Automatic Detection of B-lines in Lung Ultrasound Videos From Severe Dengue Patients
This work addresses the challenge of manual detection of lung abnormalities for medical practitioners, but it is incremental as it applies existing deep learning methods to a specific medical dataset.
The paper tackled the problem of automatically detecting B-line artefacts in lung ultrasound videos from severe dengue patients, achieving an F1 score of 0.81 for clip classification and 87.5% accuracy for frame extraction.
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%.