aiqbench analysis
This research introduces the Mixture of Multicenter Experts (MoME) framework, which leverages Mixture of Experts architectures to mitigate bias in medical AI without requiring sensitive cross-institutional data sharing. By integrating specialized expertise from diverse clinical protocols, the model demonstrates superior generalizability in multimodal prostate cancer radiotherapy tasks under conditions of high variability or limited data. The approach offers a viable path toward equitable and adaptable medical AI systems that respect local clinical preferences while maintaining broad applicability.
Mixture of Multicenter Experts in Multimodal AI for Debiased Radiotherapy Target Delineation
arXiv:2410.00046v4 Announce Type: replace-cross Abstract: Clinical decision-making reflects diverse strategies shaped by regional patient populations and institutional protocols. However, most existing medical artificial intelligence (AI) models are trained on highly prevalent data patterns, which reinforces biases and fails to capture the breadth of clinical expertise. Inspired by the recent advances in Mixture of Experts (MoE), we propose a Mixture of Multicenter Experts (MoME) framework to address AI bias in the medical domain without requiring data sharing across institutions. MoME integrates specialized expertise from diverse clinical strategies to enhance model generalizability and adaptability across medical centers. We validate this framework using a multimodal target volume delineation model for prostate cancer radiotherapy. With few-shot training that combines imaging and clinical notes from each center, the model outperformed baselines, particularly in settings with high inter-center variability or limited data availability. Furthermore, MoME enables model customization to local clinical preferences without cross-institutional data exchange, making it especially suitable for resource-constrained settings while promoting broadly generalizable medical AI.
Abstract:Clinical decision-making reflects diverse strategies shaped by regional patient populations and institutional protocols. However, most existing medical artificial intelligence (AI) models are trained on highly prevalent data patterns, which reinforces biases and fails to capture the breadth of clinical expertise. Inspired by the recent advances in Mixture of Experts (MoE), we propose a Mixture of Multicenter Experts (MoME) framework to address AI bias in the medical domain without requiring data sharing across institutions. MoME integrates specialized expertise from diverse clinical strategies to enhance model generalizability and adaptability across medical centers. We validate this framework using a multimodal target volume delineation model for prostate cancer radiotherapy. With few-shot training that combines imaging and clinical notes from each center, the model outperformed baselines, particularly in settings with high inter-center variability or limited data availability. Furthermore, MoME enables model customization to local clinical preferences without cross-institutional data exchange, making it especially suitable for resource-constrained settings while promoting broadly generalizable medical AI.
Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2410.00046 [eess.IV]
(or arXiv:2410.00046v4 [eess.IV] for this version)
https://doi.org/10.48550/arXiv.2410.00046 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 261 words
Related coverage
Introducing Gemma 4 models on Amazon Bedrock
AWS · Jun 15, 2026
Complete Guide to Thinking Machines Inkling
Analytics Vidhya · Jul 20, 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
arXiv · Oct 15, 2026