Endotracheal Tube Detection and Segmentation in Chest Radiographs using Synthetic Data

Abstract

Chest radiographs are frequently used to verify the correct intubation of patients in the emergency room. Fast and accurate identification and localization of the endotracheal (ET) tube is critical for the patient. In this study we propose a novel automated deep learning scheme for accurate detection and segmentation of the ET tubes. Development of automatic systems using deep learning networks for classification and segmentation require large annotated data which is not always available.Here we present an approach for synthesizing ET tubes in real X-ray images. We suggest a method for training the network, first with synthetic data and then with real X-ray images in a fine-tuning phase, which allows the network to train on thousands of cases without annotating any data. The proposed method was tested on 477 real chest radiographs from a public dataset and reached AUC of 0.99 in classifying the presence vs. absence of the ET tube, along with outputting high quality ET tube segmentation maps.

Determining Carina and Clavicular Distance-Dependent Positioning of Endotracheal Tube in Critically Ill Patients: An Artificial Intelligence-Based Approach

“…Using a fully convolutional CNN model with combined real and synthetic data, the entire course of the ETT has been localized. However, it lacks the location of the distal tip of ETT relative to carina [29]. Apart from detecting the ETT tube on chest radiographs, previous studies have used deep CNN to the Indiana, JSRT, and Shenzhen datasets to localize various ranges of abnormalities, in particular, cardiomegaly with the highest accuracy of 92% and highest AUC of 0.9408 for detecting cardiomegaly [30].…”

CardioNet: Automatic Semantic Segmentation to Calculate the Cardiothoracic Ratio for Cardiomegaly and Other Chest Diseases

“…Frid-Adar et al considered an important application of semantic segmentation to detect the clavicle bone positioning using Chest X-rays. The modified architecture used to segment the clavicle bones and the weights of VGG16 used in the encoder [ 34 ]. Oliveira et al presented a transfer learning-based approach f chest-related organs segmentation.…”

DeepWL: Robust EPID based Winston-Lutz analysis using deep learning, synthetic image generation and optical path-tracing

“…This technique is particularly useful in cases where manual annotation of the training data is too time consuming or would lead to high uncertainties such as inter-observer variability in the case of organ-at-risk segmentation. Previous examples of fields utilizing this technique include: geology [35,36], biology [37][38][39][40][41], automotive [42,43], medical [44][45][46][47][48][49][50] and robotics [51][52][53]. This technique has also been utilized in radiation oncology to calculate MV linac radiation doses in real patient CTs using DL models which were trained only on synthetic data [54].…”