Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans

Objective: Three-dimensional (3D) blood vessel structure information is important for diagnosis and treatment in various clinical scenarios. We present a fully automatic method for the extraction and differentiation of the arterial and venous vessel trees from abdominal contrast enhanced computed to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Golla, Alena-Kathrin (VerfasserIn) , Bauer, Dominik F. (VerfasserIn) , Schmidt, Ralf (VerfasserIn) , Russ, Tom (VerfasserIn) , Nörenberg, Dominik (VerfasserIn) , Chung, Khanlian (VerfasserIn) , Tönnes, Christian (VerfasserIn) , Schad, Lothar R. (VerfasserIn) , Zöllner, Frank G. (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: April 21, 2021
In: IEEE transactions on biomedical engineering
Year: 2021, Jahrgang: 68, Heft: 5, Pages: 1518-1526
ISSN:1558-2531
Online-Zugang: Volltext
Verfasserangaben:Alena-Kathrin Golla, Dominik F. Bauer, Ralf Schmidt, Tom Russ, Dominik Nörenberg, Khanlian Chung, Christian Tönnes, Lothar R. Schad, and Frank G. Zöllner, Member, IEEE

MARC

LEADER 00000caa a2200000 c 4500
001 1760121886
003 DE-627
005 20220819224225.0
007 cr uuu---uuuuu
008 210609s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TBME.2020.3042640  |2 doi 
035 |a (DE-627)1760121886 
035 |a (DE-599)KXP1760121886 
035 |a (OCoLC)1341415472 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Golla, Alena-Kathrin  |d 1991-  |e VerfasserIn  |0 (DE-588)1232099384  |0 (DE-627)1755854447  |4 aut 
245 1 0 |a Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans  |c Alena-Kathrin Golla, Dominik F. Bauer, Ralf Schmidt, Tom Russ, Dominik Nörenberg, Khanlian Chung, Christian Tönnes, Lothar R. Schad, and Frank G. Zöllner, Member, IEEE 
264 1 |c April 21, 2021 
300 |a 9 
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 09.06.2021 
520 |a Objective: Three-dimensional (3D) blood vessel structure information is important for diagnosis and treatment in various clinical scenarios. We present a fully automatic method for the extraction and differentiation of the arterial and venous vessel trees from abdominal contrast enhanced computed tomography (CE-CT) volumes using convolutional neural networks (CNNs). Methods: We used a novel ratio-based sampling method to train 2D and 3D versions of the U-Net, the V-Net and the DeepVesselNet. Networks were trained with a combination of the Dice and cross entropy loss. Performance was evaluated on 20 IRCAD subjects. Best performing networks were combined into an ensemble. We investigated seven different weighting schemes. Trained networks were additionally applied to 26 BTCV cases to validate the generalizability. Results: Based on our experiments, the optimal configuration is an equally weighted ensemble of 2D and 3D U- and V-Nets. Our method achieved Dice similarity coefficients of 0.758 $\boldsymbol\pm $ 0.050 (veins) and 0.838 $\boldsymbol\pm $ 0.074 (arteries) on the IRCAD data set. Application to the BTCV data set showed a high transfer ability. Conclusion: Abdominal vascular structures can be segmented more accurately using ensembles than individual CNNs. 2D and 3D networks have complementary strengths and weaknesses. Our ensemble of 2D and 3D U-Nets and V-Nets in combination with ratio-based sampling achieves a high agreement with manual annotations for both artery and vein segmentation. Our results surpass other state-of-the-art methods. Significance: Our segmentation pipeline can provide valuable information for the planning of living donor organ transplantations. 
650 4 |a Arteries 
650 4 |a Artificial neural networks 
650 4 |a Computed tomography 
650 4 |a Image segmentation 
650 4 |a Three-dimensional displays 
650 4 |a Training 
650 4 |a Two dimensional displays 
650 4 |a Veins 
700 1 |a Bauer, Dominik F.  |d 1993-  |e VerfasserIn  |0 (DE-588)1235085503  |0 (DE-627)1760118532  |4 aut 
700 1 |a Schmidt, Ralf  |d 1989-  |e VerfasserIn  |0 (DE-588)1235091597  |0 (DE-627)176012169X  |4 aut 
700 1 |a Russ, Tom  |d 1992-  |e VerfasserIn  |0 (DE-588)1231738340  |0 (DE-627)175534970X  |4 aut 
700 1 |a Nörenberg, Dominik  |e VerfasserIn  |0 (DE-588)1064719996  |0 (DE-627)814432123  |0 (DE-576)424084228  |4 aut 
700 1 |a Chung, Khanlian  |d 1988-  |e VerfasserIn  |0 (DE-588)1178448363  |0 (DE-627)1049381440  |0 (DE-576)517783150  |4 aut 
700 1 |a Tönnes, Christian  |d 1990-  |e VerfasserIn  |0 (DE-588)1232095389  |0 (DE-627)1755847319  |4 aut 
700 1 |a Schad, Lothar R.  |d 1956-  |e VerfasserIn  |0 (DE-588)1028817630  |0 (DE-627)731640241  |0 (DE-576)376271221  |4 aut 
700 1 |a Zöllner, Frank G.  |d 1976-  |e VerfasserIn  |0 (DE-588)129580015  |0 (DE-627)473357054  |0 (DE-576)297732587  |4 aut 
