Computed tomography-based machine learning for donor lung screening before transplantation.
Computed tomography
Dictionary learning
Donor assessment
Donor lung screening
Lung transplantation
Machine learning
Primary graft dysfunction
Journal
The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation
ISSN: 1557-3117
Titre abrégé: J Heart Lung Transplant
Pays: United States
ID NLM: 9102703
Informations de publication
Date de publication:
29 Sep 2023
29 Sep 2023
Historique:
received:
22
03
2023
revised:
21
09
2023
accepted:
25
09
2023
pubmed:
2
10
2023
medline:
2
10
2023
entrez:
1
10
2023
Statut:
aheadofprint
Résumé
Assessment and selection of donor lungs remain largely subjective and experience based. Criteria to accept or decline lungs are poorly standardized and are not compliant with the current donor pool. Using ex vivo computed tomography (CT) images, we investigated the use of a CT-based machine learning algorithm for screening donor lungs before transplantation. Clinical measures and ex situ CT scans were collected from 100 cases as part of a prospective clinical trial. Following procurement, donor lungs were inflated, placed on ice according to routine clinical practice, and imaged using a clinical CT scanner before transplantation while stored in the icebox. We trained and tested a supervised machine learning method called dictionary learning, which uses CT scans and learns specific image patterns and features pertaining to each class for a classification task. The results were evaluated with donor and recipient clinical measures. Of the 100 lung pairs donated, 70 were considered acceptable for transplantation (based on standard clinical assessment) before CT screening and were consequently implanted. The remaining 30 pairs were screened but not transplanted. Our machine learning algorithm was able to detect pulmonary abnormalities on the CT scans. Among the patients who received donor lungs, our algorithm identified recipients who had extended stays in the intensive care unit and were at 19 times higher risk of developing chronic lung allograft dysfunction within 2 years posttransplant. We have created a strategy to ex vivo screen donor lungs using a CT-based machine learning algorithm. As the use of suboptimal donor lungs rises, it is important to have in place objective techniques that will assist physicians in accurately screening donor lungs to identify recipients most at risk of posttransplant complications.
Sections du résumé
BACKGROUND
BACKGROUND
Assessment and selection of donor lungs remain largely subjective and experience based. Criteria to accept or decline lungs are poorly standardized and are not compliant with the current donor pool. Using ex vivo computed tomography (CT) images, we investigated the use of a CT-based machine learning algorithm for screening donor lungs before transplantation.
METHODS
METHODS
Clinical measures and ex situ CT scans were collected from 100 cases as part of a prospective clinical trial. Following procurement, donor lungs were inflated, placed on ice according to routine clinical practice, and imaged using a clinical CT scanner before transplantation while stored in the icebox. We trained and tested a supervised machine learning method called dictionary learning, which uses CT scans and learns specific image patterns and features pertaining to each class for a classification task. The results were evaluated with donor and recipient clinical measures.
RESULTS
RESULTS
Of the 100 lung pairs donated, 70 were considered acceptable for transplantation (based on standard clinical assessment) before CT screening and were consequently implanted. The remaining 30 pairs were screened but not transplanted. Our machine learning algorithm was able to detect pulmonary abnormalities on the CT scans. Among the patients who received donor lungs, our algorithm identified recipients who had extended stays in the intensive care unit and were at 19 times higher risk of developing chronic lung allograft dysfunction within 2 years posttransplant.
CONCLUSIONS
CONCLUSIONS
We have created a strategy to ex vivo screen donor lungs using a CT-based machine learning algorithm. As the use of suboptimal donor lungs rises, it is important to have in place objective techniques that will assist physicians in accurately screening donor lungs to identify recipients most at risk of posttransplant complications.
Identifiants
pubmed: 37778525
pii: S1053-2498(23)02031-4
doi: 10.1016/j.healun.2023.09.018
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Commentaires et corrections
Type : UpdateOf
Informations de copyright
Copyright © 2023 International Society for the Heart and Lung Transplantation. Published by Elsevier Inc. All rights reserved.