Process optimization with rule-learning explainable AI, and its application to MRI scanning

Sean Hartmann, Andrew Sharp, Heather Johnston, Michael S Gee, Susie Y Huang, Mukesh G Harisinghani, Jens Gühring, Wei-Ching Lo · 2026

Read Process optimization with rule-learning explainable AI, and its application to MRI scanning by Sean Hartmann, Andrew Sharp, Heather Johnston, Michael S Gee, Susie Y Huang, Mukesh G Harisinghani, Jens Gühring, Wei-Ching Lo (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-0358070.txt.

Description

Sean Hartmann led a team of eight authors applying explainable AI to MRI scanning, published in PLOS ONE in 2026. MRI scans are slow and costly, and backlogs delay diagnosis. Instead of a black-box model, the team used rule-learning AI whose advice technicians can read and judge.

Hartmann's approach mined the scanning process for steps that can be trimmed without losing image quality. Readable rules matter in medicine, where staff must defend each change to a clinical workflow. Faster scans mean more patients served on the same machines. The study shows a path where AI improves a hospital process while staying open to human checking, a pattern many clinical settings will demand.

Catalog record

CREATORSean Hartmann, Andrew Sharp, Heather Johnston, Michael S Gee, Susie Y Huang, Mukesh G Harisinghani, Jens Gühring, Wei-Ching Lo
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE36797
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0358070

Browse the full library · About the Tower of Babel