Deep Learning–Based Kernel Adaptation Enhances Quantification of Emphysema on Low-Dose Chest CT for Predicting Long-Term Mortality

Hyungin Park, MD, Eui Jin Hwang, MD, PhD, and Jin Mo Goo, MD, PhD
Investigative Radiology
Related Product


Date Published

This retrospective study examined the predictive value of quantifying emphysema using low-dose computed tomography (LDCT) with deep learning-based kernel adaptation on long-term mortality. The study utilized LDCT scans from asymptomatic individuals aged 60 years or older and employed CorelineSoft's software, which incorporated a kernel adaptation algorithm, to quantify emphysema. The results showed that after kernel adaptation, higher levels of emphysema quantification were associated with an increased risk of nonaccidental death. This study highlights the effectiveness of CorelineSoft's software in accurately quantifying emphysema and its potential as a predictive tool for long-term mortality in asymptomatic individuals.


Please leave your inquiry if you have any questions regarding our products, recruitment, investment, or any other matters.

Contact us