TC-SegNet: robust deep learning network for fully automatic two-chamber segmentation of two-dimensional echocardiography

Abstract

Heart chamber quantification is an essential clinical task to analyze heart abnormalities by evaluating the heart volume estimated through the endocardial border of the chambers. A precise heart chamber segmentation algorithm using echocardiography is essential for improving the diagnosis of cardiac disease. This paper proposes a robust two chamber segmentation network (TC-SegNet) for echocardiography which follows a U-Net architecture and effectively incorporates the proposed modified skip connection, Atrous Spatial Pyramid Pooling (ASPP) modules and squeeze and excitation modules. The TC-SegNet is evaluated on the open-source fully annotated dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS). The proposed TC-SegNet obtained an average value of F1-score of 0.91, an average Dice score of 0.9284 and an IoU score of 0.8322 which are higher than the reference models used here for comparison. Further, Pixel error (PE) of 1.5109 which are significantly less than the comparison models. The segmentation results and metrics show that the proposed model outperforms the state-of-the-art segmentation methods.

Predicting Cardiac Issues From Echocardiograms: A Literature Review Using Deep Learning and Machine Learning Techniques

“…This section examines the literature on efficient procedures and compares their performance to find out how they stack up against one another. For the cardiac image segmentation, BiSeNet [26], U-Net [30], FASTR-SCANN [32], U-Net-Transformer [33], OFHCSS [35] and U-Net-YOLOv7 [36] are considered for the evaluation. Then, CNN-ResNet [37], CNN-LSTM [41], Xception [45], 1D-CNN [46], CNN [47] and ShuffleNet [48] are taken for the cardiac view classification.…”

“…4 shows the comparison of various DL based segmentation models in terms of accuracy. It is observed that the U-Net [30] 4.05%, 2.37%, 8.63%, 20.25% and 7.95% higher than BiSeNet, FASTR-SCANN, U-Net-Transformer, OFHCSS and U-Net-YOLOv7. This results indicates that the U-Net [30] has better segmentation accuracy than other models as it employs integrates U-Net with MSC, ASPP and SEM.…”

“…It is observed that the U-Net [30] 4.05%, 2.37%, 8.63%, 20.25% and 7.95% higher than BiSeNet, FASTR-SCANN, U-Net-Transformer, OFHCSS and U-Net-YOLOv7. This results indicates that the U-Net [30] has better segmentation accuracy than other models as it employs integrates U-Net with MSC, ASPP and SEM. The model includes an encoder, bridge and decoder for echocardiogram segmentation extracting multiple scale features through convolutional layers, and incorporating MSC to reduce path size and convolutional blocks.…”

“…Lal [30] developed an automatic two-chamber segmentation model called TC-Signets for echocardiography. This model integrates U-Net with modified skip connection (MSC), Atrous Spatial Pyramid Pooling (ASPP) modules, squeeze and excitation modules (SEM).…”