Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy
Artificial intelligence (AI) is widely used to analyze gastrointestinal (GI) endoscopy image data. AI has led to several clinically approved algorithms for polyp detection, but application of AI beyond this specific task is limited by the high cost of manual annotations. Here, we show that a weakly...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
22 March 2022
|
| In: |
Scientific reports
Year: 2022, Jahrgang: 12, Pages: 1-13 |
| ISSN: | 2045-2322 |
| DOI: | 10.1038/s41598-022-08773-1 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41598-022-08773-1 Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41598-022-08773-1 
|
| Verfasserangaben: | Lukas Buendgens, Didem Cifci, Narmin Ghaffari Laleh, Marko van Treeck, Maria T. Koenen, Henning W. Zimmermann, Till Herbold, Thomas Joachim Lux, Alexander Hann, Christian Trautwein & Jakob Nikolas Kather |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1806821001 | ||
| 003 | DE-627 | ||
| 005 | 20241128091619.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220612s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41598-022-08773-1 |2 doi | |
| 035 | |a (DE-627)1806821001 | ||
| 035 | |a (DE-599)KXP1806821001 | ||
| 035 | |a (OCoLC)1341461259 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Bündgens, Lukas |d 1988- |e VerfasserIn |0 (DE-588)1050671007 |0 (DE-627)784614490 |0 (DE-576)40491537X |4 aut | |
| 245 | 1 | 0 | |a Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy |c Lukas Buendgens, Didem Cifci, Narmin Ghaffari Laleh, Marko van Treeck, Maria T. Koenen, Henning W. Zimmermann, Till Herbold, Thomas Joachim Lux, Alexander Hann, Christian Trautwein & Jakob Nikolas Kather |
| 264 | 1 | |c 22 March 2022 | |
| 300 | |a 13 | ||
| 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 12.06.2022 | ||
| 520 | |a Artificial intelligence (AI) is widely used to analyze gastrointestinal (GI) endoscopy image data. AI has led to several clinically approved algorithms for polyp detection, but application of AI beyond this specific task is limited by the high cost of manual annotations. Here, we show that a weakly supervised AI can be trained on data from a clinical routine database to learn visual patterns of GI diseases without any manual labeling or annotation. We trained a deep neural network on a dataset of N = 29,506 gastroscopy and N = 18,942 colonoscopy examinations from a large endoscopy unit serving patients in Germany, the Netherlands and Belgium, using only routine diagnosis data for the 42 most common diseases. Despite a high data heterogeneity, the AI system reached a high performance for diagnosis of multiple diseases, including inflammatory, degenerative, infectious and neoplastic diseases. Specifically, a cross-validated area under the receiver operating curve (AUROC) of above 0.70 was reached for 13 diseases, and an AUROC of above 0.80 was reached for two diseases in the primary data set. In an external validation set including six disease categories, the AI system was able to significantly predict the presence of diverticulosis, candidiasis, colon and rectal cancer with AUROCs above 0.76. Reverse engineering the predictions demonstrated that plausible patterns were learned on the level of images and within images and potential confounders were identified. In summary, our study demonstrates the potential of weakly supervised AI to generate high-performing classifiers and identify clinically relevant visual patterns based on non-annotated routine image data in GI endoscopy and potentially other clinical imaging modalities. | ||
| 650 | 4 | |a Colonoscopy | |
| 650 | 4 | |a Diagnostic markers | |
| 650 | 4 | |a Image processing | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Oesophagogastroscopy | |
