Craig J. Galban

Professor of Radiology at the University of Michigan. Author of CT image-analysis studies, including machine-learning screening of donor lungs for later CLAD risk.

As of 2026-10-10. Primary source: ORCID record.

Summary

Craig J. Galban is listed in the ORCID record as a Professor in the Department of Radiology at the University of Michigan. Craig J. Galban is included in this category because opened abstracts describe machine-learning and deep-learning analysis of lung CT scans, including a donor lung screening method linked to later CLAD.

Work summary

Craig Galban is the last author of a study that used dictionary learning, a supervised machine-learning method that learns image patterns, on CT scans of donor lungs taken before transplant [DOI 10.1016/j.healun.2023.09.018]. Scans came from 100 donor lung pairs in a prospective trial, of which 70 were implanted, and the algorithm identified recipients who had longer intensive care stays and a 19 times higher risk of chronic lung allograft dysfunction (CLAD) within 2 years. A deep-learning study, also with Craig Galban as last author, trained a convolutional neural network, a type of image-analysis model, to measure air trapping on CT scans in 36 people with mild cystic fibrosis [DOI 10.1371/journal.pone.0248902]. A 2025 study in chronic obstructive pulmonary disease used generative artificial intelligence to estimate small airway disease from a single inspiratory scan, with results that correlated strongly with the established two-scan method [DOI 10.1164/rccm.202409-1847oc]. Craig Galban is also a co-author of a 2021 study of parametric response mapping, a voxel-by-voxel CT method that is not machine learning, in which scans at potential CLAD identified patients with shorter CLAD-free survival [DOI 10.1164/rccm.202012-4528oc].

Based on 3 or more opened abstracts. Written only from abstracts that were opened (PubMed or Europe PMC); full texts were not read. Plain-language explanations are added by the editors and are not from the papers.

Role and field

Role: Professor, Radiology, University of Michigan
Role status: verified, self-asserted in ORCID employment entry
Role basis: ORCID employment entry (current, no end date), read on 2026-10-10.
Field: radiology; quantitative and machine-learning CT analysis of lung disease
Field basis: Unit name in the ORCID employment entry and the source abstracts.

Only what a cited source supports is stated. Entries marked self-asserted come from the person's own ORCID record. The field is taken from the name of the unit, not inferred from the person's name.

Details

affiliation: University of Michigan, Department of Radiology (ORCID, self-asserted)
ai evidence: Abstracts of the first three source papers describe machine-learning or deep-learning methods; the fourth is a quantitative CT study that does not use machine learning.

Sources and links

Links from this record

affiliated institution: University of Michigan Health Lung Transplant Program

Known gaps in this record

Only the donor lung screening paper links machine learning to CLAD; the others concern cystic fibrosis and COPD or use non-machine-learning CT analysis.
The 2023 donor-lung paper lists a second author with the surname Galban (Stefanie Galban); the last author, Craig J. Galban, is the person described here.
The role is self-asserted in ORCID and may be out of date.
Funding and conflicts of interest were not recorded.
Full texts were not read.

Information resource only. Not medical advice. Not a substitute for the care of the patient's transplant team.