AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sheng, Mingyu, Fan, Jianan, Liu, Dongnan, Kikinis, Ron, Cai, Weidong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915008075530240
author Sheng, Mingyu
Fan, Jianan
Liu, Dongnan
Kikinis, Ron
Cai, Weidong
author_facet Sheng, Mingyu
Fan, Jianan
Liu, Dongnan
Kikinis, Ron
Cai, Weidong
contents Surgical instrument segmentation (SIS) is pivotal for robotic-assisted minimally invasive surgery, assisting surgeons by identifying surgical instruments in endoscopic video frames. Recent unsupervised surgical instrument segmentation (USIS) methods primarily rely on pseudo-labels derived from low-level features such as color and optical flow, but these methods show limited effectiveness and generalizability in complex and unseen endoscopic scenarios. In this work, we propose a label-free unsupervised model featuring a novel module named Multi-View Normalized Cutter (m-NCutter). Different from previous USIS works, our model is trained using a graph-cutting loss function that leverages patch affinities for supervision, eliminating the need for pseudo-labels. The framework adaptively determines which affinities from which levels should be prioritized. Therefore, the low- and high-level features and their affinities are effectively integrated to train a label-free unsupervised model, showing superior effectiveness and generalization ability. We conduct comprehensive experiments across multiple SIS datasets to validate our approach's state-of-the-art (SOTA) performance, robustness, and exceptional potential as a pre-trained model. Our code is released at https://github.com/MingyuShengSMY/AMNCutter.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03695
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation
Sheng, Mingyu
Fan, Jianan
Liu, Dongnan
Kikinis, Ron
Cai, Weidong
Computer Vision and Pattern Recognition
Surgical instrument segmentation (SIS) is pivotal for robotic-assisted minimally invasive surgery, assisting surgeons by identifying surgical instruments in endoscopic video frames. Recent unsupervised surgical instrument segmentation (USIS) methods primarily rely on pseudo-labels derived from low-level features such as color and optical flow, but these methods show limited effectiveness and generalizability in complex and unseen endoscopic scenarios. In this work, we propose a label-free unsupervised model featuring a novel module named Multi-View Normalized Cutter (m-NCutter). Different from previous USIS works, our model is trained using a graph-cutting loss function that leverages patch affinities for supervision, eliminating the need for pseudo-labels. The framework adaptively determines which affinities from which levels should be prioritized. Therefore, the low- and high-level features and their affinities are effectively integrated to train a label-free unsupervised model, showing superior effectiveness and generalization ability. We conduct comprehensive experiments across multiple SIS datasets to validate our approach's state-of-the-art (SOTA) performance, robustness, and exceptional potential as a pre-trained model. Our code is released at https://github.com/MingyuShengSMY/AMNCutter.
title AMNCutter: Affinity-Attention-Guided Multi-View Normalized Cutter for Unsupervised Surgical Instrument Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.03695