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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11060922PMC
http://dx.doi.org/10.1016/j.ultrasmedbio.2024.01.016DOI Listing

Publication Analysis

Top Keywords

soft attention
12
spontaneous echo
8
echo contrast
8
convolutional neural
8
neural network
8
model
8
negative false
8
auc 074
8
attention
6
automated spontaneous
4

Similar Publications

Design of pH-responsive and amphiphilic pullulan-based biological macromolecule for gene delivery.

Int J Biol Macromol

January 2025

Institute of Organic Chemistry and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldtstr. 10, D-07743 Jena, Germany; Jena Center for Soft Matters (JCSM), Friedrich Schiller University Jena, Philosophenweg 7, D-07743 Jena, Germany. Electronic address:

Nanomedicine, particularly gene delivery, holds immense potential and offers promising therapeutic options. Non-viral systems gained attention due to their binding capacity, stability and scalability. Among these, natural polysaccharides, such as pullulan, are advantageous in terms of sustainability, biocompatibility and potential degradability.

View Article and Find Full Text PDF

[This retracts the article DOI: 10.1007/s00500-022-07122-8.].

View Article and Find Full Text PDF

The textile industry is one of the main industries that benefited from the industrial revolution. Therefore, discharging of dyes from textile, paper, plastic, and rubber industries is inevitable. This colored wastewater prevents sunlight penetration and highly affects water sources.

View Article and Find Full Text PDF

Accurate monitoring of drowsy driving through electroencephalography (EEG) can effectively reduce traffic accidents. Developing a calibration-free drowsiness detection system with single-channel EEG alone is very challenging due to the non-stationarity of EEG signals, the heterogeneity among different individuals, and the relatively parsimonious compared to multi-channel EEG. Although deep learning-based approaches can effectively decode EEG signals, most deep learning models lack interpretability due to their black-box nature.

View Article and Find Full Text PDF

Objective: To improve the accuracy and explainability of skin lesion detection and classification, particularly for several types of skin cancers, through a novel approach based on the convolutional neural networks with attention-integrated customized ResNet variants (CRVs) and an optimized ensemble learning (EL) strategy.

Methods: Our approach utilizes all ResNet variants combined with three attention mechanisms: channel attention, soft attention, and squeeze-excitation attention. These attention-integrated ResNet variants are aggregated through a unique multi-level EL strategy.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!