Random Token Fusion for Multi-View Medical Diagnosis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Jingyu, Matsoukas, Christos, Strand, Fredrik, Smith, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910658152366080
author Guo, Jingyu
Matsoukas, Christos
Strand, Fredrik
Smith, Kevin
author_facet Guo, Jingyu
Matsoukas, Christos
Strand, Fredrik
Smith, Kevin
contents In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on view-specific features, which can lead to trivial solutions. In this work, we introduce Random Token Fusion (RTF), a novel technique designed to enhance multi-view medical image analysis using vision transformers. By integrating randomness into the feature fusion process during training, RTF addresses the issue of overfitting and enhances the robustness and accuracy of diagnostic models without incurring any additional cost at inference. We validate our approach on standard mammography and chest X-ray benchmark datasets. Through extensive experiments, we demonstrate that RTF consistently improves the performance of existing fusion methods, paving the way for a new generation of multi-view medical foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15847
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Random Token Fusion for Multi-View Medical Diagnosis
Guo, Jingyu
Matsoukas, Christos
Strand, Fredrik
Smith, Kevin
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on view-specific features, which can lead to trivial solutions. In this work, we introduce Random Token Fusion (RTF), a novel technique designed to enhance multi-view medical image analysis using vision transformers. By integrating randomness into the feature fusion process during training, RTF addresses the issue of overfitting and enhances the robustness and accuracy of diagnostic models without incurring any additional cost at inference. We validate our approach on standard mammography and chest X-ray benchmark datasets. Through extensive experiments, we demonstrate that RTF consistently improves the performance of existing fusion methods, paving the way for a new generation of multi-view medical foundation models.
title Random Token Fusion for Multi-View Medical Diagnosis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.15847