Abstract
This paper proposes an intestine segmentation method from CT volumes for the intestinal obstruction and the ileus diagnosis assistance. The previous method was built based on the 3D U-Net, whose computational cost was high. Nevertheless, there was no confirmation that the 3-dimensional network contributed to the segmentation performance. In this paper, we propose a method utilizing the 2D U-Net on behalf of the previous methods’ 3D U-Net. Experimental results using 110 CT volumes showed that both the proposed (2D U-Net) and previous (3D U-Net) methods achieved similar scores for the segmentation accuracy and system usefulness. In addition, the proposed method’s inference was 0.5 min on average, around 8-times faster than the 3D U-Net’s. Although subsequent processes still require more than 20 min for each case, utilizing lightweight networks is essential for practical use in the future, especially for emergency diagnosis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shah, Z.K., Uppot, R.N., Wargo, J.A., Hahn, P.F., Sahani, D.V.: Small bowel obstruction: the value of coronal reformatted images from 16-multidetector computed tomography-a clinicoradiological perspective. J. Comput. Assist. Tomogr. 32(1), 23–31 (2008)
Sainani, N.I., Näppi, J., Sahani, D.V., Yoshida, H.: Computer-aided detection of small bowel strictures for emergency radiology in CT enterography. In: Yoshida, H., Cai, W. (eds.) ABD-MICCAI 2010. LNCS, vol. 6668, pp. 91–97. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25719-3_13
Zhang, W., Liu, J., Yao, J., Louie, A., Nguyen, T.B., Wank, S., Nowinski, W.L., Summers, R.M.: Mesenteric vasculature-guided small bowel segmentation on 3-D CT. IEEE Trans. Med. Imaging 32(11), 2006–2021 (2013)
Shin, S.Y., Lee, S., Elton, D., Gulley, J.L., Summers, R.M., et al.: Deep small bowel segmentation with cylindrical topological constraints. In: Martel, A.L. (ed.) MICCAI 2020. LNCS, vol. 12264, pp. 207–215. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_21
Oda, H., et al.: Intestinal region reconstruction of ileus cases from 3D CT images based on graphical representation and its visualization. In: Medical Imaging 2021: Computer-Aided Diagnosis, vol. 11597, p. 115971N. International Society for Optics and Photonics (2021)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Acknowledgments
Parts of this work were supported by the Hori Sciences and Arts Foundation, MEXT/JSPS KAKENHI (17H00867, 17K20099, 26108006, 26560255), JSPS Bilateral Joint Research Project, AMED (JP19lk1010036, JP20lk1010036), and JST CREST (JPMJCR20D5).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Oda, H. et al. (2021). Intestine Segmentation with Small Computational Cost for Diagnosis Assistance of Ileus and Intestinal Obstruction. In: Oyarzun Laura, C., et al. Clinical Image-Based Procedures, Distributed and Collaborative Learning, Artificial Intelligence for Combating COVID-19 and Secure and Privacy-Preserving Machine Learning. DCL PPML LL-COVID19 CLIP 2021 2021 2021 2021. Lecture Notes in Computer Science(), vol 12969. Springer, Cham. https://doi.org/10.1007/978-3-030-90874-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-90874-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90873-7
Online ISBN: 978-3-030-90874-4
eBook Packages: Computer ScienceComputer Science (R0)