Self-supervised learning for chest computed tomography: training strategies and effect on downstream applications.

ABSTRACT:

Purpose

Self-supervised pre-training can reduce the amount of labeled training data needed by pre-learning fundamental visual characteristics of the medical imaging data. We investigate several self-supervised training strategies for chest computed tomography exams and their effects on downstream applications.

Approach

We benchmark five well-known self-supervision strategies (masked image region prediction, next slice prediction, rotation prediction, flip prediction, and denoising) on 15 M chest computed tomography (CT) slices collected from four sites of the Mayo Clinic enterprise, United States. These models were evaluated for two downstream tasks on public datasets: pulmonary embolism (PE) detection (classification) and lung nodule segmentation. Image embeddings generated

SUBMITTER: Tariq A 

PROVIDER: S-EPMC11550486 | biostudies-literature | 2024 Nov

REPOSITORIES: biostudies-literature