Echocardiographic image multi-structure segmentation using Cardiac-SegNet.

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 (LV_Endo), epicardium (LV_Epi), 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 (LV_Endo ED), 0.965 (LV_Epi 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.