Related Experiment Video
Updated: Sep 23, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Cardiac Segmentation Method Based on Domain Knowledge
Yingni Wang1, Wenbin Chen2, Tianhong Tang2
1Graduate School at Shenzhen, Tsinghua University, Shenzhen, China.
Insights
This study introduces FAUet, a fast and accurate deep learning framework for echocardiographic cardiac segmentation. The novel method improves segmentation accuracy for key cardiac structures, overcoming challenges like noise and manual variability.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Cardiology
Background:
- Echocardiography is vital for cardiovascular disease diagnosis.
- Manual cardiac segmentation is time-consuming and prone to variability.
- Image artifacts like shadows and speckle noise complicate echocardiographic analysis.
Purpose of the Study:
- To develop a fast and accurate automatic cardiac segmentation framework for echocardiography.
- To enhance segmentation performance by integrating novel deep learning components.
- To validate the proposed method on diverse echocardiographic datasets.
Main Methods:
- A novel segmentation framework, FAUet, combining U-Net with coordinate attention and VGG19-based domain feature loss.
- Utilized a dataset of 88 two-dimensional echocardiograms (2DE) from Philips and Mindray devices.
- Employed Gradient-weighted Class Activation Mapping (Grad-CAM) for result interpretability.
Main Results:
- FAUet achieved high mean Dice Scores: 0.932 (LV), 0.848 (IVS), and 0.868 (PLVW), with an overall average of 0.883.
- The method demonstrated robustness across different ultrasound devices.
- FAUet significantly outperformed traditional U-Net in segmentation accuracy and efficiency.
Conclusions:
- The proposed FAUet framework offers a fast, accurate, and reliable solution for echocardiographic cardiac segmentation.
- Integration of coordinate attention and domain feature loss enhances U-Net's performance for complex cardiac imaging tasks.
- This AI-driven approach has the potential to streamline clinical workflows and improve diagnostic consistency.
Abstract:
Echocardiography plays an important role in the clinical diagnosis of cardiovascular diseases. Cardiac function assessment by echocardiography is a crucial process in daily cardiology. However, cardiac segmentation in echocardiography is a challenging task due to shadows and speckle noise. The traditional manual segmentation method is a time-consuming process and limited by inter-observer variability. In this paper, we present a fast and accurate echocardiographic automatic segmentation framework based on Convolutional neural networks (CNN). We propose FAUet, a segmentation method serially integrated U-Net with coordinate attention mechanism and domain feature loss from VGG19 pre-trained on the ImageNet dataset. The coordinate attention mechanism can capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other spatial direction. And the domain feature loss is more concerned with the topology of cardiac structures by exploiting their higher-level features. In this research, we use a two-dimensional echocardiogram (2DE) of 88 patients from two devices, Philips Epiq 7C and Mindray Resona 7T, to segment the left ventricle (LV), interventricular septal (IVS), and posterior left ventricular wall (PLVW). We also draw the gradient weighted class activation mapping (Grad-CAM) to improve the interpretability of the segmentation results. Compared with the traditional U-Net, the proposed segmentation method shows better performance. The mean Dice Score Coefficient (Dice) of LV, IVS, and PLVW of FAUet can achieve 0.932, 0.848, and 0.868, and the average Dice of the three objects can achieve 0.883. Statistical analysis showed that there is no significant difference between the segmentation results of the two devices. The proposed method can realize fast and accurate segmentation of 2DE with a low time cost. Combining coordinate attention module and feature loss with the original U-Net framework can significantly increase the performance of the algorithm.
More Related Videos
12:08From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
Published on: August 13, 2014
09:15Displacement Analysis of Myocardial Mechanical Deformation DIAMOND Reveals Segmental Heterogeneity of Cardiac Function in Embryonic Zebrafish
Published on: February 6, 2020