Surgical Workflow Dataset
Cholec80 is an endoscopic video dataset containing 80 videos of cholecystectomy surgeries performed by 13 surgeons. The videos are captured at 25 fps and downsampled to 1 fps for processing. The whole dataset is labeled with the phase and tool presence annotations. The phases have been defined by a senior surgeon in Strasbourg hospital, France. Since the tools are sometimes hardly visible in the images and thus difficult to be recognized visually, a tool is defined as present in an image if at least half of the tool tip is visible.
Source: EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos[https://arxiv.org/pdf/1602.03012.pdf]
Variants: Cholec80
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Surgical phase recognition | MuST | MuST: Multi-Scale Transformers for Surgical … | 2024-07-24 |
| Surgical phase recognition | MSN | Self-Supervised Learning for Endoscopic Video … | 2023-08-23 |
| Surgical phase recognition | SF-TMN(ASFormer) | SF-TMN: SlowFast Temporal Modeling Network … | 2023-06-15 |
| Surgical phase recognition | LoViT | LoViT: Long Video Transformer for … | 2023-05-15 |
| Surgical phase recognition | MoCo V2 Surg SSL - TCN head | Dissecting Self-Supervised Learning Methods for … | 2022-07-01 |
| Surgical phase recognition | TCN | TeCNO: Surgical Phase Recognition with … | 2020-03-24 |
Recent papers with results on this dataset: