Display options
Cite
Araújo JDL, da Cruz LB, Diniz JOB, et al. Liver segmentation from computed tomography images using cascade deep learning. Comput Biol Med. 2021;140:105095doi: 10.1016/j.compbiomed.2021.105095.
Araújo, J. D. L., da Cruz, L. B., Diniz, J. O. B., Ferreira, J. L., Silva, A. C., de Paiva, A. C., & Gattass, M. (2021). Liver segmentation from computed tomography images using cascade deep learning. Computers in biology and medicine, 140105095. https://doi.org/10.1016/j.compbiomed.2021.105095
Araújo, José Denes Lima, et al. "Liver segmentation from computed tomography images using cascade deep learning." Computers in biology and medicine vol. 140 (2021): 105095. doi: https://doi.org/10.1016/j.compbiomed.2021.105095
Araújo JDL, da Cruz LB, Diniz JOB, Ferreira JL, Silva AC, de Paiva AC, Gattass M. Liver segmentation from computed tomography images using cascade deep learning. Comput Biol Med. 2021 Dec 01;140:105095. doi: 10.1016/j.compbiomed.2021.105095. Epub 2021 Dec 01. PMID: 34902610.
Copy Download .nbib Format: NLM
Share it on

Comput Biol Med. 2021 Dec 01;140:105095. doi: 10.1016/j.compbiomed.2021.105095. Epub 2021 Dec 01.

Liver segmentation from computed tomography images using cascade deep learning.

Computers in biology and medicine

José Denes Lima Araújo, Luana Batista da Cruz, João Otávio Bandeira Diniz, Jonnison Lima Ferreira, Aristófanes Corrêa Silva, Anselmo Cardoso de Paiva, Marcelo Gattass

Affiliations

  1. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil. Electronic address: [email protected].
  2. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil. Electronic address: [email protected].
  3. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil; Federal Institute of Maranhão, BR-226, SN, Campus Grajaú, Vila Nova, 65?940-000, Grajaú, MA, Brazil. Electronic address: [email protected].
  4. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil; Federal Institute of Amazonas, Rua Santos Dumont, SN, Campus Tabatinga, Vila Verde, 69?640-000, Tabatinga, AM, Brazil. Electronic address: [email protected].
  5. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil. Electronic address: [email protected].
  6. Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, 65?085-580, São Luís, MA, Brazil. Electronic address: [email protected].
  7. Pontifical Catholic University of Rio de Janeiro, R. São Vicente, 225, Gávea, 22?453-900, Rio de Janeiro, RJ, Brazil. Electronic address: [email protected].

PMID: 34902610 DOI: 10.1016/j.compbiomed.2021.105095

Abstract

BACKGROUND: Liver segmentation is a fundamental step in the treatment planning and diagnosis of liver cancer. However, manual segmentation of liver is time-consuming because of the large slice quantity and subjectiveness associated with the specialist's experience, which can lead to segmentation errors. Thus, the segmentation process can be automated using computational methods for better time efficiency and accuracy. However, automatic liver segmentation is a challenging task, as the liver can vary in shape, ill-defined borders, and lesions, which affect its appearance. We aim to propose an automatic method for liver segmentation using computed tomography (CT) images.

METHODS: The proposed method, based on deep convolutional neural network models and image processing techniques, comprise of four main steps: (1) image preprocessing, (2) initial segmentation, (3) reconstruction, and (4) final segmentation.

RESULTS: We evaluated the proposed method using 131 CT images from the LiTS image base. An average sensitivity of 95.45%, an average specificity of 99.86%, an average Dice coefficient of 95.64%, an average volumetric overlap error (VOE) of 8.28%, an average relative volume difference (RVD) of -0.41%, and an average Hausdorff distance (HD) of 26.60 mm were achieved.

CONCLUSIONS: This study demonstrates that liver segmentation, even when lesions are present in CT images, can be efficiently performed using a cascade approach and including a reconstruction step based on deep convolutional neural networks.

Copyright © 2021 Elsevier Ltd. All rights reserved.

Keywords: Computed tomography; Convolutional neural networks; Deep learning; Liver cancer; Liver segmentation

Publication Types