Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions

@inproceedings{Morilhat2022DeepLS,
  title={Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions},
  author={Germain Morilhat and Naomi Kifle and Sandy FinesilverSmith and Bram Ruijsink and Vittoria Vergani and Habtamu Tegegne Desita and Zerubabel Tegegne Desita and Esther Puyol-Ant{\'o}n and Aaron Carass and Andrew P. King},
  booktitle={DeCaF/FAIR@MICCAI},
  year={2022}
}
. Ultrasound imaging plays a crucial role in assessing disease and making diagnoses for a range of conditions, especially so in low-to-middle-income (LMIC) countries. One such application is the assessment of pleural effusion, which can be associated with multiple morbidities including tuberculosis (TB). Currently, assessment of pleural effusion is performed manually by the sonographer during the ultrasound examination, leading to significant intra-/inter-observer variability. In this work, we… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 14 REFERENCES

A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images

A DL approach is used to automate the measurement of the abdominal muscle thickness in 2D US images by treating the problem as a localization task, and a modified FCN architecture is developed to generate blobs of coordinate locations of measurement endpoints, similar to what a human operator does.

Direct estimation of fetal head circumference from ultrasound images based on regression CNN

This paper proposes to leverage the ability of convolutional neural networks (CNN) to directly measure the head circumference, without having to resort to handcrafted features or manually labeled segmented images.

Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learning

A deep learning approach for automatically determining the estimated glomerular filtration rate (eGFR) and CKD status and is the first fundamental step toward realizing the potential of transforming kidney ultrasound imaging into an effective, real-time, distant screening tool.

Investigating CoordConv for Fully and Weakly Supervised Medical Image Segmentation

This paper investigates CoordConv as a proficient substitute to convolutional layers for organ segmentation in both fully and weakly supervised settings and shows that it may interestingly increase model convergence at almost no additional computational cost.

Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study.

Study on automatic detection and classification of breast nodule using deep convolutional neural network system

Deep convolutional neural network technology, a kind of Deep Learning algorithm, is used for the detection and classification of breast nodules, aiming to achieve the automatic and accurate diagnosis of breast nodsules.

Video-based AI for beat-to-beat assessment of cardiac function

A video-based deep learning algorithm that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy is presented.

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.

Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image

Detection and Localization of Ultrasound Scatterers Using Convolutional Neural Networks

A convolutional neural network (CNN)-based method to detect and localize high-density scatterers, some of which are closer than the resolution limit of delay-and-sum (DAS) beamforming, which can potentially be extended to detect highly concentrated microbubbles in order to shorten data acquisition times of super-resolution ultrasound imaging.