Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound

Alexander Hann, Lucas Bettac, Mark M Haenle, Tilmann Graeter, Andreas W Berger, Jens Dreyhaupt, Dieter Schmalstieg, Wolfram G Zoller, Jan Egger

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90% of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80%. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.

Original languageEnglish
Pages (from-to)12779
JournalScientific reports
Volume7
Issue number1
DOIs
Publication statusPublished - 6 Oct 2017

Fingerprint

Liver Neoplasms
Pancreatic Neoplasms
Neoplasm Metastasis
Liver

Keywords

  • Journal Article

Cite this

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound. / Hann, Alexander; Bettac, Lucas; Haenle, Mark M; Graeter, Tilmann; Berger, Andreas W; Dreyhaupt, Jens; Schmalstieg, Dieter; Zoller, Wolfram G; Egger, Jan.

In: Scientific reports, Vol. 7, No. 1, 06.10.2017, p. 12779.

Research output: Contribution to journalArticleResearchpeer-review

Hann, A, Bettac, L, Haenle, MM, Graeter, T, Berger, AW, Dreyhaupt, J, Schmalstieg, D, Zoller, WG & Egger, J 2017, 'Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound' Scientific reports, vol. 7, no. 1, pp. 12779. https://doi.org/10.1038/s41598-017-12925-z
Hann A, Bettac L, Haenle MM, Graeter T, Berger AW, Dreyhaupt J et al. Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound. Scientific reports. 2017 Oct 6;7(1):12779. https://doi.org/10.1038/s41598-017-12925-z
Hann, Alexander ; Bettac, Lucas ; Haenle, Mark M ; Graeter, Tilmann ; Berger, Andreas W ; Dreyhaupt, Jens ; Schmalstieg, Dieter ; Zoller, Wolfram G ; Egger, Jan. / Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound. In: Scientific reports. 2017 ; Vol. 7, No. 1. pp. 12779.
@article{7edcab2d835a44fea8e78defbf0727c4,
title = "Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound",
abstract = "Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90{\%} of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80{\%}. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.",
keywords = "Journal Article",
author = "Alexander Hann and Lucas Bettac and Haenle, {Mark M} and Tilmann Graeter and Berger, {Andreas W} and Jens Dreyhaupt and Dieter Schmalstieg and Zoller, {Wolfram G} and Jan Egger",
year = "2017",
month = "10",
day = "6",
doi = "10.1038/s41598-017-12925-z",
language = "English",
volume = "7",
pages = "12779",
journal = "Scientific reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound

AU - Hann, Alexander

AU - Bettac, Lucas

AU - Haenle, Mark M

AU - Graeter, Tilmann

AU - Berger, Andreas W

AU - Dreyhaupt, Jens

AU - Schmalstieg, Dieter

AU - Zoller, Wolfram G

AU - Egger, Jan

PY - 2017/10/6

Y1 - 2017/10/6

N2 - Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90% of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80%. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.

AB - Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90% of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80%. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.

KW - Journal Article

U2 - 10.1038/s41598-017-12925-z

DO - 10.1038/s41598-017-12925-z

M3 - Article

VL - 7

SP - 12779

JO - Scientific reports

JF - Scientific reports

SN - 2045-2322

IS - 1

ER -