Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies

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 stu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kawamoto, Satomi (VerfasserIn) , Zhu, Zhuotun (VerfasserIn) , Chu, Linda C. (VerfasserIn) , Javed, Ammar A. (VerfasserIn) , Kinny-Köster, Benedict (VerfasserIn) , Wolfgang, Christopher L. (VerfasserIn) , Hruban, Ralph H. (VerfasserIn) , Kinzler, Kenneth W. (VerfasserIn) , Fouladi, Daniel Fadaei (VerfasserIn) , Blanco, Alejandra (VerfasserIn) , Shayesteh, Shahab (VerfasserIn) , Fishman, Elliot K. (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: February 2024
In: Abdominal radiology
Year: 2024, Jahrgang: 49, Heft: 2, Pages: 501-511
ISSN:2366-0058
DOI:10.1007/s00261-023-04122-6
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1007/s00261-023-04122-6
Verlag, lizenzpflichtig, Volltext: https://link.springer.com/article/10.1007/s00261-023-04122-6
Volltext
Verfasserangaben: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

MARC

LEADER 00000caa a2200000 c 4500
001 1905731884
003 DE-627
005 20241205181303.0
007 cr uuu---uuuuu
008 241015s2024 xx |||||o 00| ||eng c
024 7 |a 10.1007/s00261-023-04122-6  |2 doi 
035 |a (DE-627)1905731884 
035 |a (DE-599)KXP1905731884 
035 |a (OCoLC)1475315753 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Kawamoto, Satomi  |e VerfasserIn  |0 (DE-588)1344993702  |0 (DE-627)1905728476  |4 aut 
245 1 0 |a Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT  |b evaluation of global and local accuracies  |c 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 
264 1 |c February 2024 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 15.10.2024 
500 |a Online veröffentlicht: 15. Dezember 2023 
520 |a 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. 
650 4 |a CT 
650 4 |a Deep neural network segmentation 
650 4 |a Manual segmentation 
650 4 |a Pancreas 
650 4 |a Pancreatic ductal adenocarcinoma 
700 1 |a Zhu, Zhuotun  |e VerfasserIn  |4 aut 
700 1 |a Chu, Linda C.  |e VerfasserIn  |4 aut 
700 1 |a Javed, Ammar A.  |e VerfasserIn  |4 aut 
700 1 |a Kinny-Köster, Benedict  |d 1991-  |e VerfasserIn  |0 (DE-588)1144960118  |0 (DE-627)1005123780  |0 (DE-576)495535362  |4 aut 
700 1 |a Wolfgang, Christopher L.  |e VerfasserIn  |0 (DE-588)1077118961  |0 (DE-627)836041518  |0 (DE-576)446002682  |4 aut 
700 1 |a Hruban, Ralph H.  |e VerfasserIn  |0 (DE-588)173034411  |0 (DE-627)697959112  |0 (DE-576)133887227  |4 aut 
700 1 |a Kinzler, Kenneth W.  |e VerfasserIn  |4 aut 
700 1 |a Fouladi, Daniel Fadaei  |e VerfasserIn  |4 aut 
700 1 |a Blanco, Alejandra  |e VerfasserIn  |4 aut 
700 1 |a Shayesteh, Shahab  |e VerfasserIn  |4 aut 
700 1 |a Fishman, Elliot K.  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |t Abdominal radiology  |d [Boston, MA] : Springer US, 2016  |g 49(2024), 2 vom: Feb., Seite 501-511  |h Online-Ressource  |w (DE-627)847023133  |w (DE-600)2845742-0  |w (DE-576)455030650  |x 2366-0058  |7 nnas  |a Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT evaluation of global and local accuracies 
773 1 8 |g volume:49  |g year:2024  |g number:2  |g month:02  |g pages:501-511  |g extent:11  |a Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT evaluation of global and local accuracies 
856 4 0 |u https://doi.org/10.1007/s00261-023-04122-6  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://link.springer.com/article/10.1007/s00261-023-04122-6  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20241015 
993 |a Article 
994 |a 2024 
998 |g 1144960118  |a Kinny-Köster, Benedict  |m 1144960118:Kinny-Köster, Benedict  |d 910000  |d 910200  |e 910000PK1144960118  |e 910200PK1144960118  |k 0/910000/  |k 1/910000/910200/  |p 5 
999 |a KXP-PPN1905731884  |e 459548349X 
BIB |a Y 
SER |a journal 
JSO |a {"title":[{"title_sort":"Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT","subtitle":"evaluation of global and local accuracies","title":"Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT"}],"person":[{"given":"Satomi","family":"Kawamoto","role":"aut","display":"Kawamoto, Satomi","roleDisplay":"VerfasserIn"},{"role":"aut","roleDisplay":"VerfasserIn","display":"Zhu, Zhuotun","given":"Zhuotun","family":"Zhu"},{"family":"Chu","given":"Linda C.","display":"Chu, Linda C.","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Ammar A.","family":"Javed","role":"aut","roleDisplay":"VerfasserIn","display":"Javed, Ammar A."},{"given":"Benedict","family":"Kinny-Köster","role":"aut","roleDisplay":"VerfasserIn","display":"Kinny-Köster, Benedict"},{"family":"Wolfgang","given":"Christopher L.","display":"Wolfgang, Christopher L.","roleDisplay":"VerfasserIn","role":"aut"},{"display":"Hruban, Ralph H.","roleDisplay":"VerfasserIn","role":"aut","family":"Hruban","given":"Ralph H."},{"family":"Kinzler","given":"Kenneth W.","display":"Kinzler, Kenneth W.","roleDisplay":"VerfasserIn","role":"aut"},{"display":"Fouladi, Daniel Fadaei","roleDisplay":"VerfasserIn","role":"aut","family":"Fouladi","given":"Daniel Fadaei"},{"display":"Blanco, Alejandra","roleDisplay":"VerfasserIn","role":"aut","family":"Blanco","given":"Alejandra"},{"family":"Shayesteh","given":"Shahab","roleDisplay":"VerfasserIn","display":"Shayesteh, Shahab","role":"aut"},{"roleDisplay":"VerfasserIn","display":"Fishman, Elliot K.","role":"aut","family":"Fishman","given":"Elliot K."}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"note":["Gesehen am 15.10.2024","Online veröffentlicht: 15. Dezember 2023"],"language":["eng"],"recId":"1905731884","origin":[{"dateIssuedKey":"2024","dateIssuedDisp":"February 2024"}],"id":{"doi":["10.1007/s00261-023-04122-6"],"eki":["1905731884"]},"name":{"displayForm":["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"]},"physDesc":[{"extent":"11 S."}],"relHost":[{"origin":[{"dateIssuedDisp":"2016-","publisher":"Springer US","dateIssuedKey":"2016","publisherPlace":"[Boston, MA]"}],"id":{"zdb":["2845742-0"],"eki":["847023133"],"issn":["2366-0058"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"Abdominal radiology","title":"Abdominal radiology"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"disp":"Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT evaluation of global and local accuraciesAbdominal radiology","note":["Gesehen am 29.01.18"],"language":["eng"],"recId":"847023133","pubHistory":["Volume 41, issue 1 (January 2016)-"],"part":{"year":"2024","pages":"501-511","issue":"2","volume":"49","text":"49(2024), 2 vom: Feb., Seite 501-511","extent":"11"}}]} 
SRT |a KAWAMOTOSADEEPNEURAL2024