# Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2

arXiv: https://arxiv.org/abs/2502.20934 · HTML: https://mlsanity.com/paper/2502.20934/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80](https://mlsanity.com/paper/2012.12453/) (2020)
- [SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation](https://mlsanity.com/paper/2408.04593/) (2024)
- [CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery](https://mlsanity.com/paper/2406.16039/) (2024)
- [Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models](https://mlsanity.com/paper/2501.15452/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos](https://mlsanity.com/paper/2510.02100/) (2025)

## Abstract (arXiv)

Real-time video segmentation is a promising opportunity for AI-assisted surgery, offering intraoperative guidance by identifying tools and anatomical structures. Despite growing interest in surgical video segmentation, annotation protocols vary widely across datasets -- some provide dense, frame-by-frame labels, while others rely on sparse annotations sampled at low frame rates such as 1 FPS. In this study, we investigate how such inconsistencies in annotation density and frame rate sampling influence the evaluation of zero-shot segmentation models, using SAM2 as a case study for cholecystectomy procedures. Surprisingly, we find that under conventional sparse evaluation settings, lower frame rates can appear to outperform higher ones due to a smoothing effect that conceals temporal inconsistencies. However, when assessed under real-time streaming conditions, higher frame rates yield superior segmentation stability, particularly for dynamic objects like surgical graspers. To understand how these differences align with human perception, we conducted a survey among surgeons, nurses, and machine learning engineers and found that participants consistently preferred high-FPS segmentation overlays, reinforcing the importance of evaluating every frame in real-time applications rather than relying on sparse sampling strategies. Our findings highlight the risk of evaluation bias that is introduced by inconsistent dataset protocols and bring attention to the need for temporally fair benchmarking in surgical video AI.