Improved assessment of donor liver steatosis using Banff consensus recommendations and deep learning algorithms

BACKGROUND & AIMS

The Banff Liver Working Group recently published consensus recommendations for steatosis assessment in donor liver biopsy, but few studies reported their use and no automated deep-learning algorithms based on the proposed criteria have been developed so far. We evaluated Banff recommendations on a large monocentric series of donor liver needle biopsies by comparing pathologists' scores with those generated by convolutional neural networks (CNNs) we specifically developed for automated steatosis assessment.

METHODS

We retrospectively retrieved 292 allograft liver needle biopsies collected between January 2016 and January 2020 and performed steatosis assessment using a former intra-institution method (pre-Banff method) and the newly introduced Banff recommendations. Scores provided by pathologists and CNN models were then compared, and the degree of agreement was measured with the intraclass correlation coefficient (ICC).

RESULTS

Regarding the pre-Banff method, poor agreement was observed between the pathologist and CNN models for small droplet macrovesicular steatosis (ICC: 0.38), large droplet macrovesicular steatosis (ICC: 0.08), and the final combined score (ICC: 0.16) evaluation, but none of these reached statistically significance. Interestingly, significantly improved agreement was observed using the Banff approach: ICC was 0.93 for the low-power score (p <0.001), 0.89 for the high-power score (p <0.001), and 0.93 for the final score (p <0.001). Comparing the pre-Banff method with the Banff approach on the same biopsy, pathologist and CNN model assessment showed a mean (±SD) percentage of discrepancy of 26.89 (±22.16) and 1.20 (±5.58), respectively.

CONCLUSIONS

Our findings support the use of Banff recommendations in daily practice and highlight the need for a granular analysis of their effect on liver transplantation outcomes.

IMPACT AND IMPLICATIONS

We developed and validated the first automated deep-learning algorithms for standardized steatosis assessment based on the Banff Liver Working Group consensus recommendations. Our algorithm provides an unbiased automated evaluation of steatosis, which will lay the groundwork for granular analysis of steatosis's short- and long-term effects on organ viability, enabling the identification of clinically relevant steatosis cut-offs for donor organ acceptance. Implementing our algorithm in daily clinical practice will allow for a more efficient and safe allocation of donor organs, improving the post-transplant outcomes of patients.

Removal of UK-donor deferral for variant Creutzfeldt-Jakob disease: A large donation gain in Australia

BACKGROUND AND OBJECTIVES

Until 25 July 2022, people who spent more than 6 months in the United Kingdom during the variant Creutzfeldt-Jakob disease (vCJD) risk period 1980-1996 (UK donors) were deferred from blood donation in Australia. Regulatory approval to remove the deferral was underpinned by published mathematical modelling predicting negligible vCJD transmission risk increase with a gain of 58,000 donations.

MATERIALS AND METHODS

The donor questionnaire retained the UK deferral screening question until a version update effective 12 February 2023, which enabled identification of the newly eligible cohort of UK donors. Their donations were tracked for a 6-month period (25 July 2022-24 January 2023) and compared with baseline Lifeblood donation metrics and predicted gains.

RESULTS

A total of 38,462 UK donors attended to donate 78,762 times in the 6 months. Of these, 32,358 donors (females = 19,456, males = 12,902) successfully donated 67,914 times representing 8.4% of total collections.

CONCLUSION

Cessation of the UK deferral resulted in donation gains exceeding modelled predictions because of a higher than predicted number of donors who donated at a higher rate. Had these newly eligible donors not donated, overall donation numbers would have been 88% of target rather than the 96% achieved.

Horiba Micros ES 60 Blood Cell Analyzer in Blood Donor Eligibility: A Validation Study

Background: Eligibility criteria for blood donation require hemoglobin levels of ≥12.5 g/dL for women and ≥13.5 g/dL for men, and a platelet count of ≥180 × 109/L. Screening methods before donation should ensure high accuracy, precision, and ease in operation. We assessed the performance, precision, and repeatability of the Horiba Micros ES 60 (Horiba) compared to the Beckman Coulter DXH 800. Methods: Performance was compared by testing samples for each of the 11 devices across 6 sites in the Transfusion Service of Friuli Venezia Giulia Region, Italy. We measured precision by calculating the coefficient of variation (CV), concordance with ρ-Pearson’s correlation coefficient, and accuracy with F-tests. The intra-assay agreement was examined in the 11 devices, and repeatability was performed by using CV and the Kruskal−Wallis test. Results: The precision of Horiba was acceptable. Overall, ρ-Pearson’s coefficients indicated a strong correlation and positive relationship between all variables. The Bland−Altman plots showed that most of the differences lay within the limits of agreement. All CV were below the reference threshold for all the parameters. Finally, the Kruskal−Wallis test reported non-significant statistical differences for all parameters, except platelet count (p < 0.000). Conclusions: Horiba is adequate for routine pre-donation screening. The intra-assay agreement further demonstrates the accuracy of the device.

Minority donation in the United States: challenges and needs

PURPOSE OF REVIEW

In the United States, blood donation rates of African-Americans are 25-50% of that of white individuals. As African-Americans make up an ever increasing and now substantial minority, and African-American recipients of blood transfusion, both specialized, such as sickle cell disease patients, and general hospitalized patients, have a better chance of receiving phenotype-matched or appropriate red blood cell units when there is a significant percentage of products in the inventory from African-American donors, it is important to understand the reason for the observed difference.

RECENT FINDINGS

Possible reasons for this discrepancy in donation rates include increased rates of donor deferral and ineligibility; increased barriers to donation, such as fear and distrust; and different marketing and education strategies. Thus, to increase the blood availability to African-American recipients, the reasons for these donation rate differences must be better understood and subsequently addressed through improved blood donor recruitment programs. The majority of African-American donor recruitment programs have focused on donating for sickle cell disease patients, particularly children, which have been of limited success.

SUMMARY

Significant improvements in African-American donor recruitment are needed to adequately meet the demand of African-American patients as well as the entire population.