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

• URL: http://arxiv.org/abs/2502.20934v3
• Date: Thu, 31 Jul 2025 02:07:41 GMT
• Title: Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2
• Authors: Utku Ozbulak, Seyed Amir Mousavi, Francesca Tozzi, Niki Rashidian, Wouter Willaert, Wesley De Neve, Joris Vankerschaver,
• Abstract summary: We investigate how inconsistencies in annotation density and frame rate sampling influence the evaluation of zero-shot segmentation models.<n>We find that lower frame rates can appear to outperform higher ones due to a smoothing effect that conceals temporal inconsistencies.<n>When assessed under real-time streaming conditions, higher frame rates yield superior segmentation stability.
• Score: 1.0536099636804035
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking [15.83425997240828]
  ReSurgSAM2 is a two-stage referring surgical segmentation framework.<n>It uses cross-modal spatial-temporal Mamba to generate precise detection and segmentation results.<n>It incorporates a diversity-driven memory mechanism that maintains a credible and diverse memory bank, ensuring consistent long-term tracking.
  arXiv  Detail & Related papers  (2025-05-13T13:56:10Z)
• Surgeons vs. Computer Vision: A comparative analysis on surgical phase recognition capabilities [65.66373425605278]
  Automated Surgical Phase Recognition (SPR) uses Artificial Intelligence (AI) to segment the surgical workflow into its key events. Previous research has focused on short and linear surgical procedures and has not explored if temporal context influences experts' ability to better classify surgical phases. This research addresses these gaps, focusing on Robot-Assisted Partial Nephrectomy (RAPN) as a highly non-linear procedure.
  arXiv  Detail & Related papers  (2025-04-26T15:37:22Z)
• Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation [1.6092864505858449]
  We propose a technique that can efficiently eliminate redundant frames to reduce dataset size and computation time.<n>Specifically, we compute the similarity between consecutive frames by tracking the movement of surgical tools.<n>By adaptively selecting relevant frames, we achieve a tenfold reduction in the number of frames while improving accuracy by 4.32%.
  arXiv  Detail & Related papers  (2025-01-19T19:36:09Z)
• Towards a Benchmark for Colorectal Cancer Segmentation in Endorectal Ultrasound Videos: Dataset and Model Development [59.74920439478643]
  In this paper, we collect and annotated the first benchmark dataset that covers diverse ERUS scenarios. Our ERUS-10K dataset comprises 77 videos and 10,000 high-resolution annotated frames. We introduce a benchmark model for colorectal cancer segmentation, named the Adaptive Sparse-context TRansformer (ASTR)
  arXiv  Detail & Related papers  (2024-08-19T15:04:42Z)
• WeakSurg: Weakly supervised surgical instrument segmentation using temporal equivariance and semantic continuity [14.448593791011204]
  We propose a weakly supervised surgical instrument segmentation with only instrument presence labels. We take the inherent temporal attributes of surgical video into account and extend a two-stage weakly supervised segmentation paradigm. Experiments are validated on two surgical video datasets, including one cholecystectomy surgery benchmark and one real robotic left lateral segment liver surgery dataset.
  arXiv  Detail & Related papers  (2024-03-14T16:39:11Z)
• Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything [9.338136334709818]
  We present a novel framework that combines an online point tracker with a lightweight SAM model that is fine-tuned for surgical instrument segmentation. Sparse points within the region of interest are tracked and used to prompt SAM throughout the video sequence, providing temporal consistency. Our method achieves promising performance that is comparable to XMem and transformer-based fully supervised segmentation methods.
  arXiv  Detail & Related papers  (2024-03-12T18:12:42Z)
• RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy [83.4885991036141]
  RIDE is a learning-based method for rotation-equivariant detection and invariant description. It is trained in a self-supervised manner on a large curation of endoscopic images. It sets a new state-of-the-art performance on matching and relative pose estimation tasks.
  arXiv  Detail & Related papers  (2023-09-18T08:16:30Z)
• GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos [57.93194315839009]
  We propose a vision transformer-based approach to learn temporal features directly from sequence-level patches. We extensively evaluate our approach on two cataract surgery video datasets, Cataract-101 and D99, and demonstrate superior performance compared to various state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-07-20T17:57:04Z)
• A spatio-temporal network for video semantic segmentation in surgical videos [11.548181453080087]
  We propose a novel architecture for modelling temporal relationships in videos. The proposed model includes a decoder to enable semantic video segmentation. The proposed decoder can be used on top of any segmentation encoder to improve temporal consistency.
  arXiv  Detail & Related papers  (2023-06-19T16:36:48Z)
• LoViT: Long Video Transformer for Surgical Phase Recognition [59.06812739441785]
  We present a two-stage method, called Long Video Transformer (LoViT) for fusing short- and long-term temporal information. Our approach outperforms state-of-the-art methods on the Cholec80 and AutoLaparo datasets consistently.
  arXiv  Detail & Related papers  (2023-05-15T20:06:14Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations [72.15956198507281]
  We propose PGV-CL, a novel pseudo-label guided cross-video contrast learning method to boost scene segmentation. We extensively evaluate our method on a public robotic surgery dataset EndoVis18 and a public cataract dataset CaDIS.
  arXiv  Detail & Related papers  (2022-07-20T05:42:19Z)
• Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation [49.17930380106643]
  We propose a novel framework to speed up any architecture with skip-connections for real-time vision tasks. Specifically, at the arrival of each frame, we transform the features from the previous frame to reuse them at specific spatial bins. We then perform partial computation of the backbone network on the regions of the current frame that captures temporal differences between the current and previous frame.
  arXiv  Detail & Related papers  (2022-06-20T07:20:02Z)
• Efficient Global-Local Memory for Real-time Instrument Segmentation of Robotic Surgical Video [53.14186293442669]
  We identify two important clues for surgical instrument perception, including local temporal dependency from adjacent frames and global semantic correlation in long-range duration. We propose a novel dual-memory network (DMNet) to relate both global and local-temporal knowledge. Our method largely outperforms the state-of-the-art works on segmentation accuracy while maintaining a real-time speed.
  arXiv  Detail & Related papers  (2021-09-28T10:10:14Z)
• Development and evaluation of intraoperative ultrasound segmentation with negative image frames and multiple observer labels [0.17159130619349347]
  We evaluate the utility of a pre-screening classification network prior to the segmentation network. We show experimentally that a previously proposed approach, combining random sampling and consensus labels, may need to be adapted to perform well in our application.
  arXiv  Detail & Related papers  (2021-07-28T12:15:49Z)
• Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video [11.100734994959419]
  We propose a novel Multi-frame Feature Aggregation (MFFA) module to aggregate video frame features temporally and spatially. We also develop a method that can randomly synthesize a surgical frame sequence from a single labeled frame to assist network training.
  arXiv  Detail & Related papers  (2020-11-17T16:27:27Z)
• Efficient Semantic Video Segmentation with Per-frame Inference [117.97423110566963]
  In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed.
  arXiv  Detail & Related papers  (2020-02-26T12:24:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.