What is the clinical evidence from this study?

Study design: Other. Population: Echocardiographic imaging (n=170311). Intervention: Multi-task deep learning model vs. Expert annotations. Primary outcome: Overall view classification accuracy (95% CI 97.7-98.0).

September 3, 2024Open Access

A multi-task deep learning approach for real-time view classification and quality assessment of echocardiographic images

XLXinyu LiNorthwest A&F University HZHongmei ZhangZhengzhou University of Science and Technology JYJing YueSouthwest Petroleum University

Key Result

The multi-task deep learning model achieved an overall view classification accuracy of 97.8% and a mean absolute error of 6.54 for image quality assessment on the test set.

Structured PICO

Does a multi-task deep learning model accurately classify echocardiographic views and assess image quality in real-time compared to expert annotations?

Population

170,311 echocardiographic images from adults aged 18 and older, excluding those with severe cardiac malformations, were used to develop and evaluate a deep learning model.

Intervention

Multi-task deep learning model (VGG16 backbone with Vision Transformer Block and Adaptive Feature Fusion Block) for real-time multi-view classification (six standard views and 'others') and image quality assessment.

Comparator

Expert annotations (for ground truth) and alternative CNN architectures (MobileNetV3, DenseNet121, EfficientNet, ResNet50, ConvNeXt).

Outcome

Overall view classification accuracy and image quality assessment error (Mean Absolute Error) on the test set.surrogate

A multi-task deep learning model can accurately and rapidly classify echocardiographic views and assess image quality, potentially standardizing clinical image acquisition and improving AI-assisted diagnosis.

Limitations

The standard views covered are limited, and commonly used apical series views such as the apical 2-chamber and apical 3-chamber need to be further incorporated.
The method generates an overall quality score for echocardiographic images, and the individual scoring of different quality attributes should be explored in future research.
Although the model was developed with a diverse dataset, its robustness and reliability still necessitate further validation in real-world clinical settings.

Abstract

High-quality standard views in two-dimensional echocardiography are essential for accurate cardiovascular disease diagnosis and treatment decisions. However, the quality of echocardiographic images is highly dependent on the practitioner's experience. Ensuring timely quality control of echocardiographic images in the clinical setting remains a significant challenge. In this study, we aimed to propose new quality assessment criteria and develop a multi-task deep learning model for real-time multi-view classification and image quality assessment (six standard views and "others"). A total of 170,311 echocardiographic images collected between 2015 and 2022 were utilized to develop and evaluate the model. On the test set, the model achieved an overall classification accuracy of 97.8% (95%CI 97.7-98.0) and a mean absolute error of 6.54 (95%CI 6.43-6.66). A single-frame inference time of 2.8 ms was achieved, meeting real-time requirements. We also analyzed pre-stored images from three distinct groups of echocardiographers (junior, senior, and expert) to evaluate the clinical feasibility of the model. Our multi-task model can provide objective, reproducible, and clinically significant view quality assessment results for echocardiographic images, potentially optimizing the clinical image acquisition process and improving AI-assisted diagnosis accuracy.

AI에게 질문

Bookmark

View Full Paper