Registration is open - make plans to attend
Get pricing and details
>
Conference 12033 > Paper 12033-78
Paper 12033-78

Multi-class prediction for improving intestine segmentation on non-fecal-tagged CT volume

In person: 23 February 2022 • 5:30 PM - 7:00 PM PST

Abstract

This paper proposes a segmentation method of the intestines (both the small and the large intestines) from CT volumes. Although our previous method introduced 2D distance map estimation for preventing incorrect shortcuts between adjacent regions, incorrect shortcuts between air-filled regions are often generated. Furthermore, regions generated by the Watershed algorithm were sometimes tiny. We solve those problems by a multi-class segmentation and 3D distance transformation. Experiments using 110 CT volumes showed that our proposed method successfully prevented those problems.

Presenter

Nagoya Univ. (Japan)
Hirohisa Oda received his Ph. D. degree from Nagoya University in 2021. His research interests are the computer-aided diagnosis for the chest and abdomen, and image processing of cardiac micro-focus X-ray CT.
Presenter/Author
Nagoya Univ. (Japan)
Author
Nagoya Univ. (Japan)
Author
Aichi Institute of Technology (Japan)
Author
Nagoya Univ. (Japan)
Author
Nagoya Univ. (Japan)
Author
Nagoya Univ. (Japan)
Author
Aichi Medical Univ. (Japan)
Author
Nagoya Univ. (Japan)
Author
Nagoya Univ. (Japan)