A robust approach for endotracheal tube localization in chest radiographs

Chung-Chian Hsu; Rasoul Ameri; Chih-Wen Lin; Jia-Shiang He; Meghdad Biyari; Atefeh Yarahmadi; Shahab S Band; Tin-Kwang Lin; Wen-Lin Fan

doi:10.3389/frai.2023.1181812

A robust approach for endotracheal tube localization in chest radiographs

Front Artif Intell. 2023 May 12:6:1181812. doi: 10.3389/frai.2023.1181812. eCollection 2023.

Authors

Chung-Chian Hsu¹, Rasoul Ameri², Chih-Wen Lin^{3

4}, Jia-Shiang He³, Meghdad Biyari², Atefeh Yarahmadi², Shahab S Band^{5

6}, Tin-Kwang Lin^{3

4}, Wen-Lin Fan^{3

4}

Affiliations

¹ Department of Information Management, International Graduate School of Artificial Intelligence, National Yunlin University of Science and Technology, Douliu, Taiwan.
² Department of Information Management, National Yunlin University of Science and Technology, Douliu, Taiwan.
³ Buddhist Dalin Tzu Chi Hospital, Chiayi, Taiwan.
⁴ School of Medicine, Tzu Chi University, Hualien, Taiwan.
⁵ Future Technology Research Center, National Yunlin University of Science and Technology, Douliu, Taiwan.
⁶ International Graduate School of Artificial Intelligence, National Yunlin University of Science and Technology, Douliu, Taiwan.

Abstract

Precise detection and localization of the Endotracheal tube (ETT) is essential for patients receiving chest radiographs. A robust deep learning model based on U-Net++ architecture is presented for accurate segmentation and localization of the ETT. Different types of loss functions related to distribution and region-based loss functions are evaluated in this paper. Then, various integrations of distribution and region-based loss functions (compound loss function) have been applied to obtain the best intersection over union (IOU) for ETT segmentation. The main purpose of the presented study is to maximize IOU for ETT segmentation, and also minimize the error range that needs to be considered during calculation of distance between the real and predicted ETT by obtaining the best integration of the distribution and region loss functions (compound loss function) for training the U-Net++ model. We analyzed the performance of our model using chest radiograph from the Dalin Tzu Chi Hospital in Taiwan. The results of applying the integration of distribution-based and region-based loss functions on the Dalin Tzu Chi Hospital dataset show enhanced segmentation performance compared to other single loss functions. Moreover, according to the obtained results, the combination of Matthews Correlation Coefficient (MCC) and Tversky loss functions, which is a hybrid loss function, has shown the best performance on ETT segmentation based on its ground truth with an IOU value of 0.8683.

Keywords: U-Net++; chest radiograph; deep learning; endotracheal tube; medical image segmentation.

Grants and funding

The research was supported in part by the “Intelligent Recognition Industry Service Center” from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan, the National Science and Technology Council, Taiwan (MOST 111-2410-H-224-009), and the Buddhist Dalin Tzu Chi Hospital, Chiayi, Taiwan (B11103012).