• Chỉ mục bởi
  • Năm xuất bản

Target-aware U-Net with fuzzy skip connections for refined pancreas segmentation

Chen College of Electronics and Information Engineering, Tongji University, Shanghai, 200092, China|
Hamido (35611951900) | Xiaodong (55180828700); Fujita Reginonal Research Center, Iwate Prefectural University, Iwate, Japan| Shichen (57980360200); Yue Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain| Weiping (57193448087); Sun Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Viet Nam| Chang (57929033500); Ding School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China| Yufei (22833831100); Xu School of Information Science and Technology, Nantong University, Nantong, 226019, China|

Applied Soft Computing Số , năm 2022 (Tập 131, trang -)

ISSN: 15684946

ISSN: 15684946

DOI: 10.1016/j.asoc.2022.109818

Tài liệu thuộc danh mục:



Từ khóa: Computer aided diagnosis; Computerized tomography; Convolutional neural networks; Medical imaging; Semantic Segmentation; Semantics; Attention mechanisms; Convolutional neural network; CT volume; Fuzzy skip connection; Medical image segmentation; NET architecture; Pancreas segmentation; Target attention mechanism; U-net; Variable shape; Convolution
Tóm tắt tiếng anh
Medical image segmentation is one of the important steps in the computer-aided diagnosis of pancreas diseases. Although some models have been proposed to deal with the task of automatic pancreas segmentation, it is still challenging due to the small size, variable shape and unclear boundary of pancreas. In this paper, we propose a target-aware U-Net (tU-Net) using fuzzy skip connection for pancreas segmentation. Through adding a fuzzy skip connection module into the U-Net architecture, the low-level features can be transformed into the high-level semantic features, which facilitates the segmentation of small and changeable targets of pancreas. Based on the fuzzy feature mapping, we also design a target attention mechanism consists of global average pooling and depthwise convolution. It makes the decoder of the network more sensitive to target features by increasing weights of important channels. The proposed method is evaluated on the NIH dataset of 82 CT volumes, and the pancreas Medical Segmentation Decathlon (MSD) challenge dataset of 281 CT volumes. The proposed model achieves better results comparing with other state-of-the-art models. � 2022 Elsevier B.V.

Xem chi tiết