Computed tomography-based machine learning for donor lung screening before transplantation
Copyright © 2023 International Society for the Heart and Lung Transplantation. Published by Elsevier Inc. All rights reserved..
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: 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: 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: 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.
Errataetall: | |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:43 |
---|---|
Enthalten in: |
The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation - 43(2024), 3 vom: 30. März, Seite 394-402 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Ram, Sundaresh [VerfasserIn] |
---|
Links: |
---|
Themen: |
Computed tomography |
---|
Anmerkungen: |
Date Completed 26.02.2024 Date Revised 08.03.2024 published: Print-Electronic UpdateOf: medRxiv. 2023 Mar 29;:. - PMID 37034670 Citation Status MEDLINE |
---|
doi: |
10.1016/j.healun.2023.09.018 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM362744041 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM362744041 | ||
003 | DE-627 | ||
005 | 20240308232057.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.healun.2023.09.018 |2 doi | |
028 | 5 | 2 | |a pubmed24n1320.xml |
035 | |a (DE-627)NLM362744041 | ||
035 | |a (NLM)37778525 | ||
035 | |a (PII)S1053-2498(23)02031-4 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Ram, Sundaresh |e verfasserin |4 aut | |
245 | 1 | 0 | |a Computed tomography-based machine learning for donor lung screening before transplantation |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 26.02.2024 | ||
500 | |a Date Revised 08.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a UpdateOf: medRxiv. 2023 Mar 29;:. - PMID 37034670 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 International Society for the Heart and Lung Transplantation. Published by Elsevier Inc. All rights reserved. | ||
520 | |a 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 | ||
520 | |a 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 | ||
520 | |a 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 | ||
520 | |a 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 | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Computed tomography | |
650 | 4 | |a Dictionary learning | |
650 | 4 | |a Donor assessment | |
650 | 4 | |a Donor lung screening | |
650 | 4 | |a Lung transplantation | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Primary graft dysfunction | |
700 | 1 | |a Verleden, Stijn E |e verfasserin |4 aut | |
700 | 1 | |a Kumar, Madhav |e verfasserin |4 aut | |
700 | 1 | |a Bell, Alexander J |e verfasserin |4 aut | |
700 | 1 | |a Pal, Ravi |e verfasserin |4 aut | |
700 | 1 | |a Ordies, Sofie |e verfasserin |4 aut | |
700 | 1 | |a Vanstapel, Arno |e verfasserin |4 aut | |
700 | 1 | |a Dubbeldam, Adriana |e verfasserin |4 aut | |
700 | 1 | |a Vos, Robin |e verfasserin |4 aut | |
700 | 1 | |a Galban, Stefanie |e verfasserin |4 aut | |
700 | 1 | |a Ceulemans, Laurens J |e verfasserin |4 aut | |
700 | 1 | |a Frick, Anna E |e verfasserin |4 aut | |
700 | 1 | |a Van Raemdonck, Dirk E |e verfasserin |4 aut | |
700 | 1 | |a Verschakelen, Johny |e verfasserin |4 aut | |
700 | 1 | |a Vanaudenaerde, Bart M |e verfasserin |4 aut | |
700 | 1 | |a Verleden, Geert M |e verfasserin |4 aut | |
700 | 1 | |a Lama, Vibha N |e verfasserin |4 aut | |
700 | 1 | |a Neyrinck, Arne P |e verfasserin |4 aut | |
700 | 1 | |a Galban, Craig J |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation |d 1993 |g 43(2024), 3 vom: 30. März, Seite 394-402 |w (DE-627)NLM012612367 |x 1557-3117 |7 nnns |
773 | 1 | 8 | |g volume:43 |g year:2024 |g number:3 |g day:30 |g month:03 |g pages:394-402 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.healun.2023.09.018 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 43 |j 2024 |e 3 |b 30 |c 03 |h 394-402 |