Surgical Visual Understanding (SurgVU) Dataset

TL;DR

A large dataset of surgical videos and their accompanying labels is presented, curated for a particular set of scientific challenges, that is general enough to be used for a broad range machine learning questions.

Abstract

Owing to recent advances in machine learning and the ability to harvest large amounts of data during robotic-assisted surgeries, surgical data science is ripe for foundational work. We present a large dataset of surgical videos and their accompanying labels for this purpose. We describe how the data was collected and some of its unique attributes. Multiple example problems are outlined. Although the dataset was curated for a particular set of scientific challenges (in an accompanying paper), it is general enough to be used for a broad range machine learning questions. Our hope is that this dataset exposes the larger machine learning community to the challenging problems within surgical data science, and becomes a touchstone for future research. The videos are available at https://storage.googleapis.com/isi-surgvu/surgvu24_videos_only.zip, the labels at https://storage.googleapis.com/isi-surgvu/surgvu24_labels_updated_v2.zip, and a validation set for tool detection problem at https://storage.googleapis.com/isi-surgvu/cat1_test_set_public.zip.

Figures (6)

• Figure 1: Sample frames of multiple surgical tasks included in our dataset. Note that some frames capture fluorescence imaging (top right image).
• Figure 2: example images of surgical instruments present in the dataset
• Figure 3: Distribution of tool labels in training dataset
• Figure 4: Distribution of surgical tasks in training dataset
• Figure 5: Class distribution of tools in the validation dataset