Related Experiment Video
Updated: Nov 15, 2025
Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo
Published on: October 2, 2021
Echocardiographic image multi-structure segmentation using Cardiac-SegNet
Yang Lei1, Yabo Fu1, Justin Roper1
1Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.
Insights
This study introduces Cardiac-SegNet, a deep learning method for fast and accurate segmentation of cardiac structures in echocardiographic images, improving cardiac function assessment and disease diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiology
Background:
- Echocardiographic image segmentation is vital for cardiac function assessment and disease diagnosis.
- Challenges include low contrast, speckle noise, and manual segmentation variability.
- Automated methods are needed for efficiency and accuracy.
Purpose of the Study:
- To develop a deep learning-based method for automated multi-structure segmentation of echocardiographic images.
- To address the challenges of low contrast-to-noise ratio and speckle noise.
- To provide a faster and more accurate alternative to manual segmentation.
Main Methods:
- Developed an anchor-free mask convolutional neural network (CNN) named Cardiac-SegNet.
- Utilized a backbone, a fully convolutional one-state object detector (FCOS) head, and a mask head with spatial attention.
- Evaluated on 450 patient datasets using five-fold cross-validation and a hold-out test, segmenting left ventricle endocardium (LVEndo), epicardium (LVEpi), and left atrium (LA).
Main Results:
- Cardiac-SegNet demonstrated superior segmentation accuracy and reduced speckles compared to U-Net and Mask R-CNN.
- Achieved high average Dice Similarity Coefficients (DSC): 0.952 (LVEndo ED), 0.965 (LVEpi ED), and 0.924 (LA ED).
- Segmentation was performed rapidly, within 0.5 seconds for typical image sizes.
Conclusions:
- A fast and accurate deep learning method, Cardiac-SegNet, was developed for echocardiographic image segmentation.
- The anchor-free mask CNN approach effectively segments cardiac structures.
- This method holds promise for improved cardiac function assessment and disease diagnosis.
Purpose:
Cardiac boundary segmentation of echocardiographic images is important for cardiac function assessment and disease diagnosis. However, it is challenging to segment cardiac ventricles due to the low contrast-to-noise ratio and speckle noise of the echocardiographic images. Manual segmentation is subject to interobserver variability and is too slow for real-time image-guided interventions. We aim to develop a deep learning-based method for automated multi-structure segmentation of echocardiographic images.
Methods:
We developed an anchor-free mask convolutional neural network (CNN), termed Cardiac-SegNet, which consists of three subnetworks, that is, a backbone, a fully convolutional one-state object detector (FCOS) head, and a mask head. The backbone extracts multi-level and multi-scale features from endocardium image. The FOCS head utilizes these features to detect and label the region-of-interests (ROIs) of the segmentation targets. Unlike the traditional mask regional CNN (Mask R-CNN) method, the FCOS head is anchor-free and can model the spatial relationship of the targets. The mask head utilizes a spatial attention strategy, which allows the network to highlight salient features to perform segmentation on each detected ROI. For evaluation, we investigated 450 patient datasets by a five-fold cross-validation and a hold-out test. The endocardium (LVEndo ) and epicardium (LVEpi ) of the left ventricle and left atrium (LA) were segmented and compared with manual contours using the Dice similarity coefficient (DSC), Hausdorff distance (HD), mean absolute distance (MAD), and center-of-mass distance (CMD).
Results:
Compared to U-Net and Mask R-CNN, our method achieved higher segmentation accuracy and fewer erroneous speckles. When our method was evaluated on a separate hold-out dataset at the end diastole (ED) and the end systole (ES) phases, the average DSC were 0.952 and 0.939 at ED and ES for the LVEndo , 0.965 and 0.959 at ED and ES for the LVEpi , and 0.924 and 0.926 at ED and ES for the LA. For patients with a typical image size of 549 × 788 pixels, the proposed method can perform the segmentation within 0.5 s.
Conclusion:
We proposed a fast and accurate method to segment echocardiographic images using an anchor-free mask CNN.
Related Concept Videos
01:17Imaging Studies for Cardiovascular System I:Echocardiography
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion,...
01:20Imaging Studies for Cardiovascular System II:Types of Echocardiography
Types of Echocardiography
Transthoracic Echocardiography (TTE)
TTE is the most common type of echocardiogram which involves placing a transducer on the patient's chest, emitting sound waves to create heart images. TTE is invaluable for evaluating the heart's size, structure, and motion, making it particularly useful for...