Multimodal learning for scalable representation of high-dimensional medical data

Areej Alsaafin, Abubakr Shafique, Saghir Alfasly, Krishna R. Kalari, H. R. Tizhoosh · 2026

Read Multimodal learning for scalable representation of high-dimensional medical data by Areej Alsaafin, Abubakr Shafique, Saghir Alfasly, Krishna R. Kalari, H. R. Tizhoosh (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-12891988.txt.

Description

Areej Alsaafin, Abubakr Shafique, Saghir Alfasly, Krishna R. Kalari, and H R Tizhoosh present a study published in 2025 on fusing medical data types into one searchable code. Pathology slides and genomic profiles each hold part of a patient's story, but their formats clash, and most models read only one at a time.

Their framework, MarbliX, learns to compress both into short binary codes in a shared space, trained so matching patients land near each other. Similar cases can then be retrieved instantly, supporting case-based reasoning. In lung cancer the fused codes scored eighty-five to eighty-nine percent across metrics, beating either source alone. In kidney cancer the full-value codes scored best, with binary codes close behind.

Catalog record

CREATORAreej Alsaafin, Abubakr Shafique, Saghir Alfasly, Krishna R. Kalari, H. R. Tizhoosh
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE43 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12891988

Browse the full library · About the Tower of Babel