Eduardo J. Mortani Barbosa
Researcher in chest imaging whose published work applies machine learning to chest CT. First author of a 2018 study that used CT features to predict later bronchiolitis obliterans syndrome.
As of . Primary source: ORCID record.
Summary
Eduardo J. Mortani Barbosa is a researcher in chest imaging whose papers apply machine learning and deep learning to chest CT. Eduardo J. Mortani Barbosa is included in this category because an opened abstract describes machine learning used to predict bronchiolitis obliterans syndrome, a form of CLAD, after lung transplantation.
Work summary
Eduardo Mortani Barbosa is the first author of a 2018 retrospective study of paired inspiratory and expiratory CT scans from 71 lung transplant recipients, 41 of whom developed bronchiolitis obliterans syndrome (BOS, the airway-centred form of chronic lung allograft dysfunction) [DOI 10.1016/j.acra.2018.01.013]. Machine learning applied to quantitative CT measurements was used to identify, from baseline scans, the patients who later developed BOS, and 23 baseline CT parameters distinguished them from patients who did not. The later machine-learning work lies outside transplantation. A 2021 study used random forests and a deep-learning classifier on 2,446 chest CT scans from 16 institutions to separate COVID-19 from other pneumonias, interstitial lung disease and normal scans [DOI 10.1007/s00330-021-07937-3], and a 2026 study reported that a three-dimensional deep-learning model estimated the malignancy risk of lung nodules more accurately than established scoring systems in lung cancer screening [DOI 10.1093/radadv/umag003]. A 2022 study with Eduardo Mortani Barbosa as last author trained transparent machine-learning models to classify suspicious thoracic lesions as benign or malignant [DOI 10.1016/j.acra.2021.07.002].
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 the University of Pennsylvania; not confirmed as current)
- ai evidence
- Abstracts of the four source papers, all describing machine-learning or deep-learning models.
Sources and links
- ORCID record (primary)
- OpenAlex author profile
- Machine learning on quantitative CT features to predict bronchiolitis obliterans syndrome (Academic Radiology 2018), DOI 10.1016/j.acra.2018.01.013
- Machine learning to detect COVID-19 on chest CT (European Radiology 2021), DOI 10.1007/s00330-021-07937-3
- Deep learning pulmonary nodule risk assessment in lung cancer screening (Radiology Advances 2026), DOI 10.1093/radadv/umag003
- Transparent machine-learning models for suspicious thoracic lesions (Academic Radiology 2022), DOI 10.1016/j.acra.2021.07.002
Known gaps in this record
- Only the 2018 paper concerns lung transplantation or CLAD; it is a single-centre retrospective study.
- Role and current affiliation were not verified; the ORCID record lists no employment.
- The 2018 and 2022 papers are attributed through the OpenAlex profile by name and author position; they are not listed in the ORCID record.
- 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.