].id | pmid:40027656 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | bioRxiv : the preprint server for biology |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/40027656 |
| locations[2].id | pmh:oai:pubmedcentral.nih.gov:11870613 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S2764455111 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | PubMed Central |
| locations[2].source.host_organization | https://openalex.org/I1299303238 |
| locations[2].source.host_organization_name | National Institutes of Health |
| locations[2].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | Text |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | bioRxiv |
| locations[2].landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11870613 |
| indexed_in | crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5089189717 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2424-4854 |
| authorships[0].author.display_name | Nikhil J. Dhinagar |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[0].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[0].institutions[0].id | https://openalex.org/I1174212 |
| authorships[0].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Southern California |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nikhil J. Dhinagar |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[1].author.id | https://openalex.org/A5024446214 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Saket S. Ozarkar |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[1].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[1].institutions[0].id | https://openalex.org/I1174212 |
| authorships[1].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | University of Southern California |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Saket S. Ozarkar |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[2].author.id | https://openalex.org/A5048439744 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Ketaki Buwa |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[2].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[2].institutions[0].id | https://openalex.org/I1174212 |
| authorships[2].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | University of Southern California |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ketaki U. Buwa |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[3].author.id | https://openalex.org/A5017365268 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0046-4070 |
| authorships[3].author.display_name | Sophia I. Thomopoulos |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[3].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[3].institutions[0].id | https://openalex.org/I1174212 |
| authorships[3].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | University of Southern California |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Sophia I. Thomopoulos |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[4].author.id | https://openalex.org/A5008621272 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0589-638X |
| authorships[4].author.display_name | Conor Owens‐Walton |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[4].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[4].institutions[0].id | https://openalex.org/I1174212 |
| authorships[4].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | University of Southern California |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Conor Owens-Walton |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[5].author.id | https://openalex.org/A5055654698 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Emily Laltoo |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[5].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[5].institutions[0].id | https://openalex.org/I1174212 |
| authorships[5].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[5].institutions[0].country_code | US |
| authorships[5].institutions[0].display_name | University of Southern California |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Emily Laltoo |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[6].author.id | https://openalex.org/A5009543931 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-6119-3956 |
| authorships[6].author.display_name | Chirag Jagad |
| authorships[6].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[6].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[6].institutions[0].id | https://openalex.org/I1174212 |
