Medical domain knowledge in domain-agnostic generative AI
The text-guided diffusion model GLIDE (Guided Language to Image Diffusion for Generation and Editing) is the state of the art in text-to-image generative artificial intelligence (AI). GLIDE has rich representations, but medical applications of this model have not been systematically explored. If GLI...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
11 July 2022
|
| In: |
npj digital medicine
Year: 2022, Jahrgang: 5, Pages: 1-5 |
| ISSN: | 2398-6352 |
| DOI: | 10.1038/s41746-022-00634-5 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41746-022-00634-5 Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41746-022-00634-5 
|
| Verfasserangaben: | Jakob Nikolas Kather, Narmin Ghaffari Laleh, Sebastian Foersch and Daniel Truhn |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1837701784 | ||
| 003 | DE-627 | ||
| 005 | 20230706231715.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230228s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1038/s41746-022-00634-5 |2 doi | |
| 035 | |a (DE-627)1837701784 | ||
| 035 | |a (DE-599)KXP1837701784 | ||
| 035 | |a (OCoLC)1389534389 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 245 | 1 | 0 | |a Medical domain knowledge in domain-agnostic generative AI |c Jakob Nikolas Kather, Narmin Ghaffari Laleh, Sebastian Foersch and Daniel Truhn |
| 264 | 1 | |c 11 July 2022 | |
| 300 | |a 5 | ||
| 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 28.02.2023 | ||
| 520 | |a The text-guided diffusion model GLIDE (Guided Language to Image Diffusion for Generation and Editing) is the state of the art in text-to-image generative artificial intelligence (AI). GLIDE has rich representations, but medical applications of this model have not been systematically explored. If GLIDE had useful medical knowledge, it could be used for medical image analysis tasks, a domain in which AI systems are still highly engineered towards a single use-case. Here we show that the publicly available GLIDE model has reasonably strong representations of key topics in cancer research and oncology, in particular the general style of histopathology images and multiple facets of diseases, pathological processes and laboratory assays. However, GLIDE seems to lack useful representations of the style and content of radiology data. Our findings demonstrate that domain-agnostic generative AI models can learn relevant medical concepts without explicit training. Thus, GLIDE and similar models might be useful for medical image processing tasks in the future - particularly with additional domain-specific fine-tuning. | ||
| 650 | 4 | |a Biomedical engineering | |
| 650 | 4 | |a Data integration | |
| 650 | 4 | |a Machine learning | |
| 700 | 1 | |a Ghaffari Laleh, Narmin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Foersch, Sebastian |e VerfasserIn |4 aut | |
| 700 | 1 | |a Truhn, Daniel |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t npj digital medicine |d [Basingstoke] : Macmillan Publishers Limited, 2016 |g 5(2022) vom: Juli, Artikel-ID 90, Seite 1-5 |h Online-Ressource |w (DE-627)1016587104 |w (DE-600)2925182-5 |w (DE-576)501513582 |x 2398-6352 |7 nnas |a Medical domain knowledge in domain-agnostic generative AI |
| 773 | 1 | 8 | |g volume:5 |g year:2022 |g month:07 |g elocationid:90 |g pages:1-5 |g extent:5 |a Medical domain knowledge in domain-agnostic generative AI |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41746-022-00634-5 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://www.nature.com/articles/s41746-022-00634-5 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230228 | ||
| 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 1 |x j | ||
| 999 | |a KXP-PPN1837701784 |e 4277681638 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"id":{"eki":["1837701784"],"doi":["10.1038/s41746-022-00634-5"]},"relHost":[{"pubHistory":["2016-"],"id":{"issn":["2398-6352"],"eki":["1016587104"],"zdb":["2925182-5"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"npj digital medicine","title":"npj digital medicine"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"language":["eng"],"part":{"pages":"1-5","extent":"5","text":"5(2022) vom: Juli, Artikel-ID 90, Seite 1-5","volume":"5","year":"2022"},"note":["Gesehen am 06. September 2019"],"recId":"1016587104","origin":[{"dateIssuedDisp":"[2016]-","publisher":"Macmillan Publishers Limited","publisherPlace":"[Basingstoke]"}],"disp":"Medical domain knowledge in domain-agnostic generative AInpj digital medicine"}],"title":[{"title_sort":"Medical domain knowledge in domain-agnostic generative AI","title":"Medical domain knowledge in domain-agnostic generative AI"}],"physDesc":[{"extent":"5 S."}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"person":[{"given":"Jakob Nikolas","role":"aut","display":"Kather, Jakob Nikolas","family":"Kather"},{"display":"Ghaffari Laleh, Narmin","family":"Ghaffari Laleh","given":"Narmin","role":"aut"},{"given":"Sebastian","role":"aut","display":"Foersch, Sebastian","family":"Foersch"},{"display":"Truhn, Daniel","family":"Truhn","given":"Daniel","role":"aut"}],"recId":"1837701784","note":["Gesehen am 28.02.2023"],"language":["eng"],"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"11 July 2022"}],"name":{"displayForm":["Jakob Nikolas Kather, Narmin Ghaffari Laleh, Sebastian Foersch and Daniel Truhn"]}} | ||
| SRT | |a KATHERJAKOMEDICALDOM1120 | ||