{"doi":"10.1117/1.jmi.9.6.061102","title":"Fairness-related performance and explainability effects in deep learning models for brain image analysis","abstract":null,"journal":"Journal of Medical Imaging","year":2022,"id":605153,"datarank":0.5641800173540344,"base_score":3.7612001156935624,"endowment":3.7612001156935624,"self_citation_contribution":0.5641800173540344,"citation_network_contribution":0.0,"self_endowment_contribution":0.5641800173540344,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":42,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":475750,"name":"Matthias Wilms","orcid":"0000-0001-8845-360X","position":1,"is_corresponding":false},{"id":1553018,"name":"Pauline Mouches","orcid":null,"position":2,"is_corresponding":false},{"id":268017,"name":"Nils D. Forkert","orcid":"0000-0003-2556-3224","position":3,"is_corresponding":false},{"id":1216092,"name":"Emma A. M. Stanley","orcid":"0000-0002-7802-6820","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Fairness-related performance and explainability effects in deep learning models for brain image analysis","abstract":"Purpose: Explainability and fairness are two key factors for the effective and ethical clinical implementation of deep learning-based machine learning models in healthcare settings. However, there has been limited work on investigating how unfair performance manifests in explainable artificial intelligence (XAI) methods, and how XAI can be used to investigate potential reasons for unfairness. Thus, the aim of this work was to analyze the effects of previously established sociodemographic-related confounders on classifier performance and explainability methods.Approach: A convolutional neural network (CNN) was trained to predict biological sex from T1-weighted brain MRI datasets of 4547 9- to 10-year-old adolescents from the Adolescent Brain Cognitive Development study. Performance disparities of the trained CNN between White and Black subjects were analyzed and saliency maps were generated for each subgroup at the intersection of sex and race.Results: The classification model demonstrated a significant difference in the percentage of correctly classified White male (90.3 % ± 1.7 % ) and Black male (81.1 % ± 4.5 % ) children. Conversely, slightly higher performance was found for Black female (89.3 % ± 4.8 % ) compared with White female (86.5 % ± 2.0 % ) children. Saliency maps showed subgroup-specific differences, corresponding to brain regions previously associated with pubertal development. In line with this finding, average pubertal development scores of subjects used in this study were significantly different between Black and White females (p < 0.001) and males (p < 0.001).Conclusions: We demonstrate that a CNN with significantly different sex classification performance between Black and White adolescents can identify different important brain regions when comparing subgroup saliency maps. Importance scores vary substantially between subgroups within brain structures associated with pubertal development, a race-associated confounder for predicting sex. We illustrate that unfair models can produce different XAI results between subgroups and that these results may explain potential reasons for biased performance.","is_dataset_classified":null,"base_score":3.7612001156935624,"endowment":3.7612001156935624,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"36046104","pmcid":"PMC9412191","openalex_id":"https://openalex.org/W4293199589","authors":[],"funders":[{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041134","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA050987","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA051039","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041028","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041048","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041120","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041156","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA050988","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA051037","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041022","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041093","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041174","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA050989","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA051016","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U24 DA041147","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041025","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041117","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041089","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA051018","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA051038","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U24 DA041123","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041106","title":null},{"funder_name":"NIDA NIH HHS","grant_id":"U01 DA041148","title":null}],"total_grants":23,"fwci":4.4091,"citation_percentile":0.95102242,"influential_citations":0,"citation_trend":[{"year":2022,"count":1},{"year":2023,"count":9},{"year":2024,"count":11},{"year":2025,"count":17},{"year":2026,"count":4}],"oa_status":"green","license":null,"oa_locations":[{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9412191","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9412191","host_type":"repository"},{"url":"https://www.spiedigitallibrary.org/journalArticle/Download?urlId=10.1117%2F1.JMI.9.6.061102","host_type":"publisher"},{"url":"https://doi.org/10.1117/1.jmi.9.6.061102","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/36046104","host_type":"repository"}],"fields_of_study":["Explainable Artificial Intelligence (XAI)","Artificial Intelligence in Healthcare and Education","Meta-analysis and systematic reviews"],"mesh_terms":[],"keywords":["Medicine","Convolutional neural network","Confounding","White matter","Cognition","Classifier (UML)","Artificial intelligence","Subgroup analysis","Race (biology)","Magnetic resonance imaging","Internal medicine","Psychiatry","Radiology","Computer science","Bias","Machine Learning","Fairness","Explainable Artificial Intelligence","Adolescent Brain Cognitive Development Study"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"doi"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-07-30T01:47:02.488262Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}