Micheal C. McInnis
Researcher in chest imaging whose work applies machine-learning CT analysis to CLAD. First author of a 2021 study of CLAD phenotype and graft failure.
As of . Primary source: ORCID record.
Summary
Micheal C. McInnis is a researcher in chest imaging whose ORCID record lists papers on machine-learning CT analysis in lung transplantation. Micheal C. McInnis is included in this category because opened abstracts describe machine-learning CT analysis applied to CLAD and to baseline lung allograft dysfunction.
Work summary
Micheal McInnis is the first author of a 2021 retrospective study of 88 lung transplant recipients with chronic lung allograft dysfunction (CLAD) that applied a machine-learning CT lung texture analysis tool at the time of diagnosis [DOI 10.1183/13993003.01652-2021]. The tool was compared with radiologist scoring for separating the obstructive form of CLAD, bronchiolitis obliterans syndrome, from the restrictive form, and for predicting graft failure. Both approaches were associated with graft failure, and a machine-learning measure of pulmonary vessel volume was the strongest for both phenotype and outcome. A 2026 study on which Micheal McInnis is the last author found that machine-learning CT measures at 12 months, in particular pulmonary vessel volume, were the strongest radiologic predictors of baseline lung allograft dysfunction, a related early condition [DOI 10.1016/j.healun.2025.12.018]. Related work includes a convolutional neural network, an image-analysis model, applied to radiographs of donor lungs during ex vivo lung perfusion [DOI 10.1038/s41746-024-01260-z], and machine-learning models of CT measurements in chronic thromboembolic pulmonary hypertension [DOI 10.1007/s00330-025-11972-9].
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
- unknown
- Role status
- unknown (no source read in this review states the role)
- Field
- chest imaging; machine learning for CT
- Field basis
- Topic of the source abstracts only; no unit name was read.
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
- unknown (OpenAlex lists University Health Network, Toronto; not confirmed as current)
- ai evidence
- Abstracts of the four source papers, all describing machine-learning or deep-learning methods.
Sources and links
- ORCID record (primary)
- OpenAlex author profile
- CLAD phenotype and prognosis by machine-learning CT analysis (European Respiratory Journal 2021), DOI 10.1183/13993003.01652-2021
- Radiologist- and computer-based CT quantification and baseline lung allograft dysfunction (Journal of Heart and Lung Transplantation 2026), DOI 10.1016/j.healun.2025.12.018
- Convolutional neural network on ex vivo lung perfusion radiographs (npj Digital Medicine 2024), DOI 10.1038/s41746-024-01260-z
- Machine learning for severe chronic thromboembolic pulmonary hypertension on CT (European Radiology 2025), DOI 10.1007/s00330-025-11972-9
Known gaps in this record
- Role and current affiliation were not verified; the ORCID record lists no employment.
- The 2021 study is retrospective and its abstract does not give the centre.
- Full texts were not read.
- Funding and conflicts of interest were not recorded.
Information resource only. Not medical advice. Not a substitute for the care of the patient's transplant team.