CSSegNet: Fine-Grained Cardiac Structures Segmentation Using Dilated Pyramid Pooling in U-net

TL;DR

This paper introduces CSSegNet, a novel segmentation network with dilated pyramid pooling in skip connections, improving multi-scale feature extraction for precise cardiac structure segmentation in medical images.

Contribution

The paper proposes a new network architecture with dilated pyramid pooling in skip connections, enhancing multi-scale vision and segmentation accuracy for cardiac structures.

Findings

Achieved state-of-the-art performance on MICCAI-ACDC dataset.

Improved segmentation accuracy in geometrical metrics.

Enhanced clinical evaluation metrics such as Ejection Fraction.

Abstract

Cardiac structure segmentation plays an important role in medical analysis procedures. Images' blurred boundaries issue always limits the segmentation performance. To address this difficult problem, we presented a novel network structure which embedded dilated pyramid pooling block in the skip connections between networks' encoding and decoding stage. A dilated pyramid pooling block is made up of convolutions and pooling operations with different vision scopes. Equipped the model with such module, it could be endowed with multi-scales vision ability. Together combining with other techniques, it included a multi-scales initial features extraction and a multi-resolutions' prediction aggregation module. As for backbone feature extraction network, we referred to the basic idea of Xception network which benefited from separable convolutions. Evaluated on the Post 2017 MICCAI-ACDC challenge phase data, our proposed model could achieve state-of-the-art performance in left ventricle (LVC) cavities and right ventricle cavities (RVC) segmentation tasks. Results revealed that our method has advantages on both geometrical (Dice coefficient, Hausdorff distance) and clinical evaluation (Ejection Fraction, Volume), which represent closer boundaries and more statistically significant separately.