MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation

Abstract

We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the instance-level nature of the task by employing a masked attention module that generates and classifies a set of fine instrument region proposals. Our method incorporates long-term video-level information through video transformers to improve temporal consistency and enhance mask classification. We validate our approach in the two standard public benchmarks, Endovis 2017 and Endovis 2018. Our experiments demonstrate that MATIS' per-frame baseline outperforms previous state-of-the-art methods and that including our temporal consistency module boosts our model's performance further.

ISBI 2023 (Oral). Winning method of the 2022 SAR-RARP50 Challenge (arXiv:2401.00496). Official extension published at arXiv:2401.11174 . Code available at https://github.com/BCV-Uniandes/MATIS

References in corpus (7)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• The Kinetics Human Action Video Dataset
• Deformable DETR: Deformable Transformers for End-to-End Object Detection
• Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
• 2018 Robotic Scene Segmentation Challenge
• Towards Holistic Surgical Scene Understanding
• Comparative evaluation of instrument segmentation and tracking methods in minimally invasive surgery

Cited by in corpus (1)

• CLIP-RL: Surgical Scene Segmentation Using Contrastive Language-Vision Pretraining & Reinforcement Learning