| authorships[6].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | University of Southern California |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Chirag Jagad |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[7].author.id | https://openalex.org/A5074014986 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Yao-Liang Chen |
| authorships[7].countries | TW |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I4210111603 |
| authorships[7].affiliations[0].raw_affiliation_string | Department of Diagnostic Radiology, Chang Gung Memorial Hospital, Keelung, Taiwan |
| authorships[7].institutions[0].id | https://openalex.org/I4210111603 |
| authorships[7].institutions[0].ror | https://ror.org/020dg9f27 |
| authorships[7].institutions[0].type | healthcare |
| authorships[7].institutions[0].lineage | https://openalex.org/I4210111603 |
| authorships[7].institutions[0].country_code | TW |
| authorships[7].institutions[0].display_name | Keelung Chang Gung Memorial Hospital |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Yao-Liang Chen |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | Department of Diagnostic Radiology, Chang Gung Memorial Hospital, Keelung, Taiwan |
| authorships[8].author.id | https://openalex.org/A5103169115 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-7791-7998 |
| authorships[8].author.display_name | Philip Cook |
| authorships[8].countries | US |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I79576946 |
| authorships[8].affiliations[0].raw_affiliation_string | Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA |
| authorships[8].institutions[0].id | https://openalex.org/I79576946 |
| authorships[8].institutions[0].ror | https://ror.org/00b30xv10 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I79576946 |
| authorships[8].institutions[0].country_code | US |
| authorships[8].institutions[0].display_name | University of Pennsylvania |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Philip Cook |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA |
| authorships[9].author.id | https://openalex.org/A5037938359 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-7581-6405 |
| authorships[9].author.display_name | Corey T. McMillan |
| authorships[9].countries | US |
| authorships[9].affiliations[0].institution_ids | https://openalex.org/I79576946 |
| authorships[9].affiliations[0].raw_affiliation_string | Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA |
| authorships[9].institutions[0].id | https://openalex.org/I79576946 |
| authorships[9].institutions[0].ror | https://ror.org/00b30xv10 |
| authorships[9].institutions[0].type | education |
| authorships[9].institutions[0].lineage | https://openalex.org/I79576946 |
| authorships[9].institutions[0].country_code | US |
| authorships[9].institutions[0].display_name | University of Pennsylvania |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Corey McMillan |
| authorships[9].is_corresponding | False |
| authorships[9].raw_affiliation_strings | Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA |
| authorships[10].author.id | https://openalex.org/A5103239025 |
| authorships[10].author.orcid | https://orcid.org/0000-0003-2210-1972 |
| authorships[10].author.display_name | Chih‐Chien Tsai |
| authorships[10].countries | TW |
| authorships[10].affiliations[0].institution_ids | https://openalex.org/I173093425 |
| authorships[10].affiliations[0].raw_affiliation_string | Healthy Aging Research Center, Chang Gung University, Taoyuan, Taiwan |
| authorships[10].institutions[0].id | https://openalex.org/I173093425 |
| authorships[10].institutions[0].ror | https://ror.org/00d80zx46 |
| authorships[10].institutions[0].type | education |
| authorships[10].institutions[0].lineage | https://openalex.org/I173093425 |
| authorships[10].institutions[0].country_code | TW |
| authorships[10].institutions[0].display_name | Chang Gung University |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Chih-Chien Tsai |
| authorships[10].is_corresponding | False |
| authorships[10].raw_affiliation_strings | Healthy Aging Research Center, Chang Gung University, Taoyuan, Taiwan |
| authorships[11].author.id | https://openalex.org/A5073000065 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-3056-5569 |
| authorships[11].author.display_name | Julian Wang |
| authorships[11].countries | TW |
| authorships[11].affiliations[0].institution_ids | https://openalex.org/I173093425 |
| authorships[11].affiliations[0].raw_affiliation_string | Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan |
| authorships[11].institutions[0].id | https://openalex.org/I173093425 |
