Crossmark

The interpretability paradox in cancer imaging and risk prediction: a critical narrative review of explainable AI, failure modes, and design alternatives

Crossref DOI link: https://doi.org/10.1007/s10462-026-11634-2

Published Online: 2026-07-07

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Alkhnbashi, Omer S. https://orcid.org/0000-0001-8088-590X
Mohammad, Rasheed

Khyriem, Costerwell

Hauns, Sven

Singh, Ankita

Khan, Imran

Gomez, Roshna Lawrence

Ramachandran, Revathy

AlBedwawi, Moaza Hashim

AbdulRahim, Manal Mohammed

AbdelAziz, Zaid

Batarfi, Ali. M.

Tayoun, Ahmad Abou

Soares, Nelson C.

Uddin, Mohammed

Cisse, Babacar

Ali, Fahad

Backofen, Rolf
Funding

Funding for this research was provided by:

Dubai Research, Development, and Innovation (2025/DRDI0406))

Center for Applied and Translational Genomics (CATG), Mohammed Bin Rashid University of Medicine and Health Sciences (MBRU), Dubai Health, Dubai, United Arab Emirates
License Information

Text and Data Mining valid from 2026-07-07

Accepted Manuscript valid from 2026-07-07
More Information

Article History

Received: 4 January 2026

Accepted: 25 June 2026

First Online: 7 July 2026

Declarations

:

: The authors declare no competing interests.

Document is current

Any future updates will be listed below