Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Zhaorui, Yang, Xi, Pan, Tan, Liu, Tianyi, Jiang, Chen, Guo, Xin, Wang, Qiufeng, Nguyen, Anh, Qi, Yuan, Huang, Kaizhu, Cheng, Yuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912498653855744
author Tan, Zhaorui
Yang, Xi
Pan, Tan
Liu, Tianyi
Jiang, Chen
Guo, Xin
Wang, Qiufeng
Nguyen, Anh
Qi, Yuan
Huang, Kaizhu
Cheng, Yuan
author_facet Tan, Zhaorui
Yang, Xi
Pan, Tan
Liu, Tianyi
Jiang, Chen
Guo, Xin
Wang, Qiufeng
Nguyen, Anh
Qi, Yuan
Huang, Kaizhu
Cheng, Yuan
contents Variations in medical imaging modalities and individual anatomical differences pose challenges to cross-modality generalization in multi-modal tasks. Existing methods often concentrate exclusively on common anatomical patterns, thereby neglecting individual differences and consequently limiting their generalization performance. This paper emphasizes the critical role of learning individual-level invariance, i.e., personalized representation $\mathbb{X}_h$, to enhance multi-modality generalization under both homogeneous and heterogeneous settings. It reveals that mappings from individual biological profile to different medical modalities remain static across the population, which is implied in the personalization process. We propose a two-stage approach: pre-training with invariant representation $\mathbb{X}_h$ for personalization, then fine-tuning for diverse downstream tasks. We provide both theoretical and empirical evidence demonstrating the feasibility and advantages of personalization, showing that our approach yields greater generalizability and transferability across diverse multi-modal medical tasks compared to methods lacking personalization. Extensive experiments further validate that our approach significantly enhances performance in various generalization scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation
Tan, Zhaorui
Yang, Xi
Pan, Tan
Liu, Tianyi
Jiang, Chen
Guo, Xin
Wang, Qiufeng
Nguyen, Anh
Qi, Yuan
Huang, Kaizhu
Cheng, Yuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Variations in medical imaging modalities and individual anatomical differences pose challenges to cross-modality generalization in multi-modal tasks. Existing methods often concentrate exclusively on common anatomical patterns, thereby neglecting individual differences and consequently limiting their generalization performance. This paper emphasizes the critical role of learning individual-level invariance, i.e., personalized representation $\mathbb{X}_h$, to enhance multi-modality generalization under both homogeneous and heterogeneous settings. It reveals that mappings from individual biological profile to different medical modalities remain static across the population, which is implied in the personalization process. We propose a two-stage approach: pre-training with invariant representation $\mathbb{X}_h$ for personalization, then fine-tuning for diverse downstream tasks. We provide both theoretical and empirical evidence demonstrating the feasibility and advantages of personalization, showing that our approach yields greater generalizability and transferability across diverse multi-modal medical tasks compared to methods lacking personalization. Extensive experiments further validate that our approach significantly enhances performance in various generalization scenarios.
title Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.06106