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.
Originalsprache | englisch |
---|---|
Seiten (von - bis) | 12779 |
Fachzeitschrift | Scientific reports |
Jahrgang | 7 |
Ausgabenummer | 1 |
DOIs | |
Publikationsstatus | Veröffentlicht - 6 Okt 2017 |
Fingerprint
Schlagwörter
Dies zitieren
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, Jahrgang 7, Nr. 1, 06.10.2017, S. 12779.Publikation: Beitrag in einer Fachzeitschrift › Artikel › Forschung › Begutachtung
}
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 -