English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fairness in artificial intelligence models has gained significantly moreattention in recent years, especially in the area of medicine, as fairness inmedical models is critical to people's well-being and lives. High-qualitymedical fairness datasets are needed to promote fairness learning research.Existing medical fairness datasets are all for classification tasks, and nofairness datasets are available for medical segmentation, while medicalsegmentation is an equally important clinical task as classifications, whichcan provide detailed spatial information on organ abnormalities ready to beassessed by clinicians. In this paper, we propose the first fairness datasetfor medical segmentation named Harvard-FairSeg with 10,000 subject samples. Inaddition, we propose a fair error-bound scaling approach to reweight the lossfunction with the upper error-bound in each identity group, using the segmentanything model (SAM). We anticipate that the segmentation performance equitycan be improved by explicitly tackling the hard cases with high training errorsin each identity group. To facilitate fair comparisons, we utilize a novelequity-scaled segmentation performance metric to compare segmentation metricsin the context of fairness, such as the equity-scaled Dice coefficient. Throughcomprehensive experiments, we demonstrate that our fair error-bound scalingapproach either has superior or comparable fairness performance to thestate-of-the-art fairness learning models. The dataset and code are publiclyaccessible via https://ophai.hms.harvard.edu/harvard-fairseg10k.

Harvard FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling