HyperPriv-EPN: Hypergraph Learning with Privileged Knowledge for Ependymoma Prognosis

TL;DR

HyperPriv-EPN introduces a hypergraph learning framework that leverages privileged post-surgery information during training to improve preoperative prognosis of Ependymoma from MRI data, achieving state-of-the-art results.

Contribution

It proposes a novel hypergraph-based LUPI framework with a Severed Graph Strategy and dual-stream distillation to transfer expert knowledge from post-operative data to preoperative diagnosis.

Findings

Achieves state-of-the-art diagnostic accuracy.

Improves survival stratification.

Effectively transfers expert knowledge to preoperative setting.

Abstract

Preoperative prognosis of Ependymoma is critical for treatment planning but challenging due to the lack of semantic insights in MRI compared to post-operative surgical reports. Existing multimodal methods fail to leverage this privileged text data when it is unavailable during inference. To bridge this gap, we propose HyperPriv-EPN, a hypergraph-based Learning Using Privileged Information (LUPI) framework. We introduce a Severed Graph Strategy, utilizing a shared encoder to process both a Teacher graph (enriched with privileged post-surgery information) and a Student graph (restricted to pre-operation data). Through dual-stream distillation, the Student learns to hallucinate semantic community structures from visual features alone. Validated on a multi-center cohort of 311 patients, HyperPriv-EPN achieves state-of-the-art diagnostic accuracy and survival stratification. This effectively transfers expert knowledge to the preoperative setting, unlocking the value of historical post-operative data to guide the diagnosis of new patients without requiring text at inference.