Comparison of evaluation metrics for landmark detection in CMR images

Cardiac magnetic resonance (CMR) images are widely used for cardiac diagnosis and ventricular assessment. Extracting specific landmarks like the right ventricular insertion points is of importance for spatial alignment and 3D modelling. The automatic detection of such landmarks has been tackled by m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Köhler, Sven (VerfasserIn) , Sharan, Lalith (VerfasserIn) , Kuhm, Julian (VerfasserIn) , Ghanaat, Arman (VerfasserIn) , Gordejeva, Jelizaveta (VerfasserIn) , Simon, Nike K. (VerfasserIn) , Grell, Niko M. (VerfasserIn) , André, Florian (VerfasserIn) , Engelhardt, Sandy (VerfasserIn)
Dokumenttyp: Kapitel/Artikel Konferenzschrift
Sprache:Deutsch
Veröffentlicht: 05 April 2022
In: Bildverarbeitung für die Medizin 2022
Year: 2022, Pages: 198-203
DOI:10.1007/978-3-658-36932-3_43
Online-Zugang:Resolving-System, lizenzpflichtig, Volltext: https://doi.org/10.1007/978-3-658-36932-3_43
Volltext
Verfasserangaben:Sven Koehler, Lalith Sharan, Julian Kuhm, Arman Ghanaat, Jelizaveta Gordejeva, Nike K. Simon, Niko M. Grell, Florian André, Sandy Engelhardt