| authorships[11].institutions[0].ror | https://ror.org/00d80zx46 |
| authorships[11].institutions[0].type | education |
| authorships[11].institutions[0].lineage | https://openalex.org/I173093425 |
| authorships[11].institutions[0].country_code | TW |
| authorships[11].institutions[0].display_name | Chang Gung University |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | J-J Wang |
| authorships[11].is_corresponding | False |
| authorships[11].raw_affiliation_strings | Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan |
| authorships[12].author.id | https://openalex.org/A5062034731 |
| authorships[12].author.orcid | https://orcid.org/0000-0003-1191-2542 |
| authorships[12].author.display_name | Yih‐Ru Wu |
| authorships[12].countries | TW |
| authorships[12].affiliations[0].institution_ids | https://openalex.org/I3020100970 |
| authorships[12].affiliations[0].raw_affiliation_string | Department of Neurology, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan |
| authorships[12].institutions[0].id | https://openalex.org/I3020100970 |
| authorships[12].institutions[0].ror | https://ror.org/02verss31 |
| authorships[12].institutions[0].type | healthcare |
| authorships[12].institutions[0].lineage | https://openalex.org/I3020100970 |
| authorships[12].institutions[0].country_code | TW |
| authorships[12].institutions[0].display_name | Chang Gung Memorial Hospital |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Yih-Ru Wu |
| authorships[12].is_corresponding | False |
| authorships[12].raw_affiliation_strings | Department of Neurology, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan |
| authorships[13].author.id | https://openalex.org/A5108111412 |
| authorships[13].author.orcid | |
| authorships[13].author.display_name | Paul M. Thompson |
| authorships[13].countries | US |
| authorships[13].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[13].affiliations[0].raw_affiliation_string | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| authorships[13].institutions[0].id | https://openalex.org/I1174212 |
| authorships[13].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[13].institutions[0].type | education |
| authorships[13].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[13].institutions[0].country_code | US |
| authorships[13].institutions[0].display_name | University of Southern California |
| authorships[13].author_position | last |
| authorships[13].raw_author_name | Paul M. Thompson |
| authorships[13].is_corresponding | False |
| authorships[13].raw_affiliation_strings | Imaging Genetics Center, Mark & Mary Stevens Neuroimaging & Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11870613 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage Analysis |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9962000250816345 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Neural Network Applications |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W3013693939, https://openalex.org/W2566616303, https://openalex.org/W2159052453, https://openalex.org/W3131327266, https://openalex.org/W2734887215, https://openalex.org/W2803255133, https://openalex.org/W4220775285 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:pubmedcentral.nih.gov:11870613 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2764455111 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | PubMed Central |
| best_oa_location.source.host_organization | https://openalex.org/I1299303238 |
| best_oa_location.source.host_organization_name | National Institutes of Health |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I1299303238 |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | Text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | bioRxiv |
| best_oa_location.landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11870613 |
| primary_location.id | doi:10.1101/2025.02.15.638442 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4306402567 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| primary_location.source.host_organization | https://openalex.org/I2750212522 |
| primary_location.source.host_organization_name | Cold Spring Harbor Laboratory |
| primary_location.source.host_organization_lineage | https://openalex.org/I2750212522 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.1101/2025.02.15.638442 |
