Author: Kerdegari, Hamideh; Nhat, Phung Tran Huy; McBride, Angela; Consortium, VITAL; Razavi, Reza; Hao, Nguyen Van; Thwaites, Louise; Yacoub, Sophie; Gomez, Alberto
Title: Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients Cord-id: 2vokx0zg Document date: 2021_2_1
ID: 2vokx0zg
Snippet: Lung ultrasound (LUS) imaging is used to assess lung abnormalities, including the presence of B-line artefacts due to fluid leakage into the lungs caused by a variety of diseases. However, manual detection of these artefacts is challenging. In this paper, we propose a novel methodology to automatically detect and localize B-lines in LUS videos using deep neural networks trained with weak labels. To this end, we combine a convolutional neural network (CNN) with a long short-term memory (LSTM) net
Document: Lung ultrasound (LUS) imaging is used to assess lung abnormalities, including the presence of B-line artefacts due to fluid leakage into the lungs caused by a variety of diseases. However, manual detection of these artefacts is challenging. In this paper, we propose a novel methodology to automatically detect and localize B-lines in LUS videos using deep neural networks trained with weak labels. To this end, we combine a convolutional neural network (CNN) with a long short-term memory (LSTM) network and a temporal attention mechanism. Four different models are compared using data from 60 patients. Results show that our best model can determine whether one-second clips contain B-lines or not with an F1 score of 0.81, and extracts a representative frame with B-lines with an accuracy of 87.5%.
Search related documents:
Co phrase search for related documents- accuracy achieve and lstm network: 1, 2, 3
- adam optimizer and lstm model: 1, 2
Co phrase search for related documents, hyperlinks ordered by date