Unlearning Spurious Correlations in Chest X-ray Classification Article Swipe
Misgina Tsighe Hagos
,
Kathleen M. Curran
,
Brian Mac Namee
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2308.01119
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2308.01119
Medical image classification models are frequently trained using training datasets derived from multiple data sources. While leveraging multiple data sources is crucial for achieving model generalization, it is important to acknowledge that the diverse nature of these sources inherently introduces unintended confounders and other challenges that can impact both model accuracy and transparency. A notable confounding factor in medical image classification, particularly in musculoskeletal image classification, is skeletal maturation-induced bone growth observed during adolescence. We train a deep learning model using a Covid-19 chest X-ray dataset and we showcase how this dataset can lead to spurious correlations due to unintended confounding regions. eXplanation Based Learning (XBL) is a deep learning approach that goes beyond interpretability by utilizing model explanations to interactively unlearn spurious correlations. This is achieved by integrating interactive user feedback, specifically feature annotations. In our study, we employed two non-demanding manual feedback mechanisms to implement an XBL-based approach for effectively eliminating these spurious correlations. Our results underscore the promising potential of XBL in constructing robust models even in the presence of confounding factors.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2308.01119
- https://arxiv.org/pdf/2308.01119
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385952709
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385952709Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2308.01119Digital Object Identifier
- Title
-
Unlearning Spurious Correlations in Chest X-ray ClassificationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-08-02Full publication date if available
- Authors
-
Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac NameeList of authors in order
- Landing page
-
https://arxiv.org/abs/2308.01119Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2308.01119Direct 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/2308.01119Direct OA link when available
- Concepts
-
Spurious relationship, Interpretability, Confounding, Computer science, Artificial intelligence, Machine learning, Feature (linguistics), Generalization, Statistics, Mathematics, Linguistics, Philosophy, Mathematical analysisTop 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/W4385952709 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2308.01119 |
| ids.doi | https://doi.org/10.48550/arxiv.2308.01119 |
| ids.openalex | https://openalex.org/W4385952709 |
| fwci | |
| type | preprint |
| title | Unlearning Spurious Correlations in Chest X-ray Classification |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11775 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9933000206947327 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2741 |
| topics[0].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[0].display_name | COVID-19 diagnosis using AI |
| topics[1].id | https://openalex.org/T13702 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9721999764442444 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Machine Learning in Healthcare |
| topics[2].id | https://openalex.org/T11636 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9690999984741211 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2718 |
| topics[2].subfield.display_name | Health Informatics |
| topics[2].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C97256817 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9574995040893555 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1462316 |
| concepts[0].display_name | Spurious relationship |
| concepts[1].id | https://openalex.org/C2781067378 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8863914608955383 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q17027399 |
| concepts[1].display_name | Interpretability |
| concepts[2].id | https://openalex.org/C77350462 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7023608088493347 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1125472 |
| concepts[2].display_name | Confounding |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.6555472612380981 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5984847545623779 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5883783102035522 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C2776401178 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5317133069038391 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[6].display_name | Feature (linguistics) |
