Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches

Negar Farzaneh, Samuel Habbo-Gavin, S. M.Reza Soroushmehr, Hirenkumar Patel, David P. Fessell, Kevin R. Ward, Kayvan Najarian

Research output: ResearchConference contribution

Abstract

Traumas and illnesses can cause injury in internal organs. The liver, being the largest abdominal organ, is most likely to be injured by trauma. Currently CT scans are analyzed by radiologists to see if there is any injuries in organs; however, due to the large amounts of data and its complexity in terms of noise, intensity variations in different images and so on, visual inspection would be time consuming and prone of error. Therefore, an automated approach would be beneficial. In this paper we propose a fully automated Bayesian based method for 3D segmentation of the liver. Experimental results show that the proposed method can achieve high performance with Dice and Jaccard similarity coefficients of 93:5% and 87:9% respectively.

LanguageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1093-1097
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Liver
Computerized tomography
Inspection

Keywords

  • Abdominal injuries
  • Adaptive threshold
  • Image segmentation
  • Liver segmentation
  • Probabilistic atlas
  • Superpixel

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Farzaneh, N., Habbo-Gavin, S., Soroushmehr, S. M. R., Patel, H., Fessell, D. P., Ward, K. R., & Najarian, K. (2017). Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 1093-1097). [7952325] Institute of Electrical and Electronics Engineers Inc.. DOI: 10.1109/ICASSP.2017.7952325

Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches. / Farzaneh, Negar; Habbo-Gavin, Samuel; Soroushmehr, S. M.Reza; Patel, Hirenkumar; Fessell, David P.; Ward, Kevin R.; Najarian, Kayvan.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1093-1097 7952325.

Research output: ResearchConference contribution

Farzaneh, N, Habbo-Gavin, S, Soroushmehr, SMR, Patel, H, Fessell, DP, Ward, KR & Najarian, K 2017, Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952325, Institute of Electrical and Electronics Engineers Inc., pp. 1093-1097, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. DOI: 10.1109/ICASSP.2017.7952325
Farzaneh N, Habbo-Gavin S, Soroushmehr SMR, Patel H, Fessell DP, Ward KR et al. Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc.2017. p. 1093-1097. 7952325. Available from, DOI: 10.1109/ICASSP.2017.7952325
Farzaneh, Negar ; Habbo-Gavin, Samuel ; Soroushmehr, S. M.Reza ; Patel, Hirenkumar ; Fessell, David P. ; Ward, Kevin R. ; Najarian, Kayvan. / Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1093-1097
@inbook{fe8c3489728249e1bca137035210c1a2,
title = "Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches",
abstract = "Traumas and illnesses can cause injury in internal organs. The liver, being the largest abdominal organ, is most likely to be injured by trauma. Currently CT scans are analyzed by radiologists to see if there is any injuries in organs; however, due to the large amounts of data and its complexity in terms of noise, intensity variations in different images and so on, visual inspection would be time consuming and prone of error. Therefore, an automated approach would be beneficial. In this paper we propose a fully automated Bayesian based method for 3D segmentation of the liver. Experimental results show that the proposed method can achieve high performance with Dice and Jaccard similarity coefficients of 93:5% and 87:9% respectively.",
keywords = "Abdominal injuries, Adaptive threshold, Image segmentation, Liver segmentation, Probabilistic atlas, Superpixel",
author = "Negar Farzaneh and Samuel Habbo-Gavin and Soroushmehr, {S. M.Reza} and Hirenkumar Patel and Fessell, {David P.} and Ward, {Kevin R.} and Kayvan Najarian",
year = "2017",
month = "6",
doi = "10.1109/ICASSP.2017.7952325",
pages = "1093--1097",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - CHAP

T1 - Atlas based 3D liver segmentation using adaptive thresholding and superpixel approaches

AU - Farzaneh,Negar

AU - Habbo-Gavin,Samuel

AU - Soroushmehr,S. M.Reza

AU - Patel,Hirenkumar

AU - Fessell,David P.

AU - Ward,Kevin R.

AU - Najarian,Kayvan

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Traumas and illnesses can cause injury in internal organs. The liver, being the largest abdominal organ, is most likely to be injured by trauma. Currently CT scans are analyzed by radiologists to see if there is any injuries in organs; however, due to the large amounts of data and its complexity in terms of noise, intensity variations in different images and so on, visual inspection would be time consuming and prone of error. Therefore, an automated approach would be beneficial. In this paper we propose a fully automated Bayesian based method for 3D segmentation of the liver. Experimental results show that the proposed method can achieve high performance with Dice and Jaccard similarity coefficients of 93:5% and 87:9% respectively.

AB - Traumas and illnesses can cause injury in internal organs. The liver, being the largest abdominal organ, is most likely to be injured by trauma. Currently CT scans are analyzed by radiologists to see if there is any injuries in organs; however, due to the large amounts of data and its complexity in terms of noise, intensity variations in different images and so on, visual inspection would be time consuming and prone of error. Therefore, an automated approach would be beneficial. In this paper we propose a fully automated Bayesian based method for 3D segmentation of the liver. Experimental results show that the proposed method can achieve high performance with Dice and Jaccard similarity coefficients of 93:5% and 87:9% respectively.

KW - Abdominal injuries

KW - Adaptive threshold

KW - Image segmentation

KW - Liver segmentation

KW - Probabilistic atlas

KW - Superpixel

UR - http://www.scopus.com/inward/record.url?scp=85023746408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023746408&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952325

DO - 10.1109/ICASSP.2017.7952325

M3 - Conference contribution

SP - 1093

EP - 1097

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -