A multi-modal deep learning framework for enhanced breast cancer diagnosis using mammograms and clinical data

Adam M Ibrahim, Jianqiang Li, Faheem Akhtar, Anis Ahmad Chaudhary, Mohamed A M Ali, Haneef Khan, Musa Osman · 2026

Read A multi-modal deep learning framework for enhanced breast cancer diagnosis using mammograms and clinical data by Adam M Ibrahim, Jianqiang Li, Faheem Akhtar, Anis Ahmad Chaudhary, Mohamed A M Ali, Haneef Khan, Musa Osman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13234131.txt.

Description

Adam M Ibrahim and six co-authors teach a network to read mammograms and the patient's chart together, in this 2026 paper. Mammography misses cancers in dense breasts, where tissue overlap hides subtle lesions. Clinical risk factors carry signal the image lacks; images carry signal no chart holds. Their framework fuses the two streams.

A hierarchical design blends the features with cross-modal attention, letting each source query the other, while dynamic weighting adjusts how much each counts case by case. A region-of-interest module steers the image side toward the anatomy that matters. On a benchmark set the system reached 94.6 percent accuracy with an area under the curve of 0.963, beating its baselines significantly. One honesty note stands in the paper itself: the clinical variables were synthetic, generated from known risk distributions, because real paired data were unavailable. The work is a proof of concept awaiting a fully real test.

Catalog record

CREATORAdam M Ibrahim, Jianqiang Li, Faheem Akhtar, Anis Ahmad Chaudhary, Mohamed A M Ali, Haneef Khan, Musa Osman
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE78 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13234131

Browse the full library · About the Tower of Babel