A Large-scale Medical Visual Task Adaptation Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mo, Shentong, Luo, Xufang, Wang, Yansen, Li, Dongsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917645202227200
author Mo, Shentong
Luo, Xufang
Wang, Yansen
Li, Dongsheng
author_facet Mo, Shentong
Luo, Xufang
Wang, Yansen
Li, Dongsheng
contents Visual task adaptation has been demonstrated to be effective in adapting pre-trained Vision Transformers (ViTs) to general downstream visual tasks using specialized learnable layers or tokens. However, there is yet a large-scale benchmark to fully explore the effect of visual task adaptation on the realistic and important medical domain, particularly across diverse medical visual modalities, such as color images, X-ray, and CT. To close this gap, we present Med-VTAB, a large-scale Medical Visual Task Adaptation Benchmark consisting of 1.68 million medical images for diverse organs, modalities, and adaptation approaches. Based on Med-VTAB, we explore the scaling law of medical prompt tuning concerning tunable parameters and the generalizability of medical visual adaptation using non-medical/medical pre-train weights. Besides, we study the impact of patient ID out-of-distribution on medical visual adaptation, which is a real and challenging scenario. Furthermore, results from Med-VTAB indicate that a single pre-trained model falls short in medical task adaptation. Therefore, we introduce GMoE-Adapter, a novel method that combines medical and general pre-training weights through a gated mixture-of-experts adapter, achieving state-of-the-art results in medical visual task adaptation.
format Preprint
id arxiv_https___arxiv_org_abs_2404_12876
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Large-scale Medical Visual Task Adaptation Benchmark
Mo, Shentong
Luo, Xufang
Wang, Yansen
Li, Dongsheng
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Visual task adaptation has been demonstrated to be effective in adapting pre-trained Vision Transformers (ViTs) to general downstream visual tasks using specialized learnable layers or tokens. However, there is yet a large-scale benchmark to fully explore the effect of visual task adaptation on the realistic and important medical domain, particularly across diverse medical visual modalities, such as color images, X-ray, and CT. To close this gap, we present Med-VTAB, a large-scale Medical Visual Task Adaptation Benchmark consisting of 1.68 million medical images for diverse organs, modalities, and adaptation approaches. Based on Med-VTAB, we explore the scaling law of medical prompt tuning concerning tunable parameters and the generalizability of medical visual adaptation using non-medical/medical pre-train weights. Besides, we study the impact of patient ID out-of-distribution on medical visual adaptation, which is a real and challenging scenario. Furthermore, results from Med-VTAB indicate that a single pre-trained model falls short in medical task adaptation. Therefore, we introduce GMoE-Adapter, a novel method that combines medical and general pre-training weights through a gated mixture-of-experts adapter, achieving state-of-the-art results in medical visual task adaptation.
title A Large-scale Medical Visual Task Adaptation Benchmark
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.12876