Rethinking Domain-Specific Pretraining by Supervised or Self-Supervised Learning for Chest Radiograph Classification: A Comparative Study Against ImageNet Counterparts in Cold-Start Active Learning.

Han Yuan¹, Mingcheng Zhu^1,2, Rui Yang¹, Han Liu³, Irene Li⁴, Chuan Hong⁵

¹Duke-NUS Medical School, Centre for Quantitative Medicine Singapore Singapore.

²Department of Engineering Science University of Oxford Oxford UK.

³Department of Computer Science Vanderbilt University Nashville Tennessee USA.

⁴Information Technology Center University of Tokyo Bunkyo-ku Japan.

⁵Department of Biostatistics and Bioinformatics Duke University Durham North Carolina USA.

PubMed PMC DOI PDF

Abstract

OBJECTIVE: Deep learning (DL) has become the prevailing method in chest radiograph analysis, yet its performance heavily depends on large quantities of annotated images. To mitigate the cost, cold-start active learning (AL), comprising an initialization followed by subsequent learning, selects a small subset of informative data points for labeling. Recent advancements in pretrained models by super…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.