FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tian, Yu, Wen, Congcong, Shi, Min, Afzal, Muhammad Muneeb, Huang, Hao, Khan, Muhammad Osama, Luo, Yan, Fang, Yi, Wang, Mengyu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913436479258624
author Tian, Yu
Wen, Congcong
Shi, Min
Afzal, Muhammad Muneeb
Huang, Hao
Khan, Muhammad Osama
Luo, Yan
Fang, Yi
Wang, Mengyu
author_facet Tian, Yu
Wen, Congcong
Shi, Min
Afzal, Muhammad Muneeb
Huang, Hao
Khan, Muhammad Osama
Luo, Yan
Fang, Yi
Wang, Mengyu
contents Addressing fairness in artificial intelligence (AI), particularly in medical AI, is crucial for ensuring equitable healthcare outcomes. Recent efforts to enhance fairness have introduced new methodologies and datasets in medical AI. However, the fairness issue under the setting of domain transfer is almost unexplored, while it is common that clinics rely on different imaging technologies (e.g., different retinal imaging modalities) for patient diagnosis. This paper presents FairDomain, a pioneering systemic study into algorithmic fairness under domain shifts, employing state-of-the-art domain adaptation (DA) and generalization (DG) algorithms for both medical segmentation and classification tasks to understand how biases are transferred between different domains. We also introduce a novel plug-and-play fair identity attention (FIA) module that adapts to various DA and DG algorithms to improve fairness by using self-attention to adjust feature importance based on demographic attributes. Additionally, we curate the first fairness-focused dataset with two paired imaging modalities for the same patient cohort on medical segmentation and classification tasks, to rigorously assess fairness in domain-shift scenarios. Excluding the confounding impact of demographic distribution variation between source and target domains will allow clearer quantification of the performance of domain transfer models. Our extensive evaluations reveal that the proposed FIA significantly enhances both model performance accounted for fairness across all domain shift settings (i.e., DA and DG) with respect to different demographics, which outperforms existing methods on both segmentation and classification. The code and data can be accessed at https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08813
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification
Tian, Yu
Wen, Congcong
Shi, Min
Afzal, Muhammad Muneeb
Huang, Hao
Khan, Muhammad Osama
Luo, Yan
Fang, Yi
Wang, Mengyu
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Addressing fairness in artificial intelligence (AI), particularly in medical AI, is crucial for ensuring equitable healthcare outcomes. Recent efforts to enhance fairness have introduced new methodologies and datasets in medical AI. However, the fairness issue under the setting of domain transfer is almost unexplored, while it is common that clinics rely on different imaging technologies (e.g., different retinal imaging modalities) for patient diagnosis. This paper presents FairDomain, a pioneering systemic study into algorithmic fairness under domain shifts, employing state-of-the-art domain adaptation (DA) and generalization (DG) algorithms for both medical segmentation and classification tasks to understand how biases are transferred between different domains. We also introduce a novel plug-and-play fair identity attention (FIA) module that adapts to various DA and DG algorithms to improve fairness by using self-attention to adjust feature importance based on demographic attributes. Additionally, we curate the first fairness-focused dataset with two paired imaging modalities for the same patient cohort on medical segmentation and classification tasks, to rigorously assess fairness in domain-shift scenarios. Excluding the confounding impact of demographic distribution variation between source and target domains will allow clearer quantification of the performance of domain transfer models. Our extensive evaluations reveal that the proposed FIA significantly enhances both model performance accounted for fairness across all domain shift settings (i.e., DA and DG) with respect to different demographics, which outperforms existing methods on both segmentation and classification. The code and data can be accessed at https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k.
title FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.08813