Paper Detail

Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging

Johannes Kaiser, Florian Braunmiller, Daniel Rückert, Georgios Kaissis

arxiv Score 9.8

Published 2026-09-16 · First seen 2026-09-17

General AI

Abstract

AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (MoE) architectures currently fail to satisfy. Expert-based routing improves in-domain learning but may sacrifice cross-modal signals, which appear particularly important for rare (low-prevalence) pathologies in our experiments. To resolve this, we introduce Generalist-Specialist-MoE (GS-MoE), a two-branch (MoE) architecture that couples a cross-modal generalist model with distinct modality-specific specialists (experts) via domain-constrained feature fusion. On RadImageNet (1.35M images, 165 pathologies, three modalities), GS-MoE recovers detection of six low-prevalence pathologies on which every baseline scores F1 $=$ 0, with per-class gains up to +0.60 F1. It attains this while even slightly exceeding dense and specialist-only MoE aggregate baselines (MCC 0.770), while using ${\sim}53\%$ fewer active parameters at inference than the strongest investigated dense model.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{kaiser2026generalist,
  title = {Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging},
  author = {Johannes Kaiser and Florian Braunmiller and Daniel Rückert and Georgios Kaissis},
  year = {2026},
  abstract = {AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure Mixture-of-Experts (MoE) architectures currently fail to satisfy. Expert-based routing improves in-domain learning but may sacrifice cross-modal signals, which appear particularly important for rare (low-prevalence) pathologies in our experiments. To resolve this, we introduce Generalist-Specialist-MoE (GS-MoE), a two-branch (MoE) architecture that},
  url = {https://arxiv.org/abs/2609.18688},
  keywords = {cs.CV, cs.AI},
  eprint = {2609.18688},
  archiveprefix = {arXiv},
}

Metadata

{}