mm3DSNet: multi-scale and multi-feedforward self-attention 3D segmentation network for CT scans of hepatobiliary ducts

• Published in: Medical & biological engineering & computing Vol. 63; no. 1; pp. 127 - 138
• Main Authors: Zhou, Yinghong, Xie, Yiying, Cai, Nian, Liang, Yuchen, Gong, Ruifeng, Wang, Ping
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2025; Springer Nature B.V
• Subjects: Algorithms; Attention; Bile Ducts - diagnostic imaging; Biomedical and Life Sciences; Biomedical engineering; Biomedical Engineering and Bioengineering; Biomedicine; Computed tomography; Computer Applications; design; Ducts; Encoders-Decoders; Entropy; Feature extraction; Human Physiology; Humans; Image processing; Image reconstruction; Image segmentation; Imaging; Imaging, Three-Dimensional - methods; Liver - diagnostic imaging; Medical imaging; Neural Networks, Computer; Original Article; planning; Radiology; Semantics; Tomography, X-Ray Computed - methods; trees; wells; Deep learning; Multi-scale fusion; Segmentation; Hepatobiliary duct CT scans
• ISSN: 0140-0118; 1741-0444; 1741-0444
• DOI: 10.1007/s11517-024-03183-z

Image segmentation is a key step of the 3D reconstruction of the hepatobiliary duct tree, which is significant for preoperative planning. In this paper, a novel 3D U-Net variant is designed for CT image segmentation of hepatobiliary ducts from the abdominal CT scans, which is composed of a 3D encoder-decoder and a 3D multi-feedforward self-attention module (MFSAM). To well sufficient semantic and spatial features with high inference speed, the 3D ConvNeXt block is designed as the 3D extension of the 2D ConvNeXt. To improve the ability of semantic feature extraction, the MFSAM is designed to transfer the semantic and spatial features at different scales from the encoder to the decoder. Also, to balance the losses for the voxels and the edges of the hepatobiliary ducts, a boundary-aware overlap cross-entropy loss is proposed by combining the cross-entropy loss, the Dice loss, and the boundary loss. Experimental results indicate that the proposed method is superior to some existing deep networks as well as the radiologist without rich experience in terms of CT segmentation of hepatobiliary ducts, with a segmentation performance of 76.54% Dice and 6.56 HD. Graphical Abstract