Deep learning based dual stage model for accurate nasogastric tube positioning in chest radiographs
Open Access
- 25 April 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-9
Abstract
Accurate placement of nasogastric tubes (NGTs) is crucial for ensuring patient safety and effective treatment. Traditional methods relying on manual inspection are susceptible to human error, highlighting the need for innovative solutions. This study introduces a deep-learning model that enhances the detection and analysis of NGT positioning in chest radiographs. By integrating advanced segmentation and classification techniques, the model leverages the nnU-Net framework for segmenting critical regions and the ResNet50 architecture, pre-trained with MedCLIP, for classifying NGT placement. Trained on 1799 chest radiographs, the model demonstrates remarkable performance, achieving a Dice Similarity Coefficient of 65.35% for segmentation and an Area Under the Curve of 99.72% for classification. These results underscore its ability to accurately distinguish between correct and incorrect placements, outperforming traditional approaches. This method not only enhances diagnostic precision but also has the potential to streamline clinical workflows and improve patient care. A functional prototype of the model is accessible at https://ngtube.ziovision.ai.Keywords
Funding Information
- Ministry of Science and ICT, Republic of Korea
This publication has 24 references indexed in Scilit:
- 3D MFA: An automated 3D Multi-Feature Attention based approach for spine segmentation using a multi-stage network pruningComputers in Biology and Medicine, 2024
- An Automated Multi-scale Feature Fusion Network for Spine Fracture Segmentation Using Computed Tomography ImagesJournal of Imaging Informatics in Medicine, 2024
- MSFF: An automated multi-scale feature fusion deep learning model for spine fracture segmentation using MRIBiomedical Signal Processing and Control, 2024
- 3D MRU-Net: A novel mobile residual U-Net deep learning model for spine segmentation using computed tomography imagesBiomedical Signal Processing and Control, 2023
- Semi-supervised Medical Image Segmentation Using Cross-Model Pseudo-Supervision with Shape Awareness and Local Context Constraints2022
- Automated detection of enteric tubes misplaced in the respiratory tract on chest radiographs using deep learning with two centre validationClinical Radiology, 2022
- CLiP, catheter and line position datasetScientific Data, 2021
- Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research DirectionsSN Computer Science, 2021
- Assessment of Critical Feeding Tube Malpositions on Radiographs Using Deep LearningJournal of Digital Imaging, 2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015