December 10, 2018 — Korean image software company Coreline Soft Co. Ltd. recently developed a 2.5D convolutional neural network (CNN)-based artificial intelligence (AI) engine for airway segmentation from computed tomography (CT) images through collaboration with Asan Medical Center in Seoul. The engine enables accurate segmentation without any human interaction, taking just a few minutes for a task that experts used to spend more than an hour doing, according to research published in the October 2018 issue of Medical Image Analysis.1
The engine was one of five products built on Coreline Soft’s thin-client cloud technology that were presented at the 2018 Radiological Society of North America (RSNA) annual meeting, Nov. 25-30 in Chicago.
AView Research is a powerful platform for research support. It provides functions such as:
- Easy data management;
- DICOM anonymization with honest broker;
- Radiomics analysis from texture/shape/fractal features;
- Segmentation mask export; and
- Multi-user access for efficient collaboration on a cloud base.
AView Metric is a chronic obstructive pulmonary disease (COPD) analysis solution that offers AI-powered lung/lobe segmentation, airway measurement and INSP/EXP lung registration for various quantification. All quantification is performed automatically without a single click, according to Coreline Soft.
For more information: www.corelinesoft.com
Reference
1. Yun J., Park J., Yu D., et al. Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net. Medical Image Analysis, published online Oct. 19, 2018. https://doi.org/10.1016/j.media.2018.10.006
May 02, 2024 
