Fully Automated Spleen Localization And Segmentation Using Machine Learning And 3D Active Contours

Alexander Wood; S M Reza Soroushmehr; Negar Farzaneh; David Fessell; Kevin R Ward; Jonathan Gryak; Delaram Kahrobaei; Kayvan Na

doi:10.1109/EMBC.2018.8512182

Fully Automated Spleen Localization And Segmentation Using Machine Learning And 3D Active Contours

Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul:2018:53-56. doi: 10.1109/EMBC.2018.8512182.

Authors

Alexander Wood, S M Reza Soroushmehr, Negar Farzaneh, David Fessell, Kevin R Ward, Jonathan Gryak, Delaram Kahrobaei, Kayvan Na

PMID: 30440339
DOI: 10.1109/EMBC.2018.8512182

Abstract

Automated segmentation of the spleen in CT volumes is difficult due to variations in size, shape, and position of the spleen within the abdominal cavity as well as similarity of intensity values among organs in the abdominal cavity. In this paper we present a method for automated localization and segmentation of the spleen within axial abdominal CT volumes using trained classification models, active contours, anatomical information, and adaptive features. The results show an average Dice score of 0.873 on patients experiencing various chest, abdominal, and pelvic traumas taken at different contrast phases.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Abdomen
Algorithms
Humans
Imaging, Three-Dimensional* / methods
Machine Learning*
Spleen* / anatomy & histology
Spleen* / diagnostic imaging
Thorax
Tomography, X-Ray Computed* / methods