Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI

Klara Mogensen, Valerio Guarrasi, Sofia Behndig, Johan Eriksson De Ryst, Paolo Soda, Anders Eklund, Jan Malm, Sara Qvarlander · 2026

Read Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI by Klara Mogensen, Valerio Guarrasi, Sofia Behndig, Johan Eriksson De Ryst, Paolo Soda, Anders Eklund, Jan Malm, Sara Qvarlander (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/plos-pone-0350335.txt.

Description

Klara Mogensen and colleagues tested whether smart software reading brain scans can predict who will benefit from a brain fluid shunt for a treatable walking and thinking disorder of older adults. Scans from one hundred and forty nine operated patients were classed by whether walking speed improved after surgery. Three software routes were tried: deep networks, a fused network, and hand built scan features with classic learning.

All routes performed poorly, with none reaching seventy percent discrimination. Hand built features did least badly. Scan appearance alone, the authors conclude, does not yet hold enough signal to pick shunt winners. Clinics should keep using gait tests and fluid trials rather than scan based software for this call.

Catalog record

CREATORKlara Mogensen, Valerio Guarrasi, Sofia Behndig, Johan Eriksson De Ryst, Paolo Soda, Anders Eklund, Jan Malm, Sara Qvarlander
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE38201
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350335

Browse the full library · About the Tower of Babel