Show simple item record

AuthorAnsari, Mohammed Yusuf
AuthorYang, Yin
AuthorBalakrishnan, Shidin
AuthorAbinahed, Julien
AuthorAl-Ansari, Abdulla
AuthorWarfa, Mohamed
AuthorAlmokdad, Omran
AuthorBarah, Ali
AuthorOmer, Ahmed
AuthorSingh, Ajay Vikram
AuthorMeher, Pramod Kumar
AuthorBhadra, Jolly
AuthorHalabi, Osama
AuthorAzampour, Mohammad Farid
AuthorNavab, Nassir
AuthorWendler, Thomas
AuthorDakua, Sarada Prasad
Available date2023-01-11T06:37:51Z
Publication Date2022-12-01
Publication NameScientific Reports
Identifierhttp://dx.doi.org/10.1038/s41598-022-16828-6
CitationAnsari, M.Y., Yang, Y., Balakrishnan, S. et al. A lightweight neural network with multiscale feature enhancement for liver CT segmentation. Sci Rep 12, 14153 (2022). https://doi.org/10.1038/s41598-022-16828-6
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85136923717&origin=inward
URIhttp://hdl.handle.net/10576/38313
AbstractSegmentation of abdominal Computed Tomography (CT) scan is essential for analyzing, diagnosing, and treating visceral organ diseases (e.g., hepatocellular carcinoma). This paper proposes a novel neural network (Res-PAC-UNet) that employs a fixed-width residual UNet backbone and Pyramid Atrous Convolutions, providing a low disk utilization method for precise liver CT segmentation. The proposed network is trained on medical segmentation decathlon dataset using a modified surface loss function. Additionally, we evaluate its quantitative and qualitative performance; the Res16-PAC-UNet achieves a Dice coefficient of 0.950 ± 0.019 with less than half a million parameters. Alternatively, the Res32-PAC-UNet obtains a Dice coefficient of 0.958 ± 0.015 with an acceptable parameter count of approximately 1.2 million.
SponsorThis publication was made possible by NPRP-11S-1219-170106 from the Qatar National Research Fund (a member of Qatar Foundation). The findings herein reflect the work, and are solely the responsibility of the authors.
Languageen
PublisherNature Research
SubjectA lightweight neural network
liver CT segmentation
TitleA lightweight neural network with multiscale feature enhancement for liver CT segmentation
TypeArticle
Issue Number1
Volume Number12
ESSN2045-2322
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record