h1

h2

h3

h4

h5
h6

NADIR

New directions for deep learning in cancer research through concept explainability and virtual experimentation

Grant period2024-01-01 - 2028-12-31
Funding bodyEuropean Union
 CORDIS
Call numberERC-2023-STG - ERC STARTING GRANTS
Grant number101114631 ; ERC-2023-STG - ERC STARTING GRANTS
Further information: Homepage
IdentifierG:(EU-Grant)101114631

Note: Deep learning tools for cancer research in biomedicine. Deep learning (DL) has revolutionised cancer research by extracting molecular information from image data. However, its effectiveness is limited as it remains purely descriptive and disconnected from biological mechanistic knowledge. In this context, the ERC-funded NADIR project aims to leverage DL models to predict, verify and even discover new biological mechanisms. Integrating programming, medical image analysis and biomedical engineering, the project will develop DL tools capable of extracting biological concepts, elucidating biological mechanisms, and generating and testing mechanistic hypotheses. NADIR’s primary focus lies on understanding tumour-immune interactions in colorectal and gastric cancers. Through its educational and outreach programme, the project aims to make the tools available to cancer researchers in the field of biomedicine.
   

Recent Publications

All known publications ...
Download: BibTeX | EndNote XML,  Text | RIS | 

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;  ;  ;  ;  ;  ;  ;  ;
Hallucination filtering in radiology vision-language models using discrete semantic entropy
European radiology 36(7), 6107-6118 () [10.1007/s00330-026-12384-z]  GO OpenAccess  Download fulltext Files BibTeX | EndNote: XML, Text | RIS

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;
Deep Learning Reveals Liver MRI Features Associated With PNPLA3 I148M in Steatotic Liver Disease
Liver international 45(7), e70164 () [10.1111/liv.70164]  GO OpenAccess  Download fulltext Files BibTeX | EndNote: XML, Text | RIS

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;
Medical large language models are susceptible to targeted misinformation attacks
npj digital medicine 7(1), 288 () [10.1038/s41746-024-01282-7]  GO OpenAccess  Download fulltext Files BibTeX | EndNote: XML, Text | RIS

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Journal Article  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;
Reconstruction of patient-specific confounders in AI-based radiologic image interpretation using generative pretraining
Cell reports / Medicine 5(9), 101713 () [10.1016/j.xcrm.2024.101713]  GO OpenAccess  Download fulltext Files BibTeX | EndNote: XML, Text | RIS

All known publications ...
Download: BibTeX | EndNote XML,  Text | RIS | 

 Record created 2025-01-28, last modified 2025-01-29
Similar records


External link:
Download fulltext
Homepage
Rate this document:

Rate this document:
1
2
3
4
5
 
(Not yet reviewed)