| publication_date | 2025-02-20 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4393407350, https://openalex.org/W4293103539, https://openalex.org/W3203607638, https://openalex.org/W3005680577, https://openalex.org/W4280490805, https://openalex.org/W4386352556, https://openalex.org/W6800751262, https://openalex.org/W4282005462, https://openalex.org/W6759579507, https://openalex.org/W6796581206, https://openalex.org/W4205991051, https://openalex.org/W6852717961, https://openalex.org/W4376653706, https://openalex.org/W4367189325, https://openalex.org/W4361302959, https://openalex.org/W4401750332, https://openalex.org/W2117340355, https://openalex.org/W1915710460, https://openalex.org/W1947223519, https://openalex.org/W2995808388 |
| referenced_works_count | 20 |
| abstract_inverted_index.- | 251 |
| abstract_inverted_index.a | 49, 119, 127, 187, 197, 218, 252 |
| abstract_inverted_index.1. | 167 |
| abstract_inverted_index.2. | 193 |
| abstract_inverted_index.3% | 209 |
| abstract_inverted_index.3. | 227 |
| abstract_inverted_index.3D | 219 |
| abstract_inverted_index.4. | 261 |
| abstract_inverted_index.AD | 237 |
| abstract_inverted_index.In | 90 |
| abstract_inverted_index.We | 117 |
| abstract_inverted_index.as | 110, 154, 156 |
| abstract_inverted_index.by | 208 |
| abstract_inverted_index.in | 3, 19, 36, 52, 66, 200, 259, 270, 288 |
| abstract_inverted_index.of | 83, 97, 158, 189, 278 |
| abstract_inverted_index.on | 10, 100, 130, 232, 247 |
| abstract_inverted_index.or | 173 |
| abstract_inverted_index.to | 21, 25, 58, 62, 88, 105, 125, 153, 211, 217, 282, 290 |
| abstract_inverted_index.we | 93 |
| abstract_inverted_index.11% | 215 |
| abstract_inverted_index.258 | 223 |
| abstract_inverted_index.32% | 198 |
| abstract_inverted_index.MRI | 249 |
| abstract_inverted_index.Our | 163, 273 |
| abstract_inverted_index.T1- | 131 |
| abstract_inverted_index.The | 136 |
| abstract_inverted_index.and | 68, 113, 180, 214, 226, 238, 243, 286 |
| abstract_inverted_index.are | 15, 72 |
| abstract_inverted_index.few | 155 |
| abstract_inverted_index.for | 75, 255 |
| abstract_inverted_index.has | 47 |
| abstract_inverted_index.the | 33, 80, 149, 159, 175, 190, 276 |
| abstract_inverted_index.(AD) | 206 |
| abstract_inverted_index.(AI) | 6 |
| abstract_inverted_index.(PD) | 241 |
| abstract_inverted_index.CNN, | 220 |
| abstract_inverted_index.PEFT | 98, 145, 168, 194, 228 |
| abstract_inverted_index.T1-w | 248 |
| abstract_inverted_index.been | 48 |
| abstract_inverted_index.data | 40, 85 |
| abstract_inverted_index.deep | 256 |
| abstract_inverted_index.from | 115, 183 |
| abstract_inverted_index.full | 111, 177, 212 |
| abstract_inverted_index.have | 7, 31 |
| abstract_inverted_index.keen | 50 |
| abstract_inverted_index.lead | 87 |
| abstract_inverted_index.more | 16 |
| abstract_inverted_index.only | 186, 222 |
| abstract_inverted_index.show | 275 |
| abstract_inverted_index.size | 202 |
| abstract_inverted_index.such | 109 |
| abstract_inverted_index.test | 271 |
| abstract_inverted_index.that | 14, 147 |
| abstract_inverted_index.then | 141 |
| abstract_inverted_index.this | 91 |
| abstract_inverted_index.used | 118 |
| abstract_inverted_index.well | 231 |
| abstract_inverted_index.were | 140, 170, 265 |
| abstract_inverted_index.with | 172, 185, 196, 221, 267 |
| abstract_inverted_index.(MAE) | 123 |
| abstract_inverted_index.0.04% | 157 |
| abstract_inverted_index.MRIs. | 135 |
| abstract_inverted_index.There | 46 |
| abstract_inverted_index.These | 70 |
| abstract_inverted_index.adapt | 59 |
| abstract_inverted_index.alone | 293 |
| abstract_inverted_index.based | 246 |
| abstract_inverted_index.brain | 134 |
| abstract_inverted_index.could | 86 |
| abstract_inverted_index.image | 77 |
| abstract_inverted_index.model | 151, 161, 201, 263 |
| abstract_inverted_index.shows | 165 |
| abstract_inverted_index.size. | 162 |
| abstract_inverted_index.sizes | 264 |
| abstract_inverted_index.study | 164 |
| abstract_inverted_index.tasks | 65, 235, 284 |
| abstract_inverted_index.text, | 43 |
| abstract_inverted_index.that: | 166 |
| abstract_inverted_index.these | 60 |
| abstract_inverted_index.types | 96 |
| abstract_inverted_index.using | 143 |
| abstract_inverted_index.value | 277 |
| abstract_inverted_index.where | 79 |
| abstract_inverted_index.work, | 92 |
| abstract_inverted_index.(PEFT) | 56 |
| abstract_inverted_index.(T1-w) | 133 |
| abstract_inverted_index.Recent | 1 |
| abstract_inverted_index.across | 39 |
| abstract_inverted_index.audio, | 44 |
| abstract_inverted_index.become | 32 |
| abstract_inverted_index.larger | 268 |
| abstract_inverted_index.masked | 121 |
| abstract_inverted_index.models | 13, 23, 38, 61, 258, 269, 281 |
| abstract_inverted_index.scans; | 225 |
| abstract_inverted_index.stand- | 292 |
