---
title: "GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences"
authors:
  - "Pengfei Song"
  - "Fangjin Liu"
  - "Wenwen Zeng"
  - "Yonghuang Wu"
  - "Chengqian Zhao"
  - "Feiyu Yin"
  - "Xuan Xie"
  - "Jinhua Yu"
doi: "10.24963/ijcai.2026/765"
url: "https://ijcai.org/proceedings/2026/765"
pdf: "https://ijcai.org/proceedings/2026/0765.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6877-6885"
track: "AI and Health"
keywords:
  - "Medical diagnosis: Medical diagnosis"
  - "Medical imaging: Medical imaging"
  - "Precision medicine: Precision medicine"
---

# GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences

Pengfei Song, Fangjin Liu, Wenwen Zeng, Yonghuang Wu, Chengqian Zhao, Feiyu Yin, Xuan Xie, Jinhua Yu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6877-6885. DOI: [10.24963/ijcai.2026/765](https://doi.org/10.24963/ijcai.2026/765)

## Abstract

Contemporary glioma diagnosis integrates molecular features with histopathology to guide clinical decision-making. However, in clinical settings, divergent imaging protocols result in incomplete MRI sequences, leading to two primary challenges: forcing existing frameworks to discard a large portion of clinical data during training and consequently limiting their clinical applicability. To address these limitations, we propose GMENet, a Generative Mixture of Experts Network for multi-center glioma diagnosis with incomplete imaging sequences. Firstly, we design a Cross-attention-based Gated Generation Module that synthesizes missing sequence features from available sequences via cross-attention and dynamic gating mechanisms, incorporating a cycle-consistency loss to preserve semantic integrity. Secondly, we introduce a Dynamically Weighted Experts Fusion Module that performs mixture-of-experts interaction and confidence-aware fusion over original and synthesized dual-sequence features for multi-task prediction. We evaluate GMENet on a multi-center cohort of 1,241 subjects from four in-house datasets and two public repositories. Experiments show that GMENet expands clinically usable training data by 97%, relative to complete-sequence-only data. Furthermore, it consistently outperforms state-of-the-art methods trained on complete data, demonstrating improved robustness under cross-center distribution shifts. Code is available at: https://github.com/spf-sd/GMENet.