Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound

TL;DR

This paper introduces a fast, efficient, weakly-supervised CNN-based method for catheter segmentation in 3D frustum ultrasound images, overcoming computational and annotation challenges of traditional Cartesian approaches.

Contribution

It proposes a novel frustum ultrasound representation combined with a weakly supervised learning framework using pseudo labels, enabling accurate segmentation with minimal annotation effort.

Findings

Achieved state-of-the-art segmentation performance.

Reduced processing time to 0.25 seconds per volume.

Provided a faster, cheaper solution suitable for clinical use.

Abstract

Accurate and efficient catheter segmentation in 3D ultrasound (US) is essential for cardiac intervention. Currently, the state-of-the-art segmentation algorithms are based on convolutional neural networks (CNNs), which achieved remarkable performances in a standard Cartesian volumetric data. Nevertheless, these approaches suffer the challenges of low efficiency and GPU unfriendly image size. Therefore, such difficulties and expensive hardware requirements become a bottleneck to build accurate and efficient segmentation models for real clinical application. In this paper, we propose a novel Frustum ultrasound based catheter segmentation method. Specifically, Frustum ultrasound is a polar coordinate based image, which includes same information of standard Cartesian image but has much smaller size, which overcomes the bottleneck of efficiency than conventional Cartesian images. Nevertheless, the irregular and deformed Frustum images lead to more efforts for accurate voxel-level annotation. To address this limitation, a weakly supervised learning framework is proposed, which only needs 3D bounding box annotations overlaying the region-of-interest to training the CNNs. Although the bounding box annotation includes noise and inaccurate annotation to mislead to model, it is addressed by the proposed pseudo label generated scheme. The labels of training voxels are generated by incorporating class activation maps with line filtering, which is iteratively updated during the training. Our experimental results show the proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume. More crucially, the Frustum image segmentation provides a much faster and cheaper solution for segmentation in 3D US image, which meet the demands of clinical applications.