| abstract_inverted_index.tasks. | 28 |
| abstract_inverted_index.vision | 102, 128, 138 |
| abstract_inverted_index.(image, | 42 |
| abstract_inverted_index.boosted | 203 |
| abstract_inverted_index.disease | 205, 240 |
| abstract_inverted_index.diverse | 233 |
| abstract_inverted_index.encoder | 129 |
| abstract_inverted_index.focused | 9 |
| abstract_inverted_index.general | 17 |
| abstract_inverted_index.limited | 81 |
| abstract_inverted_index.medical | 76 |
| abstract_inverted_index.methods | 57, 71, 99, 146, 169, 195, 229 |
| abstract_inverted_index.models. | 296 |
| abstract_inverted_index.perform | 26 |
| abstract_inverted_index.purpose | 18, 295 |
| abstract_inverted_index.reduced | 148 |
| abstract_inverted_index.results | 274 |
| abstract_inverted_index.smaller | 262 |
| abstract_inverted_index.special | 294 |
| abstract_inverted_index.trained | 24 |
| abstract_inverted_index.typical | 106 |
| abstract_inverted_index.video). | 45 |
| abstract_inverted_index.vision. | 69 |
| abstract_inverted_index.ABSTRACT | 0 |
| abstract_inverted_index.adapting | 279 |
| abstract_inverted_index.analysis | 78 |
| abstract_inverted_index.applying | 53 |
| abstract_inverted_index.approach | 179 |
| abstract_inverted_index.backbone | 35 |
| abstract_inverted_index.contrast | 20, 289 |
| abstract_inverted_index.datasets | 250 |
| abstract_inverted_index.fraction | 188 |
| abstract_inverted_index.interest | 51 |
| abstract_inverted_index.language | 67 |
| abstract_inverted_index.learning | 257 |
| abstract_inverted_index.original | 160 |
| abstract_inverted_index.pretrain | 126 |
| abstract_inverted_index.relative | 104, 210, 216 |
| abstract_inverted_index.scratch, | 184 |
| abstract_inverted_index.scratch. | 116 |
| abstract_inverted_index.standard | 34, 253 |
| abstract_inverted_index.training | 84, 107, 114, 182, 224, 291 |
| abstract_inverted_index.weighted | 132 |
| abstract_inverted_index.benchmark | 254 |
| abstract_inverted_index.different | 95, 144 |
| abstract_inverted_index.essential | 74 |
| abstract_inverted_index.evaluated | 94 |
| abstract_inverted_index.including | 236 |
| abstract_inverted_index.performed | 230 |
| abstract_inverted_index.reduction | 199 |
| abstract_inverted_index.reference | 176 |
| abstract_inverted_index.trainable | 150, 191 |
| abstract_inverted_index.artificial | 4 |
| abstract_inverted_index.downstream | 64 |
| abstract_inverted_index.fine-tuned | 142 |
| abstract_inverted_index.foundation | 37, 280 |
| abstract_inverted_index.framework, | 124 |
| abstract_inverted_index.modalities | 41 |
| abstract_inverted_index.parameters | 152 |
| abstract_inverted_index.prediction | 245 |
| abstract_inverted_index.pretrained | 137 |
| abstract_inverted_index.approaches, | 108 |
| abstract_inverted_index.autoencoder | 122 |
| abstract_inverted_index.competitive | 171, 266 |
| abstract_inverted_index.effectively | 287 |
| abstract_inverted_index.efficiently | 285 |
| abstract_inverted_index.fine-tuning | 55, 112, 178, 213 |
| abstract_inverted_index.innovations | 2 |
| abstract_inverted_index.large-scale | 11 |
| abstract_inverted_index.parameters; | 192 |
| abstract_inverted_index.pre-trained | 101 |
| abstract_inverted_index.specialized | 27, 63 |
| abstract_inverted_index.availability | 82 |
| abstract_inverted_index.conventional | 22 |
| abstract_inverted_index.foundational | 12 |
| abstract_inverted_index.increasingly | 8 |
| abstract_inverted_index.intelligence | 5 |
| abstract_inverted_index.neuroimaging | 234, 283 |
| abstract_inverted_index.outperformed | 174, 181 |
| abstract_inverted_index.overfitting. | 89 |
| abstract_inverted_index.particularly | 73 |
| abstract_inverted_index.performance. | 272 |
| abstract_inverted_index.transformers | 103, 139 |
| abstract_inverted_index.Alzheimer’s | 204 |
| abstract_inverted_index.Parkinson’s | 239 |
| abstract_inverted_index.architectures | 30 |
| abstract_inverted_index.neuroimaging; | 260 |
| abstract_inverted_index.classification | 207 |
| abstract_inverted_index.classification, | 242 |
| abstract_inverted_index.“brain-age” | 244 |
| abstract_inverted_index.Transformer-based | 29 |
| abstract_inverted_index.transformer-based | 120 |
| abstract_inverted_index.parameter-efficient | 54 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| corresponding_author_ids | https://openalex.org/A5089189717 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 14 |
| corresponding_institution_ids | https://openalex.org/I1174212 |
| citation_normalized_percentile.value | 0.83672568 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |