## **AIRWAYS 2020 (Airway Segmentation 2020)**

The segmentation of the airway trees in chest computed tomography (CT) images is critical for quantitative assessment of airway diseases including bronchiectasis and chronic obstructive pulmonary disease (COPD). However, obtaining an accurate segmentation of airways from CT scans is difficult due to the high complexity and artifacts of airway structures including complex bifurcations, tapering airways, partial volume effect andmotion artifacts. Fully automated airway segmentation still remains a highchallenging task. Recently, a semantic segmentation using deep convolutional neural networks (CNNs) on airway tree segmentation in CT came true [1], but various kinds of robust airway segmentation methods are still a challenge. We developed a special software to semi-automatically label and correct airway tree as exact as possible [1]. We labeled 100 airway trees of CT from normal to various severities of COPD patients (GOLD I to IV) to build the gold standards, which was confirmed by an expert thoracic radiologist with more than 20 years’ experience. We split 100 datasets into training and validation, test phase I, and test phaseII as 50, 20, and 30. With Kaggle competition platform, we want to open an AIRWAYS challenge in MICCAI 2020 to develop robust airway tree segmentation.

## Reference
[1] Yun, Jihye, et al. "Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net." Medical image analysis 51 (2019): 13-20.