CVC-LumenDB is a database of frames extracted from colonoscopy and bronchoscopy videos. These frames contain several examples of different lumen. In addition to the frames, we provide the ground truth segmenting the lumen. This ground truth consists of a mask corresponding to the region covered by the lumen in the image.
CVC-LumenDB has been generated from 20 different video sequences of bronchoscopy and 15 from colonoscopy. Finally, a set of frames were selected from each sequence, paying particular attention in showing several points of view of the lumen, multilumen and non lumen.
If you want to use this dataset in your research, please cite this database as:
Carles Sanchez, Jorge Bernal, Debora Gil, & F. Javier Sanchez. (2013). On-line lumen centre detection in gastrointestinal and respiratory endoscopy. In 16th International Conference on Medical Image Computing and Computer Assisted Intervention. LNCS.