| concepts[7].id | https://openalex.org/C177148314 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5291355848312378 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[7].display_name | Generalization |
| concepts[8].id | https://openalex.org/C105795698 |
| concepts[8].level | 1 |
| concepts[8].score | 0.1336587369441986 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[8].display_name | Statistics |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.12196621298789978 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C134306372 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[12].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/spurious-relationship |
| keywords[0].score | 0.9574995040893555 |
| keywords[0].display_name | Spurious relationship |
| keywords[1].id | https://openalex.org/keywords/interpretability |
| keywords[1].score | 0.8863914608955383 |
| keywords[1].display_name | Interpretability |
| keywords[2].id | https://openalex.org/keywords/confounding |
| keywords[2].score | 0.7023608088493347 |
| keywords[2].display_name | Confounding |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.6555472612380981 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5984847545623779 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.5883783102035522 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/feature |
| keywords[6].score | 0.5317133069038391 |
| keywords[6].display_name | Feature (linguistics) |
| keywords[7].id | https://openalex.org/keywords/generalization |
| keywords[7].score | 0.5291355848312378 |
| keywords[7].display_name | Generalization |
| keywords[8].id | https://openalex.org/keywords/statistics |
| keywords[8].score | 0.1336587369441986 |
| keywords[8].display_name | Statistics |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.12196621298789978 |
| keywords[9].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2308.01119 |
| 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/2308.01119 |
| 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/2308.01119 |
| locations[1].id | doi:10.48550/arxiv.2308.01119 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2308.01119 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5058624041 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9318-9417 |
| authorships[0].author.display_name | Misgina Tsighe Hagos |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hagos, Misgina Tsighe |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5031311803 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0095-9337 |
| authorships[1].author.display_name | Kathleen M. Curran |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Curran, Kathleen M. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5084251444 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2518-0274 |
| authorships[2].author.display_name | Brian Mac Namee |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Mac Namee, Brian |
| authorships[2].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/2308.01119 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unlearning Spurious Correlations in Chest X-ray Classification |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11775 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9933000206947327 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2741 |
| primary_topic.subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| primary_topic.display_name | COVID-19 diagnosis using AI |
| related_works | https://openalex.org/W2905433371, https://openalex.org/W4390569940, https://openalex.org/W2888392564, https://openalex.org/W4310278675, https://openalex.org/W4388422664, https://openalex.org/W4361193272, https://openalex.org/W3113091479, https://openalex.org/W2162899405, https://openalex.org/W2963326959, https://openalex.org/W941090075 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2308.01119 |
| 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/2308.01119 |
| 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/2308.01119 |
| primary_location.id | pmh:oai:arXiv.org:2308.01119 |
| 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/2308.01119 |
| 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/2308.01119 |
| publication_date | 2023-08-02 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 53 |
| abstract_inverted_index.a | 76, 81, 107 |
| abstract_inverted_index.In | 135 |
| abstract_inverted_index.We | 74 |
| abstract_inverted_index.an | 147 |
| abstract_inverted_index.by | 115, 127 |
| abstract_inverted_index.in | 57, 62, 164, 169 |
| abstract_inverted_index.is | 20, 27, 66, 106, 125 |
| abstract_inverted_index.it | 26 |
| abstract_inverted_index.of | 35, 162, 172 |
| abstract_inverted_index.to | 29, 94, 98, 119, 145 |
| abstract_inverted_index.we | 87, 138 |
| abstract_inverted_index.Our | 156 |
| abstract_inverted_index.XBL | 163 |
| abstract_inverted_index.and | 42, 51, 86 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 46, 92 |
