Skip to main navigation Skip to main content Skip to page footer

Medical Physics Laboratory


GBVasc181 dataset

Prompted by the recent advances in surgical image understanding, we have developed a dataset for the assessment of gallbladder wall vascularity using images from laparoscopic cholecystectomy (LC) operations. The GBVasc181 dataset contains 181 intraoperative images with manual contours (ROIs) of the gallbladder (GB) and 800 patches (70x70) extracted from the ROIs. The patches and ROIs were annotated by expert surgeons using two separate schemes: (a) Low vs. High vascularity and (b) Low, Medium, High vascularity. The dataset is associated with the publication [1]. The images were extracted from the popular Cholec80 video dataset [2]. So, if you use the GBVasc181 dataset you are kindly requested to cite the following works:

[1] C. Loukas, M. Frountzas, D. Schizas. Patch-based classification of gallbladder wall vascularity from laparoscopic images using deep learning. Int J Comput Assist Radiol Surg, 16(1), 103-113, 2021,

[2] A.P. Twinanda, S. Shehata, D. Mutter, J. Marescaux, M. de Mathelin, N. Padoy. EndoNet: A deep architecture for recognition tasks on laparoscopic videos. IEEE Trans on Med Imaging, 36(1), 86-97, 2017

Download GBVasc181 (~100 MB)