DCD: A Semantic Segmentation Model for Fetal Ultrasound Four-Chamber View
This work addresses the need for automated segmentation to reduce sonographer workload and enhance early diagnosis of congenital heart disease in fetal echocardiography, representing an incremental improvement in domain-specific medical imaging.
The paper tackles the problem of accurately segmenting anatomical structures in fetal ultrasound four-chamber views, which is challenging due to artifacts and variability, by proposing the DCD model that incorporates Dense ASPP and CBAM modules to achieve precise and robust segmentation for improved prenatal cardiac assessment.
Accurate segmentation of anatomical structures in the apical four-chamber (A4C) view of fetal echocardiography is essential for early diagnosis and prenatal evaluation of congenital heart disease (CHD). However, precise segmentation remains challenging due to ultrasound artifacts, speckle noise, anatomical variability, and boundary ambiguity across different gestational stages. To reduce the workload of sonographers and enhance segmentation accuracy, we propose DCD, an advanced deep learning-based model for automatic segmentation of key anatomical structures in the fetal A4C view. Our model incorporates a Dense Atrous Spatial Pyramid Pooling (Dense ASPP) module, enabling superior multi-scale feature extraction, and a Convolutional Block Attention Module (CBAM) to enhance adaptive feature representation. By effectively capturing both local and global contextual information, DCD achieves precise and robust segmentation, contributing to improved prenatal cardiac assessment.