Corpus ID: 236428736

B-line Detection in Lung Ultrasound Videos: Cartesian vs Polar Representation

  title={B-line Detection in Lung Ultrasound Videos: Cartesian vs Polar Representation},
  author={Hamideh Kerdegari and Phung Tran Huy Nhat and Angela McBride and Luigi Pisani and Reza Razavi and Louise Thwaites and Sophie Yacoub and Alberto Gomez},
Lung ultrasound (LUS) imaging is becoming popular in the intensive care units (ICU) for assessing lung abnormalities such as the appearance of B-line artefacts as a result of severe dengue. These artefacts appear in the LUS images and disappear quickly, making their manual detection very challenging. They also extend radially following the propagation of the sound waves. As a result, we hypothesize that a polar representation may be more adequate for automatic image analysis of these images… Expand

Figures and Tables from this paper


Automatic Detection of B-lines in Lung Ultrasound Videos from Severe Dengue Patients
This paper proposes a novel methodology to automatically detect and localize B-lines in LUS videos using deep neural networks trained with weak labels, which combines a convolutional neural network with a long short-term memory (LSTM) network and a temporal attention mechanism. Expand
Localizing B-Lines in Lung Ultrasonography by Weakly Supervised Deep Learning, In-Vivo Results
Results confirm the capability of the proposed method to identify and localize the presence of B-lines in clinical lung ultrasonography and calculate neural attention maps that visualize which components in the image triggered the network, thereby offering simultaneous weak-supervised localization. Expand
Ultrasound-Based Detection of Lung Abnormalities Using Single Shot Detection Convolutional Neural Networks
A convolutional neural network algorithm was developed to identify five key lung features linked to pathological lung conditions: B-lines, merged B- lines, lack of lung sliding, consolidation and pleural effusion, and the results indicate that deep learning algorithms can successfully detect lung abnormalities in ultrasound imagery. Expand
Deep Learning for Classification and Localization of COVID-19 Markers in Point-of-Care Lung Ultrasound
A novel deep network, derived from Spatial Transformer Networks, is presented, which simultaneously predicts the disease severity score associated to a input frame and provides localization of pathological artefacts in a weakly-supervised way. Expand
Attention U-Net Based Adversarial Architectures for Chest X-ray Lung Segmentation information
A novel deep learning approach for lung segmentation, a basic, but arduous task in the diagnostic pipeline, using state-of-the-art fully convolutional neural networks in conjunction with an adversarial critic model is presented. Expand
Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images
This study uses the Aggregated Residual Transformations to learn a robust and expressive feature representation and applies the soft attention mechanism to improve the capability of the model to distinguish a variety of symptoms of the COVID-19. Expand
Online COVID-19 diagnosis with chest CT images: Lesion-attention deep neural networks
A lesion-attention deep neural network (LA-DNN) is developed to predict COVID-19 positive or negative with a richly annotated chest CT image dataset, and the experimental results show that the area under the curve (AUC) and sensitivity for the diagnosis of CO VID-19 patients are 91.2% and 85.7% respectively, which reach the clinical standards for practical use. Expand
Lung B-line artefacts and their use.
BLA is useful to monitor clinical response, and may become crucial in directing the diagnostic process, and further research is warranted to clarify technical adjustments, different probe and machine factors that influence the visualization of BLA. Expand
The VIA Annotation Software for Images, Audio and Video
A light weight, standalone and offline software package that does not require any installation or setup and runs solely in a web browser, the VIA software allows human annotators to define and describe spatial regions in images or video frames, and temporal segments in audio or video. Expand
Ultrasound patterns of pulmonary edema.
Differentiating between hydrostatic or cardiogenic pulmonary edema (CPE) and ARDS is challenging, especially in the early stages of illness, and this diagnostic task becomes more difficult in older patients, where a higher number of morbidities often coexists. Expand