Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients

TL;DR

This paper presents a deep learning-based method for automatic detection and localization of B-lines in lung ultrasound videos, aiding diagnosis in severe dengue patients by reducing manual effort.

Contribution

It introduces a novel combination of CNN, LSTM, and attention mechanisms trained with weak labels for B-line detection in LUS videos.

Findings

F1 score of 0.81 for B-line presence detection

87.5% accuracy in localizing B-line frames

Comparison of four different deep learning models

Abstract

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%.