Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Ziqin, Li, Heng, Li, Zinan, Fu, Huazhu, Liu, Jiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913357857030144
author Lin, Ziqin
Li, Heng
Li, Zinan
Fu, Huazhu
Liu, Jiang
author_facet Lin, Ziqin
Li, Heng
Li, Zinan
Fu, Huazhu
Liu, Jiang
contents Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?
Lin, Ziqin
Li, Heng
Li, Zinan
Fu, Huazhu
Liu, Jiang
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues.
title Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.12584