biostudies-literatureUnknown11(6)Tariq A<h4>Purpose</h4>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.<h4>Approach</h4>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 generatedJournal of medical imaging (Bellingham, Wash.)064003https://www.ebi.ac.uk/biostudies/studies/S-EPMC11550486biostudies-literatureSelf-supervised learning for chest computed tomography: training strategies and effect on downstream applications.PMC11550486Patel BBanerjee ITariq ARamasamy GfalseSelf-supervised learning for chest computed tomography: training strategies and effect on downstream applications.<h4>Purpose</h4>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.<h4>Approach</h4>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 generated2024-01-01T00:00:00Z2024 Nov2026-06-12T04:58:32.792Z2026-06-12T03:08:07.525ZS-EPMC115504863952965810.1117/1.JMI.11.6.06400310.1117/1.jmi.11.6.064003