SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography

Autor: Wang, Jinke, Lv, Peiqing, Wang, Haiying, Shi, Changfa

Background and objective: In this paper, a modified U-Net based framework is presented, which leverages techniques from Squeeze-and-Excitation (SE) block, Atrous Spatial Pyramid Pooling (ASPP) and residual learning for accurate and robust liver CT se

Externí odkaz: http://arxiv.org/abs/2103.06419

Deep supervision and atrous inception-based U-Net combining CRF for automatic liver segmentation from CT.

Autor: Lv, Peiqing¹ (AUTHOR), Wang, Jinke^1,2 (AUTHOR) jkwang@hitwh.edu.cn, Zhang, Xiangyang¹ (AUTHOR), Shi, Changfa³ (AUTHOR)

Publikováno v: Scientific Reports. 10/10/2022, Vol. 12 Issue 1, p1-14. 14p.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

An improved residual U-Net with morphological-based loss function for automatic liver segmentation in computed tomography.

Autor: Lv P; School of Automation, Harbin University of Science and Technology, Harbin 150080, China., Wang J; School of Automation, Harbin University of Science and Technology, Harbin 150080, China.; Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China., Zhang X; School of Automation, Harbin University of Science and Technology, Harbin 150080, China., Ji C; Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China., Zhou L; School of Automation, Harbin University of Science and Technology, Harbin 150080, China., Wang H; School of Automation, Harbin University of Science and Technology, Harbin 150080, China.

Publikováno v: Mathematical biosciences and engineering : MBE [Math Biosci Eng] 2022 Jan; Vol. 19 (2), pp. 1426-1447. Date of Electronic Publication: 2021 Dec 07.