Rui Sun

Achieving flexible fairness metrics in federated medical imaging

The rapid adoption of Artificial Intelligence (AI) in medical imaging raises fairness and privacy concerns across demographic groups, especially in diagnosis and treatment decisions. While federated learning (FL) offers decentralized privacy preservation, current frameworks often prioritize collaboration fairness over group fairness, risking healthcare disparities. Here we present FlexFair, an innovative FL framework designed to address both fairness and privacy challenges. FlexFair incorporates a flexible regularization term to facilitate the integration of multiple fairness criteria, including equal accuracy, demographic parity, and equal opportunity. Evaluated across four clinical applications (polyp segmentation, fundus vascular segmentation, cervical cancer segmentation, and skin disease diagnosis), FlexFair outperforms state-of-the-art methods in both fairness and accuracy. Moreover, we curate a multi-center dataset for cervical cancer segmentation that includes 678 patients from four hospitals. This diverse dataset allows for a more comprehensive analysis of model performance across different population groups, ensuring the findings are applicable to a broader range of patients.

Diagnostic accuracy of serum human epididymis protein 4 in ovarian cancer patients with different ethnic groups and menopausal status: a meta-analysis and systematic evaluation

We aimed to analyze and evaluate the diagnostic value of serum human epididymis protein 4 (HE4) in ovarian cancer (OC) of patients with different menopausal status. A comprehensive electronic and manual search of the relevant literature was performed through several databases such as CNKI, Wanfang database, VIP database, Chinese biomedical database, web of science, PubMed, EMBASE, and Cochrane database. We collected Chinese and English articles to assess the diagnostic value of HE4 for ovarian cancer in female with different menopausal status. The quality of the studies included in the systematic review was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. A total of 14 publications were included in this study and we didn't find publication bias in them. The sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of HE4 for the diagnosis of ovarian cancer in postmenopausal vs premenopausal female were 0.71 (95% CI, 0.63-0.78) vs 0.78 (95% CI, 0.74-0.81); 0.91 (95% CI, 0.85-0.95) vs 0.90 (95% CI, 0.86-0.93); 11.90 (95% CI, 6.42-22.07) vs 11.03 (95% CI, 6.44-18.89); and 0.30 (95% CI, 0.22-0.39) vs 0.24 (95% CI, 0.20-0.29), respectively. Serum HE4 has greater diagnostic value in detecting ovarian cancer, especially in Asian postmenopausal female.