| 700 | 1 | |a Cifci, Didem |e VerfasserIn |4 aut | |
| 700 | 1 | |a Ghaffari Laleh, Narmin |e VerfasserIn |4 aut | |
| 700 | 1 | |a van Treeck, Marko |e VerfasserIn |4 aut | |
| 700 | 1 | |a Koenen, Maria T. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Zimmermann, Henning W. |e VerfasserIn |4 aut | |
| 700 | 1 | |a Herbold, Till |e VerfasserIn |4 aut | |
| 700 | 1 | |a Lux, Thomas Joachim |d 1994- |e VerfasserIn |0 (DE-588)1254195270 |0 (DE-627)1796820717 |4 aut | |
| 700 | 1 | |a Hann, Alexander |e VerfasserIn |4 aut | |
| 700 | 1 | |a Trautwein, Christian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Scientific reports |d [London] : Springer Nature, 2011 |g 12(2022), Artikel-ID 4829, Seite 1-13 |h Online-Ressource |w (DE-627)663366712 |w (DE-600)2615211-3 |w (DE-576)346641179 |x 2045-2322 |7 nnas |a Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy |
| 773 | 1 | 8 | |g volume:12 |g year:2022 |g elocationid:4829 |g pages:1-13 |g extent:13 |a Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41598-022-08773-1 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s41598-022-08773-1 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20220612 | ||
| 993 | |a Article | ||
| 994 | |a 2022 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 11 |y j | ||
| 999 | |a KXP-PPN1806821001 |e 4148283989 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"22 March 2022"}],"relHost":[{"recId":"663366712","physDesc":[{"extent":"Online-Ressource"}],"disp":"Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopyScientific reports","pubHistory":["1, article number 1 (2011)-"],"origin":[{"publisher":"Springer Nature ; Nature Publishing Group","publisherPlace":"[London] ; London","dateIssuedKey":"2011","dateIssuedDisp":"2011-"}],"title":[{"title":"Scientific reports","title_sort":"Scientific reports"}],"part":{"volume":"12","text":"12(2022), Artikel-ID 4829, Seite 1-13","extent":"13","pages":"1-13","year":"2022"},"id":{"eki":["663366712"],"issn":["2045-2322"],"zdb":["2615211-3"]},"note":["Gesehen am 12.07.24"],"language":["eng"],"type":{"media":"Online-Ressource","bibl":"periodical"}}],"person":[{"display":"Bündgens, Lukas","family":"Bündgens","role":"aut","given":"Lukas"},{"display":"Cifci, Didem","family":"Cifci","role":"aut","given":"Didem"},{"role":"aut","given":"Narmin","family":"Ghaffari Laleh","display":"Ghaffari Laleh, Narmin"},{"display":"van Treeck, Marko","family":"van Treeck","given":"Marko","role":"aut"},{"display":"Koenen, Maria T.","role":"aut","given":"Maria T.","family":"Koenen"},{"display":"Zimmermann, Henning W.","role":"aut","given":"Henning W.","family":"Zimmermann"},{"family":"Herbold","given":"Till","role":"aut","display":"Herbold, Till"},{"display":"Lux, Thomas Joachim","given":"Thomas Joachim","role":"aut","family":"Lux"},{"family":"Hann","role":"aut","given":"Alexander","display":"Hann, Alexander"},{"family":"Trautwein","given":"Christian","role":"aut","display":"Trautwein, Christian"},{"display":"Kather, Jakob Nikolas","given":"Jakob Nikolas","role":"aut","family":"Kather"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"language":["eng"],"note":["Gesehen am 12.06.2022"],"title":[{"title_sort":"Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy","title":"Weakly supervised end-to-end artificial intelligence in gastrointestinal endoscopy"}],"physDesc":[{"extent":"13 S."}],"recId":"1806821001","name":{"displayForm":["Lukas Buendgens, Didem Cifci, Narmin Ghaffari Laleh, Marko van Treeck, Maria T. Koenen, Henning W. Zimmermann, Till Herbold, Thomas Joachim Lux, Alexander Hann, Christian Trautwein & Jakob Nikolas Kather"]},"id":{"eki":["1806821001"],"doi":["10.1038/s41598-022-08773-1"]}} | ||
| SRT | |a BUENDGENSLWEAKLYSUPE2220 | ||