Final published version
Licence: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - UDT
T2 - U-shaped deformable transformer for subarachnoid haemorrhage image segmentation
AU - Xie, Wei
AU - Jin, Lianghao
AU - Hua, Shiqi
AU - Sun, Hao
AU - Sun, Bo
AU - Tu, Zhigang
AU - Liu, Jun
N1 - Publisher Copyright: © 2024 The Authors. CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.
PY - 2024/6/30
Y1 - 2024/6/30
N2 - Subarachnoid haemorrhage (SAH), mostly caused by the rupture of intracranial aneurysm, is a common disease with a high fatality rate. SAH lesions are generally diffusely distributed, showing a variety of scales with irregular edges. The complex characteristics of lesions make SAH segmentation a challenging task. To cope with these difficulties, a u-shaped deformable transformer (UDT) is proposed for SAH segmentation. Specifically, first, a multi-scale deformable attention (MSDA) module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions, where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale features. Second, the cross deformable attention-based skip connection (CDASC) module is designed to model the irregular edge characteristic of SAH lesions, where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder features. Third, the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed UDT. Extensive experiments are conducted on the self-built SAH-CT dataset and two public medical datasets (GlaS and MoNuSeg). Experimental results show that the presented UDT achieves the state-of-the-art performance.
AB - Subarachnoid haemorrhage (SAH), mostly caused by the rupture of intracranial aneurysm, is a common disease with a high fatality rate. SAH lesions are generally diffusely distributed, showing a variety of scales with irregular edges. The complex characteristics of lesions make SAH segmentation a challenging task. To cope with these difficulties, a u-shaped deformable transformer (UDT) is proposed for SAH segmentation. Specifically, first, a multi-scale deformable attention (MSDA) module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions, where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale features. Second, the cross deformable attention-based skip connection (CDASC) module is designed to model the irregular edge characteristic of SAH lesions, where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder features. Third, the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed UDT. Extensive experiments are conducted on the self-built SAH-CT dataset and two public medical datasets (GlaS and MoNuSeg). Experimental results show that the presented UDT achieves the state-of-the-art performance.
KW - image segmentation
KW - medical image processing
U2 - 10.1049/cit2.12302
DO - 10.1049/cit2.12302
M3 - Journal article
AN - SCOPUS:85189502648
VL - 9
SP - 756
EP - 768
JO - CAAI Transactions on Intelligence Technology
JF - CAAI Transactions on Intelligence Technology
SN - 2468-6557
IS - 3
ER -