The Binary Airway Segmentation Dataset [1][2] includes 90 CT scans in total. 70 CT scans are from LIDC [3], and 20 CT scans are from the training set of the EXACT'09 [4].

We provided the images and airway annotations for the 70 CT scans from LIDC. Meanwhile, only the airway annotations for the 20 CT scans from EXACT'09 are provided. The original images of EXACT'09 should be acquired from its own official website: http://image.diku.dk/exact/.

Download Links The BAS dataset can be acquired from here: Link

Reference:

[1] Qin Y, Zheng H, Gu Y, et al. Learning tubule-sensitive CNNs for pulmonary airway and artery-vein segmentation in CT[J]. IEEE transactions on medical imaging, 2021, 40(6): 1603-1617.

[2] Zheng H, Qin Y, Gu Y, et al. Alleviating class-wise gradient imbalance for pulmonary airway segmentation[J]. IEEE transactions on medical imaging, 2021, 40(9): 2452-2462.

[3] Armato III, S.G., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)

[4] Lo, P., et al.: Extraction of airways from CT (EXACT 2009). IEEE TMI 31(11), 2093–2107 (2012)