2019/08/20 by Maayan Frid-Adar, Frid-Adar, Maayan, Rula Amer +3
Medicine · #Airway Management and Intubation Techniques #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Lung Cancer Diagnosis and Treatment #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1908.07170
openalex publication_date 2019/08/20 · openalex created_date 2022/07/19 · openalex updated_date 2026/07/28
Chest radiographs are frequently used to verify the correct intubation of\npatients in the emergency room. Fast and accurate identification and\nlocalization of the endotracheal (ET) tube is critical for the patient. In this\nstudy we propose a novel automated deep learning scheme for accurate detection\nand segmentation of the ET tubes. Development of automatic systems using deep\nlearning networks for classification and segmentation require large annotated\ndata which is not always available. Here we present an approach for\nsynthesizing ET tubes in real X-ray images. We suggest a method for training\nthe network, first with synthetic data and then with real X-ray images in a\nfine-tuning phase, which allows the network to train on thousands of cases\nwithout annotating any data. The proposed method was tested on 477 real chest\nradiographs from a public dataset and reached AUC of 0.99 in classifying the\npresence vs. absence of the ET tube, along with outputting high quality ET tube\nsegmentation maps.\n