773 0 8 |i Enthalten in  |a Institute of Electrical and Electronics Engineers  |t IEEE transactions on biomedical engineering  |d New York, NY : IEEE, 1964  |g 68(2021), 5, Seite 1518-1526  |h Online-Ressource  |w (DE-627)320614050  |w (DE-600)2021742-0  |w (DE-576)094080682  |x 1558-2531  |7 nnas 
773 1 8 |g volume:68  |g year:2021  |g number:5  |g pages:1518-1526  |g extent:9  |a Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans 
951 |a AR 
992 |a 20210609 
993 |a Article 
994 |a 2021 
998 |g 129580015  |a Zöllner, Frank G.  |m 129580015:Zöllner, Frank G.  |d 60000  |d 65200  |e 60000PZ129580015  |e 65200PZ129580015  |k 0/60000/  |k 1/60000/65200/  |p 9  |y j 
998 |g 1028817630  |a Schad, Lothar R.  |m 1028817630:Schad, Lothar R.  |d 60000  |d 65200  |e 60000PS1028817630  |e 65200PS1028817630  |k 0/60000/  |k 1/60000/65200/  |p 8 
998 |g 1232095389  |a Tönnes, Christian  |m 1232095389:Tönnes, Christian  |d 60000  |d 65200  |e 60000PT1232095389  |e 65200PT1232095389  |k 0/60000/  |k 1/60000/65200/  |p 7 
998 |g 1178448363  |a Chung, Khanlian  |m 1178448363:Chung, Khanlian  |d 60000  |d 65200  |e 60000PC1178448363  |e 65200PC1178448363  |k 0/60000/  |k 1/60000/65200/  |p 6 
998 |g 1064719996  |a Nörenberg, Dominik  |m 1064719996:Nörenberg, Dominik  |d 60000  |d 62900  |e 60000PN1064719996  |e 62900PN1064719996  |k 0/60000/  |k 1/60000/62900/  |p 5 
998 |g 1231738340  |a Russ, Tom  |m 1231738340:Russ, Tom  |d 60000  |d 65200  |e 60000PR1231738340  |e 65200PR1231738340  |k 0/60000/  |k 1/60000/65200/  |p 4 
998 |g 1235091597  |a Schmidt, Ralf  |m 1235091597:Schmidt, Ralf  |d 60000  |d 65200  |e 60000PS1235091597  |e 65200PS1235091597  |k 0/60000/  |k 1/60000/65200/  |p 3 
998 |g 1235085503  |a Bauer, Dominik F.  |m 1235085503:Bauer, Dominik F.  |d 60000  |d 65200  |e 60000PB1235085503  |e 65200PB1235085503  |k 0/60000/  |k 1/60000/65200/  |p 2 
998 |g 1232099384  |a Golla, Alena-Kathrin  |m 1232099384:Golla, Alena-Kathrin  |d 60000  |d 65200  |e 60000PG1232099384  |e 65200PG1232099384  |k 0/60000/  |k 1/60000/65200/  |p 1  |x j 
999 |a KXP-PPN1760121886  |e 3936313687 
BIB |a Y 
SER |a journal 
JSO |a {"person":[{"family":"Golla","display":"Golla, Alena-Kathrin","given":"Alena-Kathrin","role":"aut"},{"family":"Bauer","display":"Bauer, Dominik F.","given":"Dominik F.","role":"aut"},{"display":"Schmidt, Ralf","family":"Schmidt","given":"Ralf","role":"aut"},{"display":"Russ, Tom","family":"Russ","role":"aut","given":"Tom"},{"family":"Nörenberg","display":"Nörenberg, Dominik","given":"Dominik","role":"aut"},{"given":"Khanlian","role":"aut","family":"Chung","display":"Chung, Khanlian"},{"given":"Christian","role":"aut","display":"Tönnes, Christian","family":"Tönnes"},{"family":"Schad","display":"Schad, Lothar R.","given":"Lothar R.","role":"aut"},{"display":"Zöllner, Frank G.","family":"Zöllner","role":"aut","given":"Frank G."}],"language":["eng"],"note":["Gesehen am 09.06.2021"],"origin":[{"dateIssuedDisp":"April 21, 2021","dateIssuedKey":"2021"}],"title":[{"title":"Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans","title_sort":"Convolutional neural network ensemble segmentation with ratio-based sampling for the arteries and veins in abdominal CT scans"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"recId":"1760121886","relHost":[{"language":["eng"],"part":{"text":"68(2021), 5, Seite 1518-1526","issue":"5","year":"2021","pages":"1518-1526","volume":"68","extent":"9"},"titleAlt":[{"title":"Transactions on biomedical engineering"}],"corporate":[{"role":"aut","display":"Institute of Electrical and Electronics Engineers"}],"recId":"320614050","name":{"displayForm":["Institute of Electrical and Electronics Engineers"]},"physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["320614050"],"zdb":["2021742-0"],"issn":["1558-2531"]},"origin":[{"dateIssuedDisp":"1964-","publisher":"IEEE","dateIssuedKey":"1964","publisherPlace":"New York, NY"}],"pubHistory":["11.1964 -"],"title":[{"title_sort":"IEEE transactions on biomedical engineering","subtitle":"a publication of the IEEE Engineering in Medicine and Biology Society","title":"IEEE transactions on biomedical engineering"}],"disp":"Institute of Electrical and Electronics EngineersIEEE transactions on biomedical engineering","type":{"bibl":"periodical","media":"Online-Ressource"}}],"name":{"displayForm":["Alena-Kathrin Golla, Dominik F. Bauer, Ralf Schmidt, Tom Russ, Dominik Nörenberg, Khanlian Chung, Christian Tönnes, Lothar R. Schad, and Frank G. Zöllner, Member, IEEE"]},"physDesc":[{"extent":"9 S."}],"id":{"doi":["10.1109/TBME.2020.3042640"],"eki":["1760121886"]}} 
SRT |a GOLLAALENACONVOLUTIO2120