Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction Article Swipe
Yuning Du
,
Yuyang Xue
,
Rohan Dharmakumar
,
Sotirios A. Tsaftaris
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.14392
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.14392
Deep learning (DL) reconstruction particularly of MRI has led to improvements in image fidelity and reduction of acquisition time. In neuroimaging, DL methods can reconstruct high-quality images from undersampled data. However, it is essential to consider fairness in DL algorithms, particularly in terms of demographic characteristics. This study presents the first fairness analysis in a DL-based brain MRI reconstruction model. The model utilises the U-Net architecture for image reconstruction and explores the presence and sources of unfairness by implementing baseline Empirical Risk Minimisation (ERM) and rebalancing strategies. Model performance is evaluated using image reconstruction metrics. Our findings reveal statistically significant performance biases between the gender and age subgroups. Surprisingly, data imbalance and training discrimination are not the main sources of bias. This analysis provides insights of fairness in DL-based image reconstruction and aims to improve equity in medical AI applications.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2309.14392
- https://arxiv.org/pdf/2309.14392
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387145075
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387145075Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2309.14392Digital Object Identifier
- Title
-
Unveiling Fairness Biases in Deep Learning-Based Brain MRI ReconstructionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-09-25Full publication date if available
- Authors
-
Yuning Du, Yuyang Xue, Rohan Dharmakumar, Sotirios A. TsaftarisList of authors in order
- Landing page
-
https://arxiv.org/abs/2309.14392Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2309.14392Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2309.14392Direct OA link when available
- Concepts
-
Iterative reconstruction, Fidelity, Computer science, Artificial intelligence, Deep learning, Equity (law), Neuroimaging, Image quality, Machine learning, Image (mathematics), Dictionary learning, Psychology, Law, Psychiatry, Telecommunications, Political scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387145075 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2309.14392 |
| ids.doi | https://doi.org/10.48550/arxiv.2309.14392 |
| ids.openalex | https://openalex.org/W4387145075 |
| fwci | |
| type | preprint |
| title | Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction |
| awards[0].id | https://openalex.org/G7471596932 |
| awards[0].funder_id | https://openalex.org/F4320334627 |
| awards[0].display_name | |
| awards[0].funder_award_id | EP/X017680/1 |
| awards[0].funder_display_name | Engineering and Physical Sciences Research Council |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12026 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.887499988079071 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Explainable Artificial Intelligence (XAI) |
| funders[0].id | https://openalex.org/F4320334627 |
| funders[0].ror | https://ror.org/0439y7842 |
| funders[0].display_name | Engineering and Physical Sciences Research Council |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C141379421 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7055427432060242 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6094427 |
| concepts[0].display_name | Iterative reconstruction |
| concepts[1].id | https://openalex.org/C2776459999 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6626267433166504 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2119376 |
| concepts[1].display_name | Fidelity |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6377304196357727 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6052039861679077 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C108583219 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5823172926902771 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep learning |
| concepts[5].id | https://openalex.org/C199728807 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5759446620941162 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2578557 |
| concepts[5].display_name | Equity (law) |
| concepts[6].id | https://openalex.org/C58693492 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5485086441040039 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q551875 |
| concepts[6].display_name | Neuroimaging |
| concepts[7].id | https://openalex.org/C55020928 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4854603409767151 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q3813865 |
| concepts[7].display_name | Image quality |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4556758999824524 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C115961682 |
