Saved in:
Bibliographic Details
Main Author: Chang, Peter D.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.09587
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916126154293248
author Chang, Peter D.
author_facet Chang, Peter D.
contents This paper introduces the DeepATLAS foundational model for localization tasks in the domain of high-dimensional biomedical data. Upon convergence of the proposed self-supervised objective, a pretrained model maps an input to an anatomically-consistent embedding from which any point or set of points (e.g., boxes or segmentations) may be identified in a one-shot or few-shot approach. As a representative benchmark, a DeepATLAS model pretrained on a comprehensive cohort of 51,000+ unlabeled 3D computed tomography exams yields high one-shot segmentation performance on over 50 anatomic structures across four different external test sets, either matching or exceeding the performance of a standard supervised learning model. Further improvements in accuracy can be achieved by adding a small amount of labeled data using either a semisupervised or more conventional fine-tuning strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09587
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeepATLAS: One-Shot Localization for Biomedical Data
Chang, Peter D.
Computer Vision and Pattern Recognition
This paper introduces the DeepATLAS foundational model for localization tasks in the domain of high-dimensional biomedical data. Upon convergence of the proposed self-supervised objective, a pretrained model maps an input to an anatomically-consistent embedding from which any point or set of points (e.g., boxes or segmentations) may be identified in a one-shot or few-shot approach. As a representative benchmark, a DeepATLAS model pretrained on a comprehensive cohort of 51,000+ unlabeled 3D computed tomography exams yields high one-shot segmentation performance on over 50 anatomic structures across four different external test sets, either matching or exceeding the performance of a standard supervised learning model. Further improvements in accuracy can be achieved by adding a small amount of labeled data using either a semisupervised or more conventional fine-tuning strategy.
title DeepATLAS: One-Shot Localization for Biomedical Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.09587