UNGT: Ultrasound Nasogastric Tube Dataset for Medical Image Analysis

TL;DR

This paper introduces the UNGT dataset with annotated ultrasound images of nasogastric tubes and proposes a semi-supervised segmentation method that effectively handles data imbalance, improving medical image analysis accuracy.

Contribution

The paper presents a new ultrasound dataset for nasogastric tubes and a novel semi-supervised segmentation approach with adaptive weighting and multiscale attention.

Findings

AAMS outperforms existing segmentation methods.

The dataset enables improved medical image analysis.

The adaptive weighting effectively handles data imbalance.

Abstract

We develop a novel ultrasound nasogastric tube (UNGT) dataset to address the lack of public nasogastric tube datasets. The UNGT dataset includes 493 images gathered from 110 patients with an average image resolution of approximately 879 $\times$ 583. Four structures, encompassing the liver, stomach, tube, and pancreas, are precisely annotated. Besides, we propose a semi-supervised adaptive-weighting aggregation medical segmenter to address data limitation and imbalance concurrently. The introduced adaptive weighting approach tackles the severe unbalanced challenge by regulating the loss across varying categories as training proceeds. The presented multiscale attention aggregation block bolsters the feature representation by integrating local and global contextual information. With these, the proposed AAMS can emphasize sparse or small structures and feature enhanced representation ability. We perform extensive segmentation experiments on our UNGT dataset, and the results show that AAMS outperforms existing state-of-the-art approaches to varying extents. In addition, we conduct comprehensive classification experiments across varying state-of-the-art methods and compare their performance. The dataset and code will be available upon publication at https://github.com/NUS-Tim/UNGT.