| concepts[9].level | 2 |
| concepts[9].score | 0.453311949968338 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[9].display_name | Image (mathematics) |
| concepts[10].id | https://openalex.org/C2988886741 |
| concepts[10].level | 3 |
| concepts[10].score | 0.4501134157180786 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q25304494 |
| concepts[10].display_name | Dictionary learning |
| concepts[11].id | https://openalex.org/C15744967 |
| concepts[11].level | 0 |
| concepts[11].score | 0.22940000891685486 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[11].display_name | Psychology |
| concepts[12].id | https://openalex.org/C199539241 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[12].display_name | Law |
| concepts[13].id | https://openalex.org/C118552586 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7867 |
| concepts[13].display_name | Psychiatry |
| concepts[14].id | https://openalex.org/C76155785 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[14].display_name | Telecommunications |
| concepts[15].id | https://openalex.org/C17744445 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[15].display_name | Political science |
| keywords[0].id | https://openalex.org/keywords/iterative-reconstruction |
| keywords[0].score | 0.7055427432060242 |
| keywords[0].display_name | Iterative reconstruction |
| keywords[1].id | https://openalex.org/keywords/fidelity |
| keywords[1].score | 0.6626267433166504 |
| keywords[1].display_name | Fidelity |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6377304196357727 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.6052039861679077 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/deep-learning |
| keywords[4].score | 0.5823172926902771 |
| keywords[4].display_name | Deep learning |
| keywords[5].id | https://openalex.org/keywords/equity |
| keywords[5].score | 0.5759446620941162 |
| keywords[5].display_name | Equity (law) |
| keywords[6].id | https://openalex.org/keywords/neuroimaging |
| keywords[6].score | 0.5485086441040039 |
| keywords[6].display_name | Neuroimaging |
| keywords[7].id | https://openalex.org/keywords/image-quality |
| keywords[7].score | 0.4854603409767151 |
| keywords[7].display_name | Image quality |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.4556758999824524 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/image |
| keywords[9].score | 0.453311949968338 |
| keywords[9].display_name | Image (mathematics) |
| keywords[10].id | https://openalex.org/keywords/dictionary-learning |
| keywords[10].score | 0.4501134157180786 |
| keywords[10].display_name | Dictionary learning |
| keywords[11].id | https://openalex.org/keywords/psychology |
| keywords[11].score | 0.22940000891685486 |
| keywords[11].display_name | Psychology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2309.14392 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2309.14392 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2309.14392 |
| locations[1].id | doi:10.48550/arxiv.2309.14392 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2309.14392 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5010944460 |
| authorships[0].author.orcid | https://orcid.org/0009-0007-4995-5472 |
| authorships[0].author.display_name | Yuning Du |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Du, Yuning |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5008578775 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2281-9418 |
| authorships[1].author.display_name | Yuyang Xue |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xue, Yuyang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5086319135 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4120-4635 |
| authorships[2].author.display_name | Rohan Dharmakumar |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Dharmakumar, Rohan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5054437456 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8795-9294 |
| authorships[3].author.display_name | Sotirios A. Tsaftaris |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Tsaftaris, Sotirios A. |
| authorships[3].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2309.14392 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-09-29T00:00:00 |
| display_name | Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12026 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.887499988079071 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Explainable Artificial Intelligence (XAI) |
| related_works | https://openalex.org/W2757389719, https://openalex.org/W2951714568, https://openalex.org/W1963814553, https://openalex.org/W2037595954, https://openalex.org/W1988158806, https://openalex.org/W2507293823, https://openalex.org/W2386146599, https://openalex.org/W2018015402, https://openalex.org/W2144778520, https://openalex.org/W2801815023 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2309.14392 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| 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 | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2309.14392 |
