Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Shuren Gabriel, Ren, Sikang, Tian, Yongji
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.00626
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918269426860032
author Yu, Shuren Gabriel
Ren, Sikang
Tian, Yongji
author_facet Yu, Shuren Gabriel
Ren, Sikang
Tian, Yongji
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00626
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperPriv-EPN: Hypergraph Learning with Privileged Knowledge for Ependymoma Prognosis
Yu, Shuren Gabriel
Ren, Sikang
Tian, Yongji
Computer Vision and Pattern Recognition
Machine Learning
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.
title HyperPriv-EPN: Hypergraph Learning with Privileged Knowledge for Ependymoma Prognosis
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2601.00626