| abstract_inverted_index.due | 97 |
| abstract_inverted_index.for | 22, 150 |
| abstract_inverted_index.how | 89 |
| abstract_inverted_index.our | 136 |
| abstract_inverted_index.the | 32, 159, 170 |
| abstract_inverted_index.two | 140 |
| abstract_inverted_index.This | 124 |
| abstract_inverted_index.bone | 69 |
| abstract_inverted_index.both | 48 |
| abstract_inverted_index.data | 13, 18 |
| abstract_inverted_index.deep | 77, 108 |
| abstract_inverted_index.even | 168 |
| abstract_inverted_index.from | 11 |
| abstract_inverted_index.goes | 112 |
| abstract_inverted_index.lead | 93 |
| abstract_inverted_index.that | 31, 45, 111 |
| abstract_inverted_index.this | 90 |
| abstract_inverted_index.user | 130 |
| abstract_inverted_index.(XBL) | 105 |
| abstract_inverted_index.Based | 103 |
| abstract_inverted_index.While | 15 |
| abstract_inverted_index.X-ray | 84 |
| abstract_inverted_index.chest | 83 |
| abstract_inverted_index.image | 1, 59, 64 |
| abstract_inverted_index.model | 24, 49, 79, 117 |
| abstract_inverted_index.other | 43 |
| abstract_inverted_index.these | 36, 153 |
| abstract_inverted_index.train | 75 |
| abstract_inverted_index.using | 7, 80 |
| abstract_inverted_index.beyond | 113 |
| abstract_inverted_index.during | 72 |
| abstract_inverted_index.factor | 56 |
| abstract_inverted_index.growth | 70 |
| abstract_inverted_index.impact | 47 |
| abstract_inverted_index.manual | 142 |
| abstract_inverted_index.models | 3, 167 |
| abstract_inverted_index.nature | 34 |
| abstract_inverted_index.robust | 166 |
| abstract_inverted_index.study, | 137 |
| abstract_inverted_index.Medical | 0 |
| abstract_inverted_index.crucial | 21 |
| abstract_inverted_index.dataset | 85, 91 |
| abstract_inverted_index.derived | 10 |
| abstract_inverted_index.diverse | 33 |
| abstract_inverted_index.feature | 133 |
| abstract_inverted_index.medical | 58 |
| abstract_inverted_index.notable | 54 |
| abstract_inverted_index.results | 157 |
| abstract_inverted_index.sources | 19, 37 |
| abstract_inverted_index.trained | 6 |
| abstract_inverted_index.unlearn | 121 |
| abstract_inverted_index.Covid-19 | 82 |
| abstract_inverted_index.Learning | 104 |
| abstract_inverted_index.accuracy | 50 |
| abstract_inverted_index.achieved | 126 |
| abstract_inverted_index.approach | 110, 149 |
| abstract_inverted_index.datasets | 9 |
| abstract_inverted_index.employed | 139 |
| abstract_inverted_index.factors. | 174 |
| abstract_inverted_index.feedback | 143 |
| abstract_inverted_index.learning | 78, 109 |
| abstract_inverted_index.multiple | 12, 17 |
| abstract_inverted_index.observed | 71 |
| abstract_inverted_index.presence | 171 |
| abstract_inverted_index.regions. | 101 |
| abstract_inverted_index.showcase | 88 |
| abstract_inverted_index.skeletal | 67 |
| abstract_inverted_index.sources. | 14 |
| abstract_inverted_index.spurious | 95, 122, 154 |
| abstract_inverted_index.training | 8 |
| abstract_inverted_index.XBL-based | 148 |
| abstract_inverted_index.achieving | 23 |
| abstract_inverted_index.feedback, | 131 |
| abstract_inverted_index.implement | 146 |
| abstract_inverted_index.important | 28 |
| abstract_inverted_index.potential | 161 |
| abstract_inverted_index.promising | 160 |
| abstract_inverted_index.utilizing | 116 |
| abstract_inverted_index.challenges | 44 |
| abstract_inverted_index.frequently | 5 |
| abstract_inverted_index.inherently | 38 |
| abstract_inverted_index.introduces | 39 |
| abstract_inverted_index.leveraging | 16 |
| abstract_inverted_index.mechanisms | 144 |
| abstract_inverted_index.underscore | 158 |
| abstract_inverted_index.unintended | 40, 99 |
| abstract_inverted_index.acknowledge | 30 |
| abstract_inverted_index.confounders | 41 |
| abstract_inverted_index.confounding | 55, 100, 173 |
| abstract_inverted_index.eXplanation | 102 |
| abstract_inverted_index.effectively | 151 |
| abstract_inverted_index.eliminating | 152 |
| abstract_inverted_index.integrating | 128 |
| abstract_inverted_index.interactive | 129 |
| abstract_inverted_index.adolescence. | 73 |
| abstract_inverted_index.annotations. | 134 |
| abstract_inverted_index.constructing | 165 |
| abstract_inverted_index.correlations | 96 |
| abstract_inverted_index.explanations | 118 |
| abstract_inverted_index.particularly | 61 |
| abstract_inverted_index.specifically | 132 |
| abstract_inverted_index.correlations. | 123, 155 |
| abstract_inverted_index.interactively | 120 |
| abstract_inverted_index.non-demanding | 141 |
| abstract_inverted_index.transparency. | 52 |
| abstract_inverted_index.classification | 2 |
| abstract_inverted_index.classification, | 60, 65 |
| abstract_inverted_index.generalization, | 25 |
| abstract_inverted_index.musculoskeletal | 63 |
| abstract_inverted_index.interpretability | 114 |
| abstract_inverted_index.maturation-induced | 68 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |