---
title: "PANDA：面向部分未配对多模态学习的原型锚定对齐方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25970v1"
permalink: "https://feed.astralor.com/items/itm_74f2a5d3a5cd8fc6f40cd52c"
published: "2026-08-26T16:28:20.000Z"
score: 72
channel: "ai"
tags: ["PANDA","医学影像","原型对齐","多模态学习"]
---

# PANDA：面向部分未配对多模态学习的原型锚定对齐方法

## AI 点评

> PANDA 将多模态对齐从样本级提升到类原型级，使得完全无配对的外部模态也能参与训练，这对医学场景中数据稀缺且部署受限的问题很有价值。对于多模态学习和医学影像 AI 研究者，这是一个值得尝试的训练范式。

## 速览

PANDA 提出一种两阶段框架，用于解决多模态医学预测中辅助模态配对不完整的问题。第一阶段在配对子集上学习共享嵌入，并从辅助模态估计类别原型；第二阶段仅用主模态编码器在所有受试者上训练，通过交叉熵与原型对齐。该方法支持任意配对率，推理时无需辅助输入。在 ADNI 数据集上将 MRI 基线 AUC 提升 7.9 个百分点，在 TCGA-Lung 生存预测中优于全融合训练。

## 关键点

- 提出 PANDA 框架，通过类原型对齐实现部分未配对多模态学习，推理时无需辅助模态。
- 在 ADNI 队列上，PANDA 将 MRI-only 基线 AUC 提升 7.9 个百分点，并显著降低 1.5T 扫描的假阳性率。
- 在 TCGA-Lung 生存预测中，PANDA 优于全融合训练，且推理时不需要 RNA-seq 数据。
- 方法支持任意配对率，包括零配对，具备较强的部署适应性。

## 全文

Multimodal medical prediction often faces incomplete pairing: auxiliary modalities with complementary signal are available for only a subset of subjects (or none) and cannot be assumed at deployment. We introduce PANDA (Prototype Anchored Data Alignment), a two-stage framework that transfers auxiliary information to a primary-modality model without auxiliary inputs at inference. Stage 1 learns a shared embedding from the paired subset and estimates class prototypes from auxiliary modalities; Stage 2 trains the primary encoder on all subjects using cross-entropy plus alignment to the frozen prototypes. Because supervision is defined at the class-prototype level, PANDA accommodates arbitrary pairing rates, including zero subject overlap. We evaluate PANDA on two applications. On a 1,021-subject multi-scanner ADNI cohort, we perform AD/CN classification with three auxiliary modalities at distinct pairing rates: tabular scores (44.8%), FDG-PET (18.7%), and external handwriting kinematics (0% overlap). Relative to the same-backbone MRI-only baseline, PANDA attains AUC 0.868 +-0.020 (+7.9pp) and reduces 1.5T CN false positives by 24.3pp; on a fully trainable Conv5-FC3 backbone it reaches AUC 0.893 (best overall). A pairing-rate ablation shows that the joint anchor remains within seed noise from 75% to 5% pairing. On TCGA-Lung survival prediction from whole-slide images with RNA-seq as auxiliary data, PANDA improves over WSI-only on 2-year OS (AUC +3.5pp) and Cox PH (C-index +9.0pts) and outperforms full-fusion training, which underperforms WSI-only, while requiring no RNA at inference; wide confidence intervals on this smaller cohort keep the gains below conventional significance. Overall, PANDA provides a deployment-oriented mechanism for leveraging incomplete auxiliary modalities to improve primary-modality prediction.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_74f2a5d3a5cd8fc6f40cd52c