Zum Hauptinhalt springen

BAGLS

The BAGLS dataset

We provide here a benchmark dataset for glottis segmentation (BAGLS). It features the following specifications:

  • 55750 training images and their corresponding segmentation
  • 3500 test images and their corresponding segmentation

If you are interested in the dataset, please write to Prof. Dr. Michael Döllinger.

 

Benchmark for Automatic Glottis Segmentation (BAGLS)

Website of the Benchmark for Automatic Glottis Segmentation (BAGLS)

Publications

P. Gomez, A. M. Kist, P. Schlegel, D. A. Berry, D. K. Chhetri, S. Dürr, M. Echternach, A. M. Johnson, S. Kniesburges, M. Kunduk, Y. Maryn, A. Schützenberger, M. Verguts, M. Döllinger. BAGLS, a multihospital benchmark for automatic glottis segmentation. Scientific Data, 7(1):186; 2020.

M. Döllinger, T. Schraut, L.A. Henrich, D. Chhetri, M. Echternach, A.M. Johnson, M. Kunduk, Y. Maryn, R.R. Patel, R. Samlan, M. Semmler, A. Schützenberger. Re-training of convolutional neural networks for glottis segmentation in endoscopic high-speed videos. Appl. Sci., 12, 9791, 2022. https://doi.org/10.3390/app12199791