Saved in:
Bibliographic Details
Main Authors: Goel, Raghavv, Morales, Cecilia, Singh, Manpreet, Dubrawski, Artur, Galeotti, John, Choset, Howie
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.01239
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908562242928640
author Goel, Raghavv
Morales, Cecilia
Singh, Manpreet
Dubrawski, Artur
Galeotti, John
Choset, Howie
author_facet Goel, Raghavv
Morales, Cecilia
Singh, Manpreet
Dubrawski, Artur
Galeotti, John
Choset, Howie
contents Segmenting a moving needle in ultrasound images is challenging due to the presence of artifacts, noise, and needle occlusion. This task becomes even more demanding in scenarios where data availability is limited. In this paper, we present a novel approach for needle segmentation for 2D ultrasound that combines classical Kalman Filter (KF) techniques with data-driven learning, incorporating both needle features and needle motion. Our method offers three key contributions. First, we propose a compatible framework that seamlessly integrates into commonly used encoder-decoder style architectures. Second, we demonstrate superior performance compared to recent state-of-the-art needle segmentation models using our novel convolutional neural network (CNN) based KF-inspired block, achieving a 15\% reduction in pixel-wise needle tip error and an 8\% reduction in length error. Third, to our knowledge we are the first to implement a learnable filter to incorporate non-linear needle motion for improving needle segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2312_01239
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Motion Informed Needle Segmentation in Ultrasound Images
Goel, Raghavv
Morales, Cecilia
Singh, Manpreet
Dubrawski, Artur
Galeotti, John
Choset, Howie
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Segmenting a moving needle in ultrasound images is challenging due to the presence of artifacts, noise, and needle occlusion. This task becomes even more demanding in scenarios where data availability is limited. In this paper, we present a novel approach for needle segmentation for 2D ultrasound that combines classical Kalman Filter (KF) techniques with data-driven learning, incorporating both needle features and needle motion. Our method offers three key contributions. First, we propose a compatible framework that seamlessly integrates into commonly used encoder-decoder style architectures. Second, we demonstrate superior performance compared to recent state-of-the-art needle segmentation models using our novel convolutional neural network (CNN) based KF-inspired block, achieving a 15\% reduction in pixel-wise needle tip error and an 8\% reduction in length error. Third, to our knowledge we are the first to implement a learnable filter to incorporate non-linear needle motion for improving needle segmentation.
title Motion Informed Needle Segmentation in Ultrasound Images
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2312.01239