Cover Image

Optimal statistical incorporation of independent feature stability information into radiomics studies

Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model build...

Full description

Saved in:
Bibliographic Details
Main Authors: Götz, Michael (Author) , Maier-Hein, Klaus H. (Author)
Format: Article (Journal)
Language:English
Published: [2020]
In: Scientific reports
Year: 2020, Volume: 10
ISSN:2045-2322
DOI:10.1038/s41598-020-57739-8
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41598-020-57739-8
Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41598-020-57739-8
Get full text
Author Notes:Michael Götz & Klaus H. Maier-Hein

MARC

LEADER 00000caa a2200000 c 4500
001 1733662987
003 DE-627
005 20220818205237.0
007 cr uuu---uuuuu
008 200924s2020 xx |||||o 00| ||eng c
024 7 |a 10.1038/s41598-020-57739-8  |2 doi 
035 |a (DE-627)1733662987 
035 |a (DE-599)KXP1733662987 
035 |a (OCoLC)1341361545 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Götz, Michael  |e VerfasserIn  |0 (DE-588)119554541X  |0 (DE-627)1677564326  |4 aut 
245 1 0 |a Optimal statistical incorporation of independent feature stability information into radiomics studies  |c Michael Götz & Klaus H. Maier-Hein 
264 1 |c [2020] 
300 |b Diaramme 
300 |a 10 
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 24.09.2020 
520 |a Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model building process still needs to be explored. Three different methods for incorporating prior knowledge into a radiomics modelling process were evaluated: the naïve approach (ignoring feature quality), the most common approach consisting of removing unstable features, and a novel approach using data augmentation for information transfer (DAFIT). Multiple experiments were conducted using both synthetic and publicly available real lung imaging patient data. Ignoring additional information from side experiments resulted in significantly overestimated model performances meaning the estimated mean area under the curve achieved with a model was increased. Removing unstable features improved the performance estimation, while slightly decreasing the model performance, i.e. decreasing the area under curve achieved with the model. The proposed approach was superior both in terms of the estimation of the model performance and the actual model performance. Our experiments show that data augmentation can prevent biases in performance estimation and has several advantages over the plain omission of the unstable feature. The actual gain that can be obtained depends on the quality and applicability of the prior information on the features in the given domain. This will be an important topic of future research. 
700 1 |a Maier-Hein, Klaus H.  |d 1980-  |e VerfasserIn  |0 (DE-588)1100551875  |0 (DE-627)85946461X  |0 (DE-576)333771222  |4 aut 
773 0 8 |i Enthalten in  |t Scientific reports  |d [London] : Springer Nature, 2011  |g 10(2020) Artikel-Nummer 737, 10 Seiten  |h Online-Ressource  |w (DE-627)663366712  |w (DE-600)2615211-3  |w (DE-576)346641179  |x 2045-2322  |7 nnas  |a Optimal statistical incorporation of independent feature stability information into radiomics studies 
773 1 8 |g volume:10  |g year:2020  |g extent:10  |a Optimal statistical incorporation of independent feature stability information into radiomics studies 
856 4 0 |u https://doi.org/10.1038/s41598-020-57739-8  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://www.nature.com/articles/s41598-020-57739-8  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20200924 
993 |a Article 
994 |a 2020 
998 |g 1100551875  |a Maier-Hein, Klaus H.  |m 1100551875:Maier-Hein, Klaus H.  |d 910000  |d 911400  |d 50000  |e 910000PM1100551875  |e 911400PM1100551875  |e 50000PM1100551875  |k 0/910000/  |k 1/910000/911400/  |k 0/50000/  |p 2  |y j 
999 |a KXP-PPN1733662987  |e 3760717802 
BIB |a Y 
SER |a journal 
JSO |a {"title":[{"title_sort":"Optimal statistical incorporation of independent feature stability information into radiomics studies","title":"Optimal statistical incorporation of independent feature stability information into radiomics studies"}],"person":[{"role":"aut","family":"Götz","given":"Michael","roleDisplay":"VerfasserIn","display":"Götz, Michael"},{"display":"Maier-Hein, Klaus H.","roleDisplay":"VerfasserIn","given":"Klaus H.","family":"Maier-Hein","role":"aut"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"name":{"displayForm":["Michael Götz & Klaus H. Maier-Hein"]},"recId":"1733662987","id":{"eki":["1733662987"],"doi":["10.1038/s41598-020-57739-8"]},"language":["eng"],"physDesc":[{"noteIll":"Diaramme","extent":"10 S."}],"relHost":[{"pubHistory":["1, article number 1 (2011)-"],"origin":[{"dateIssuedDisp":"2011-","publisherPlace":"[London] ; London","publisher":"Springer Nature ; Nature Publishing Group","dateIssuedKey":"2011"}],"id":{"issn":["2045-2322"],"eki":["663366712"],"zdb":["2615211-3"]},"recId":"663366712","disp":"Optimal statistical incorporation of independent feature stability information into radiomics studiesScientific reports","language":["eng"],"title":[{"title_sort":"Scientific reports","title":"Scientific reports"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"note":["Gesehen am 12.07.24"],"physDesc":[{"extent":"Online-Ressource"}],"part":{"extent":"10","text":"10(2020) Artikel-Nummer 737, 10 Seiten","volume":"10","year":"2020"}}],"note":["Gesehen am 24.09.2020"],"origin":[{"dateIssuedKey":"2020","dateIssuedDisp":"[2020]"}]} 
SRT |a GOETZMICHAOPTIMALSTA2020 

Similar Items