MO078DEEP LEARNING DIAGNOSIS OF ANTIBODY-MEDIATED REJECTION (AMR) ON GLOMERULAR TRANSECTIONS

Abstract

Abstract Background and Aims Antibody-mediated rejection (AMR) is among the most common causes for kidney transplant loss. The histological diagnosis is hampered by significant intra- and interobserver variability. Training a deep learning classifier for the recognition of AMR on glomerular transections as the most decisive compartment could establish a reliable and perfectly reproducible diagnostic method. Method We identified 48 biopsies with AMR (all positive for donor-specific antibody) and 38 biopsies without AMR according to Banff 2017 from our archive. Photographs were taken from all non-globally sclerosed glomeruli on two PAS-stained level sections, yielding a total of 1,655 images as a training set. 1,503 images could be labeled by three experienced nephropathologists conclusively as AMR or non-AMR in a blinded fashion. We trained a DenseNet-121 classifier (pre-trained on ImageNet) with basic online augmentation. In addition, we implemented StyPath++, a data augmentation algorithm that leverages a style transfer mechanism, addressing significant domain shifts in histopathology. Each sample was assigned a consensus label generated by the pathologists. Results Five-fold cross validation schemes produced a weighted glomerular level performance of 88.1%, exceeding the baseline performance by 5%. The improved generalization ability of the StyPath++ augmented model shows that it is possible to construct reliable glomerular classification algorithms with scarce datasets. Conclusion We created a deep learning classifier with excellent performance and reproducibility for the diagnosis of AMR on glomerular transections. We plan to expand the training set, including challenging cases of differential diagnoses like glomerulonephritis or other glomerulopathies. We are also interested in external clinicopathological datasets to further validate our results.