| 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 | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2309.14392 |
| primary_location.id | pmh:oai:arXiv.org:2309.14392 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2309.14392 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2309.14392 |
| publication_date | 2023-09-25 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 54 |
| abstract_inverted_index.AI | 138 |
| abstract_inverted_index.DL | 21, 38 |
| abstract_inverted_index.In | 19 |
| abstract_inverted_index.by | 77 |
| abstract_inverted_index.in | 11, 37, 41, 53, 127, 136 |
| abstract_inverted_index.is | 32, 89 |
| abstract_inverted_index.it | 31 |
| abstract_inverted_index.of | 5, 16, 43, 75, 119, 125 |
| abstract_inverted_index.to | 9, 34, 133 |
| abstract_inverted_index.MRI | 6, 57 |
| abstract_inverted_index.Our | 95 |
| abstract_inverted_index.The | 60 |
| abstract_inverted_index.age | 106 |
| abstract_inverted_index.and | 14, 69, 73, 84, 105, 111, 131 |
| abstract_inverted_index.are | 114 |
| abstract_inverted_index.can | 23 |
| abstract_inverted_index.for | 66 |
| abstract_inverted_index.has | 7 |
| abstract_inverted_index.led | 8 |
| abstract_inverted_index.not | 115 |
| abstract_inverted_index.the | 49, 63, 71, 103, 116 |
| abstract_inverted_index.(DL) | 2 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.Risk | 81 |
| abstract_inverted_index.This | 46, 121 |
| abstract_inverted_index.aims | 132 |
| abstract_inverted_index.data | 109 |
| abstract_inverted_index.from | 27 |
| abstract_inverted_index.main | 117 |
| abstract_inverted_index.(ERM) | 83 |
| abstract_inverted_index.Model | 87 |
| abstract_inverted_index.U-Net | 64 |
| abstract_inverted_index.bias. | 120 |
| abstract_inverted_index.brain | 56 |
| abstract_inverted_index.data. | 29 |
| abstract_inverted_index.first | 50 |
| abstract_inverted_index.image | 12, 67, 92, 129 |
| abstract_inverted_index.model | 61 |
| abstract_inverted_index.study | 47 |
| abstract_inverted_index.terms | 42 |
| abstract_inverted_index.time. | 18 |
| abstract_inverted_index.using | 91 |
| abstract_inverted_index.biases | 101 |
| abstract_inverted_index.equity | 135 |
| abstract_inverted_index.gender | 104 |
| abstract_inverted_index.images | 26 |
| abstract_inverted_index.model. | 59 |
| abstract_inverted_index.reveal | 97 |
| abstract_inverted_index.between | 102 |
| abstract_inverted_index.improve | 134 |
| abstract_inverted_index.medical | 137 |
| abstract_inverted_index.methods | 22 |
| abstract_inverted_index.sources | 74, 118 |
| abstract_inverted_index.DL-based | 55, 128 |
| abstract_inverted_index.However, | 30 |
| abstract_inverted_index.analysis | 52, 122 |
| abstract_inverted_index.baseline | 79 |
| abstract_inverted_index.consider | 35 |
| abstract_inverted_index.explores | 70 |
| abstract_inverted_index.fairness | 36, 51, 126 |
| abstract_inverted_index.fidelity | 13 |
| abstract_inverted_index.findings | 96 |
| abstract_inverted_index.insights | 124 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.metrics. | 94 |
| abstract_inverted_index.presence | 72 |
| abstract_inverted_index.presents | 48 |
| abstract_inverted_index.provides | 123 |
| abstract_inverted_index.training | 112 |
| abstract_inverted_index.utilises | 62 |
| abstract_inverted_index.Empirical | 80 |
| abstract_inverted_index.essential | 33 |
| abstract_inverted_index.evaluated | 90 |
| abstract_inverted_index.imbalance | 110 |
| abstract_inverted_index.reduction | 15 |
| abstract_inverted_index.subgroups. | 107 |
| abstract_inverted_index.unfairness | 76 |
| abstract_inverted_index.acquisition | 17 |
| abstract_inverted_index.algorithms, | 39 |
| abstract_inverted_index.demographic | 44 |
| abstract_inverted_index.performance | 88, 100 |
| abstract_inverted_index.rebalancing | 85 |
| abstract_inverted_index.reconstruct | 24 |
| abstract_inverted_index.significant | 99 |
| abstract_inverted_index.strategies. | 86 |
| abstract_inverted_index.Minimisation | 82 |
| abstract_inverted_index.architecture | 65 |
| abstract_inverted_index.high-quality | 25 |
| abstract_inverted_index.implementing | 78 |
| abstract_inverted_index.improvements | 10 |
| abstract_inverted_index.particularly | 4, 40 |
| abstract_inverted_index.undersampled | 28 |
| abstract_inverted_index.Surprisingly, | 108 |
| abstract_inverted_index.applications. | 139 |
| abstract_inverted_index.neuroimaging, | 20 |
| abstract_inverted_index.statistically | 98 |
| abstract_inverted_index.discrimination | 113 |
| abstract_inverted_index.reconstruction | 3, 58, 68, 93, 130 |
| abstract_inverted_index.characteristics. | 45 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/5 |
| sustainable_development_goals[0].score | 0.5699999928474426 |
| sustainable_development_goals[0].display_name | Gender equality |
| citation_normalized_percentile |