Tool Segmentation in Cataract Surgery Videos
This dataset contains bounding-box and mask segmentations for typical instruments in cataract surgery, sampled from 393 selected frames of the Cataract-101 video dataset as well as 4738 images of the CaDIS dataset. An evaluation for this dataset can be found in the following CBMS 2020 paper:
Markus Fox, Mario Taschwer, Klaus Schoeffmann. 2020. Pixel-Based Tool Segmentation in Cataract Surgery Videos with Mask R-CNN. Proceedings of the 33rd International Symposium on Computer Based Medical Systems (CBMS), IEEE, Los Alamitos, 4 pages.
The dataset is available for download here.
Iris and Pupil Segmentation in Cataract Surgery Videos
This dataset contains mask segmentations for Iris and Pupil in 82 frames sampled from videos of the Cataract-101 video dataset. An evaluation for automatic Iris and Pupil segmentation can be found in our ISBI 2020 workshop paper:
Natalia Sokolova, Mario Taschwer, Stephanie Sarny, Doris Putzgruber-Adamitsch, Klaus Schoeffmann. 2020. Pixel-Based Iris and Pupil Segmentation in Cataract Surgery Videos Using Mask R-CNN. Proceedings in IEEE International Symposium on Biomedical Imaging Workshops. IEEE, Los Alamitos, CA, USA, 4 pages.
GLENDA – The ITEC Gynecologic Laparoscopy Endometriosis Dataset
GLENDA (Gynecologic Laparoscopy ENdometriosis DAtaset) comprises over 25 000 images taken from 400+ gynecologic laparoscopy surgeries and is purposefully created to be utilized for a variety of automatic content analysis problems in the context of Endometriosis recognition. It contains about 12000 frames showing endometriosis of varying severity (peritoneum, ovary, uterus, and deep infiltrated endometriosis) as well as about 13000 frames showing no endometriosis. Many frames with endometriosis further contain region-based and temporal expert annotations.
The GLENDA dataset is available for download here.
V3C1 Analysis Data
Results of content analysis on the V3C1 dataset can be downloaded from my GitHub repository. An overview and description of the analysis data can be found in our SIGMM Records article. Thanks a lot also to Luca Rossetto for providing the second part of the analysis results.
V3C1 Mirror (Vimeo Creative Commons License)
We provide a mirror of the V3C1 dataset in collaboration with NIST/TRECVID, which is used for the Video Browser Showdown as well as for the TRECVID Ad-Hoc Video Search (AVS) Task (thanks a lot to Luca Rossetto). This first part of the V3C dataset consists of 7475 video files, amounting for 1000h of video content (1,082,659 predefined segments) and 1.3 TB in size. In order to download the dataset, please complete this data agreement form and send a scan to email@example.com with CC to firstname.lastname@example.org and email@example.com. You will be provided with an FTP-server link for downloading the data.
LapGyn4 Gynecologic Laparoscopy Dataset
The ITEC LapGyn4 Gynecologic Laparoscopy Image Dataset actually comprises four individual datasets:
- surgical actions
- anatomical structures
- actions on anatomy
- instrument count
The dataset was collected from 500+ gynecologic laparoscopic surgeries for the task of automatic content analysis, as described in detail in the corresponding paper presented at MMSYS 2018 (if you use our dataset, please cite this paper).
Cataract-101 Video Dataset
The ITEC Cataract-101 dataset consists of videos from 101 cataract surgeries, annotated with different operation phases that were performed by four different surgeons over a period of 9 months. These surgeons are grouped into moderately experienced and highly experienced surgeons (assistant vs. senior physicians), providing the basis for experience-based video analytics, as described in detail in the corresponding paper presented at MMSYS 2018 (if you use our dataset, please cite this paper) .
Cataract-21 Video Dataset
The dataset contains 21 video recordings of cataract surgeries. The dataset is divided into a training part consisting of 17 videos and a validation part consisting of 4 videos. For each video a CSV file with ground-truth annotations is provided, linking each frame number to one of ten classes (operation phases) listed above. The ground-truth annotation has been done by medical experts of Klinikum Klagenfurt. Please note that parts of video recordings that do not belong to any of the classes are labelled with “not_initialized” (in particular, the part before the first phase “Incision”).
The ITEC SurgicalActions160 dataset consists of short video clips representing 16 typical actions in gynecologic laparoscopy, which have been compiled from different surgeries. For each action class there are exactly 10 example clips.
More information about the dataset can be found in our MTAP paper (if you use our dataset, please cite this paper):
Klaus Schoeffmann, Heinrich Husslein, Sabrina Kletz, Stefan Petscharnig, Bernd Münzer, and Christian Beecks. Video Retrieval in Laparoscopic Video Recordings with Dynamic Content Descriptors, in Multimedia Tools and Applications (MTAP), 2018, pp. 1-18, online first.