Histopathologic and radiologic assessment of nontransplanted donor lungs

Computed tomography-based machine learning for donor lung screening before transplantation

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.

Identification of regional variation in gene expression and inflammatory proteins in donor lung tissue and ex vivo lung perfusate

OBJECTIVE

Diagnosing lung injury is a challenge in lung transplantation. It has been unclear if a single biopsy specimen is truly representative of the entire organ. Our objective was to investigate lung inflammatory biomarkers using human lung tissue biopsies and ex vivo lung perfusion perfusate.

METHODS

Eight human donor lungs declined for transplantation were air inflated, flash frozen, and partitioned from apex to base. Biopsies were then sampled throughout the lung. Perfusate was sampled from 4 lung lobes in 8 additional donor lungs subjected to ex vivo lung perfusion. The levels of interleukin-6, interleukin-8, interleukin-10, and interleukin-1β were measured using quantitative reverse transcription polymerase chain reaction from lung biopsies and enzyme-linked immunosorbent assay from ex vivo lung perfusion perfusate.

RESULTS

The median intra-biopsy equal-variance P value was .50 for messenger RNA biomarkers in tissue biopsies. The median intra-biopsy coefficient of variance was 18%. In donors with no apparent focal injuries, the biopsies in each donor showed no difference in various lung slices, with a coefficient of variance of 20%. The exception was biopsies from the lingula and injured focal areas that demonstrated larger differences. Cytokines in ex vivo lung perfusion perfusate showed minimal variation among different lobes (coefficient of variance = 4.9%).

CONCLUSIONS

Cytokine gene expression in lung biopsies was consistent, and the biopsy analysis reflects the whole lung, except when specimens were collected from the lingula or an area of focal injury. Ex vivo lung perfusion perfusate also provides a representative measurement of lung inflammation from the draining lobe. These results will reassure clinicians that a lung biopsy or an ex vivo lung perfusion perfusate sample can be used to inform donor lung selection.

CT-based Machine Learning for Donor Lung Screening Prior to Transplantation

Background

Assessment and selection of donor lungs remains 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 CT images, we investigated the use of a CT-based machine learning algorithm for screening donor lungs prior to 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 prior to 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) prior to 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 ICU and were at 19 times higher risk of developing CLAD within 2 years post-transplant.

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 post-transplant complications.

A Retrospective Review of Declined Lung Donors: Estimating the Potential of Ex Vivo Lung Perfusion

BACKGROUND

Even in the extended-criteria era, the reasons for declining lung donors are not always clear. Furthermore, it has not been determined how many actual declined lungs would be retrieved by ex vivo lung perfusion (EVLP) beyond that already achieved in centers with an existing high utilization rate.

METHODS

This retrospective study reviewed all lung donor referrals between 2014 and 2018, including detailed formal referrals and preliminary notifications. This study categorized reasons for lung donor non-acceptance and estimated how many declined grafts could have been theoretically retrievable by using EVLP.

RESULTS

In total, 966 lung donor candidates were referred, including 313 transplanted donors, 336 declined donors after detailed referrals (group A) and 258 preliminary declined. In group A, the primary reasons for refusal were lung quality issues (49%), general medical issues (25%), and organization issues (26%), combined with secondary reasons in many cases. Main lung quality issues were an extensive smoking history, abnormal chest radiography, and underlying lung disease. Although 73 declined lung donors had indications for EVLP, the retrievable lungs decreased to only 30 cases after considering the details of all clinical contraindications and organizational issues. Nevertheless, 59 intended donation after circulatory death donors did not progress to death after withdrawal of cardiorespiratory support in the required timeframe, and EVLP may have an emerging additional role here.

CONCLUSIONS

Based on commonly cited criteria for EVLP indication, the number of EVLP retrievable lung donors represented only a small portion of declined donor lungs referred to our center from the state donation network.

Ex vivo lung CT findings may predict the outcome of the early phase after lung transplantation

Purpose

We developed an ex vivo lung CT (EVL-CT) technique that allows us to obtain detailed CT images and morphologically assess the retrieved lung from a donor for transplantation. After we recovered the lung graft from a brain-dead donor, we transported it to our hospital and CT images were obtained ex vivo before lung transplant surgery. The objective of this study was to investigate the correlation between the EVL-CT findings and post-transplant outcome in patients who underwent bilateral lung transplantation (BLT) or single lung transplantation (SLT).

Methods

We retrospectively reviewed the records of 70 patients with available EVL-CT data who underwent BLT (34 cases) or SLT (36 cases) in our hospital between October 2007 and September 2017. The recipients were divided into 2 groups (control group, infiltration group) according to the findings of EVL-CT of the lung graft in BLT and SLT, respectively. Recipients in the control group were transplanted lung grafts without any infiltrates (BLT control group, SLT control group). Recipients in the infiltration group received lung grafts with infiltrates (BLT infiltration group, SLT infiltration group).

Results

The recipients in the BLT infiltration group showed significantly slower recovery from primary graft dysfunction and a longer mechanical ventilation period and ICU stay period than those in the BLT control group. The mechanical ventilation period was significantly longer in the recipients in the SLT infiltration group than those in the SLT control group.

Conclusion

EVL-CT may predict the outcome of the early phase after lung transplantation.