Automated Spontaneous Echo Contrast Detection Using a Multisequence Attention Convolutional Neural Network

Authors

Ouwen Huang
Zewei Shi
Naveen Garg
Corey Jensen
Mark L Palmeri

Publication Date

6-1-2024

Journal

Ultrasound in Medicine and Biology

DOI

10.1016/j.ultrasmedbio.2024.01.016

PMID

38461036

PMCID

PMC11060922

PubMedCentral® Posted Date

6-1-2025

PubMedCentral® Full Text Version

Author MSS

Abstract

OBJECTIVE: Spontaneous echo contrast (SEC) is a vascular ultrasound finding associated with increased thromboembolism risk. However, identification requires expert determination and clinician time to report. We developed a deep learning model that can automatically identify SEC. Our model can be applied retrospectively without deviating from routine clinical practice. The retrospective nature of our model means future works could scan archival data to opportunistically correlate SEC findings with documented clinical outcomes.

METHODS: We curated a data set of 801 archival acquisitions along the femoral vein from 201 patients. We used a multisequence convolutional neural network (CNN) with ResNetv2 backbone and visualized keyframe importance using soft attention. We evaluated SEC prediction performance using an 80/20 train/test split. We report receiver operating characteristic area under the curve (ROC-AUC), along with the Youden threshold-associated sensitivity, specificity, F1 score, true negative, false negative, false positive and true positive.

RESULTS: Using soft attention, we can identify SEC with an AUC of 0.74, sensitivity of 0.73 and specificity of 0.68. Without soft attention, our model achieves an AUC of 0.69, sensitivity of 0.71 and specificity of 0.60. Additionally, we provide attention visualizations and note that our model assigns higher attention score to ultrasound frames containing more vessel lumen.

CONCLUSION: Our multisequence CNN model can identify the presence of SEC from ultrasound keyframes with an AUC of 0.74, which could enable screening applications and enable more SEC data discovery. The model does not require the expert intervention or additional clinician reporting time that are currently significant barriers to SEC adoption. Model and processed data sets are publicly available at https://github.com/Ouwen/automatic-spontaneous-echo-contrast.

Keywords

Humans, Neural Networks, Computer, Ultrasonography, Retrospective Studies, Femoral Vein, Deep Learning, Female, Sensitivity and Specificity, Male, Deep learning, Spontaneous echo contrast, Point-of-care ultrasound, Femoral vein, COVID-19, Oncology, Deep vein thrombosis, Venous thromboembolism

Published Open-Access

yes

Recommended Citation

Huang, Ouwen; Shi, Zewei; Garg, Naveen; et al., "Automated Spontaneous Echo Contrast Detection Using a Multisequence Attention Convolutional Neural Network" (2024). Faculty, Staff and Student Publications. 4425.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/4425