MARC

LEADER 00000naa a2200000 c 4500
001 1920905359
003 DE-627
005 20250401084848.0
007 cr uuu---uuuuu
008 250401s2022 xx |||||o 00| ||ger c
024 7 |a 10.1007/978-3-658-36932-3_43  |2 doi 
035 |a (DE-627)1920905359 
035 |a (DE-599)KXP1920905359 
035 |a (OCoLC)1512610019 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a ger 
084 |a 33  |2 sdnb 
100 1 |a Köhler, Sven  |e VerfasserIn  |0 (DE-588)124712830X  |0 (DE-627)1780697864  |4 aut 
245 1 0 |a Comparison of evaluation metrics for landmark detection in CMR images  |c Sven Koehler, Lalith Sharan, Julian Kuhm, Arman Ghanaat, Jelizaveta Gordejeva, Nike K. Simon, Niko M. Grell, Florian André, Sandy Engelhardt 
264 1 |c 05 April 2022 
300 |a 6 
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 01.04.2025 
520 |a Cardiac magnetic resonance (CMR) images are widely used for cardiac diagnosis and ventricular assessment. Extracting specific landmarks like the right ventricular insertion points is of importance for spatial alignment and 3D modelling. The automatic detection of such landmarks has been tackled by multiple groups using Deep Learning, but relatively little attention has been paid to the failure cases of evaluation metrics in this field. In this work, we extended the public ACDC dataset with additional labels of the right ventricular insertion points and compare different variants of a heatmap-based landmark detection pipeline. In this comparison, we demonstrate very likely pitfalls of apparently simple detection and localisation metrics which highlights the importance of a clear detection strategy and the definition of an upper-limit for localisation based metrics. Our preliminary results indicate that a combination of different metrics are necessary, as they yield different winners for method comparison. Additionally, they highlight the need of a comprehensive metric description and evaluation standardisation, especially for the error cases where no metrics could be computed or where no lower/upper boundary of a metric exists. Code and labels: https://github.com/Cardio-AI/rvip_landmark_detection 
700 1 |a Sharan, Lalith  |d 1993-  |e VerfasserIn  |0 (DE-588)1255069554  |0 (DE-627)1798142104  |4 aut 
700 1 |a Kuhm, Julian  |e VerfasserIn  |0 (DE-588)1186911824  |0 (DE-627)1666191507  |4 aut 
700 1 |a Ghanaat, Arman  |e VerfasserIn  |4 aut 
700 1 |a Gordejeva, Jelizaveta  |e VerfasserIn  |4 aut 
700 1 |a Simon, Nike K.  |e VerfasserIn  |4 aut 
700 1 |a Grell, Niko M.  |e VerfasserIn  |4 aut 
700 1 |a André, Florian  |d 1983-  |e VerfasserIn  |0 (DE-588)1051060230  |0 (DE-627)785671714  |0 (DE-576)405733267  |4 aut 
700 1 |a Engelhardt, Sandy  |d 1987-  |e VerfasserIn  |0 (DE-588)1122674465  |0 (DE-627)876003080  |0 (DE-576)481436049  |4 aut 
773 0 8 |i Enthalten in  |a German Workshop on Medical Image Computing (2022 : Heidelberg)  |t Bildverarbeitung für die Medizin 2022  |d Wiesbaden : Springer Gabler, 2022  |g (2022), Seite 198-203  |h 1 Online-Ressource (xx, 356 Seiten, 142 Abb.)  |w (DE-627)1799312186  |z 9783658369323  |7 nnam 
773 1 8 |g year:2022  |g pages:198-203  |g extent:6  |a Comparison of evaluation metrics for landmark detection in CMR images 
776 0 8 |i Erscheint auch als  |n Druck-Ausgabe  |a Köhler, Sven  |t Comparison of evaluation metrics for landmark detection in CMR images  |d 2022  |w (DE-627)1853503738 
856 4 0 |u https://doi.org/10.1007/978-3-658-36932-3_43  |x Resolving-System  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20250401 
993 |a ConferencePaper 
994 |a 2022 
998 |g 1122674465  |a Engelhardt, Sandy  |m 1122674465:Engelhardt, Sandy  |d 910000  |d 910100  |e 910000PE1122674465  |e 910100PE1122674465  |k 0/910000/  |k 1/910000/910100/  |p 10 
998 |g 1051060230  |a André, Florian  |m 1051060230:André, Florian  |d 910000  |d 910100  |e 910000PA1051060230  |e 910100PA1051060230  |k 0/910000/  |k 1/910000/910100/  |p 8 
998 |g 1186911824  |a Kuhm, Julian  |m 1186911824:Kuhm, Julian  |d 50000  |e 50000PK1186911824  |k 0/50000/  |p 3 
998 |g 1255069554  |a Sharan, Lalith  |m 1255069554:Sharan, Lalith  |d 910000  |d 910100  |e 910000PS1255069554  |e 910100PS1255069554  |k 0/910000/  |k 1/910000/910100/  |p 2 
998 |g 124712830X  |a Köhler, Sven  |m 124712830X:Köhler, Sven  |d 910000  |d 910100  |e 910000PK124712830X  |e 910100PK124712830X  |k 0/910000/  |k 1/910000/910100/  |p 1  |x j 
999 |a KXP-PPN1920905359  |e 4695808439 
BIB |a Y 
JSO |a {"language":["ger"],"name":{"displayForm":["Sven Koehler, Lalith Sharan, Julian Kuhm, Arman Ghanaat, Jelizaveta Gordejeva, Nike K. Simon, Niko M. Grell, Florian André, Sandy Engelhardt"]},"note":["Gesehen am 01.04.2025"],"recId":"1920905359","person":[{"given":"Sven","display":"Köhler, Sven","role":"aut","family":"Köhler"},{"family":"Sharan","role":"aut","display":"Sharan, Lalith","given":"Lalith"},{"role":"aut","family":"Kuhm","display":"Kuhm, Julian","given":"Julian"},{"role":"aut","family":"Ghanaat","display":"Ghanaat, Arman","given":"Arman"},{"display":"Gordejeva, Jelizaveta","given":"Jelizaveta","role":"aut","family":"Gordejeva"},{"given":"Nike K.","display":"Simon, Nike K.","role":"aut","family":"Simon"},{"role":"aut","family":"Grell","given":"Niko M.","display":"Grell, Niko M."},{"display":"André, Florian","given":"Florian","family":"André","role":"aut"},{"family":"Engelhardt","role":"aut","display":"Engelhardt, Sandy","given":"Sandy"}],"physDesc":[{"extent":"6 S."}],"id":{"eki":["1920905359"],"doi":["10.1007/978-3-658-36932-3_43"]},"title":[{"title_sort":"Comparison of evaluation metrics for landmark detection in CMR images","title":"Comparison of evaluation metrics for landmark detection in CMR images"}],"type":{"media":"Online-Ressource","bibl":"chapter"},"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"05 April 2022"}],"relHost":[{"title":[{"title_sort":"Bildverarbeitung für die Medizin 2022","subtitle":"proceedings, German Workshop on Medical Image Computing, Heidelberg, June 26-28, 2022","title":"Bildverarbeitung für die Medizin 2022"}],"physDesc":[{"extent":"1 Online-Ressource (xx, 356 Seiten, 142 Abb.)"}],"id":{"doi":["10.1007/978-3-658-36932-3"],"eki":["1799312186"],"isbn":["9783658369323"]},"origin":[{"publisherPlace":"Wiesbaden","dateIssuedKey":"2022","dateIssuedDisp":"[2022]","publisher":"Springer Gabler"}],"name":{"displayForm":["Klaus Maier-Hein, Thomas M. Deserno, Heinz Handels, Andreas Maier, Christoph Palm, Thomas Tolxdorff (Hrsg.)"]},"person":[{"family":"Maier-Hein","role":"edt","display":"Maier-Hein, Klaus H.","given":"Klaus H."},{"family":"Deserno","role":"edt","given":"Thomas M.","display":"Deserno, Thomas M."},{"given":"Heinz","display":"Handels, Heinz","role":"edt","family":"Handels"},{"given":"Andreas","display":"Maier, Andreas","role":"edt","family":"Maier"},{"role":"edt","family":"Palm","display":"Palm, Christoph","given":"Christoph"},{"display":"Tolxdorff, Thomas","given":"Thomas","family":"Tolxdorff","role":"edt"}],"recId":"1799312186","disp":"German Workshop on Medical Image Computing (2022 : Heidelberg)Bildverarbeitung für die Medizin 2022","type":{"media":"Online-Ressource","bibl":"book"},"corporate":[{"display":"German Workshop on Medical Image Computing (2022, Heidelberg)","role":"aut"}],"language":["ger"],"part":{"extent":"6","pages":"198-203","text":"(2022), Seite 198-203","year":"2022"}}]} 
SRT |a KOEHLERSVECOMPARISON0520