2D Upper airway annotated MRI dataset

This dataset consists of manually segmented 2D static upper airway images acquired at the University of Iowa 3T research scanner. The images were captured using a fast GRE sequence in the midsagittal plane, with a spatial resolution of 2.7 mm² and approximately 6 frames per second, and a field of view (FOV) of 20x20 cm².<br>The airways in 1000 image frames from 5 volunteers were manually segmented while performing various speech tasks, such as producing za-na-za, loo-lee-la, apa-ipi-upu, counting numbers, and speaking spontaneous speech. This dataset is suitable for training a deep learning model to segment the upper airway.The dataset is structured as follows:Image: Zip folder containing mid-sagittal images of a dynamic airway (256 x 256 pixels).Mask: Zip folder containing the respective segmentations for the images.If you use this dataset, please cite the following papers:1. [ERATTAKULANGARA, SUBIN, et al. "Stacked hybrid learning U-NET for segmentation of multiple articulators in speech MRI." ISMRM 2021]2. [Erattakulangara, Subin, et al. "Automatic Multiple Articulator Segmentation in Dynamic Speech MRI Using a Protocol Adaptive Stacked Transfer Learning U-NET Model." Bioengineering 10.5 (2023): 623.]