Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Kawamoto, Satomi [VerfasserIn]   i
 Zhu, Zhuotun [VerfasserIn]   i
 Chu, Linda C. [VerfasserIn]   i
 Javed, Ammar A. [VerfasserIn]   i
 Kinny-Köster, Benedict [VerfasserIn]   i
 Wolfgang, Christopher L. [VerfasserIn]   i
 Hruban, Ralph H. [VerfasserIn]   i
 Kinzler, Kenneth W. [VerfasserIn]   i
 Fouladi, Daniel Fadaei [VerfasserIn]   i
 Blanco, Alejandra [VerfasserIn]   i
 Shayesteh, Shahab [VerfasserIn]   i
 Fishman, Elliot K. [VerfasserIn]   i
Titel:Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT
Titelzusatz:evaluation of global and local accuracies
Verf.angabe:Satomi Kawamoto, Zhuotun Zhu, Linda C. Chu, Ammar A. Javed, Benedict Kinny-Köster, Christopher L. Wolfgang, Ralph H. Hruban, Kenneth W. Kinzler, Daniel Fadaei Fouladi, Alejandra Blanco, Shahab Shayesteh, Elliot K. Fishman
E-Jahr:2024
Jahr:February 2024
Umfang:11 S.
Fussnoten:Gesehen am 15.10.2024 ; Online veröffentlicht: 15. Dezember 2023
Titel Quelle:Enthalten in: Abdominal radiology
Ort Quelle:[Boston, MA] : Springer US, 2016
Jahr Quelle:2024
Band/Heft Quelle:49(2024), 2 vom: Feb., Seite 501-511
ISSN Quelle:2366-0058
Abstract:PurposeDelay in diagnosis can contribute to poor outcomes in pancreatic ductal adenocarcinoma (PDAC), and new tools for early detection are required. Recent application of artificial intelligence to cancer imaging has demonstrated great potential in detecting subtle early lesions. The aim of the study was to evaluate global and local accuracies of deep neural network (DNN) segmentation of normal and abnormal pancreas with pancreatic mass.MethodsOur previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas.ResultsForty-two normal and 49 abnormal CTs were assessed. Average DSC was 87.4 +/- 3.1% and 85.5 +/- 3.2%, ASSD 0.97 +/- 0.30 and 1.34 +/- 0.65, HD95 4.28 +/- 2.36 and 6.31 +/- 6.31 for normal and abnormal pancreas, respectively. Semi-quantitatively, >= 95% of pancreas volume was correctly segmented in 95.2% and 53.1% of normal and abnormal pancreas by both radiologists, and 97.6% and 75.5% by at least one radiologist. Most common segmentation errors were made on pancreatic and duodenal borders in both groups, and related to pancreatic tumor including duct dilatation, atrophy, tumor infiltration and collateral vessels.ConclusionPancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.
DOI:doi:10.1007/s00261-023-04122-6
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext: https://doi.org/10.1007/s00261-023-04122-6
 Volltext: https://link.springer.com/article/10.1007/s00261-023-04122-6
 DOI: https://doi.org/10.1007/s00261-023-04122-6
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:CT
 Deep neural network segmentation
 Manual segmentation
 Pancreas
 Pancreatic ductal adenocarcinoma
K10plus-PPN:1905731884
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69262582   QR-Code
zum Seitenanfang