Deep-learning Based Pathological Assessment of Frozen Procurement Kidney Biopsies Predicts Graft Loss and Guides Organ Utilization: A Large-scale Retrospective Study

Yi, Z.; Xi, C.; Menon, M. C.; Cravedi, P.; Tedla, F.; Soto, A.; Sun, Z.; Liu, K.; Zhang, J.; Wei, C.; Chen, M.; Wang, W.; Veremis, B.; Garcia-barros, M.; Kumar, A.; Haakinson, D.; Brody, R.; Gallon, L.; O'Connell, P.; Naesens, M.; Shapiro, R.; Colvin, R.; Ward, S.; Salem, F.; Zhang, W.

doi:10.1101/2023.05.31.543098

Home/Archive/bioRxiv

bioRxiv · 10.1101/2023.05.31.543098

Deep-learning Based Pathological Assessment of Frozen Procurement Kidney Biopsies Predicts Graft Loss and Guides Organ Utilization: A Large-scale Retrospective Study

View original source ↗Export metadata ↓

Abstract

BackgroundLesion scores on procurement donor biopsies are commonly used to guide organ utilization. However, frozen sections present challenges for histological scoring, leading to inter- and intra-observer variability and inappropriate discard. MethodsWe constructed deep-learning based models to recognize kidney tissue compartments in H&E stained sections from procurement biopsies performed at 583 hospitals nationwide in year 2011-2020. The models were trained and tested respectively on 11473 and 3986 images sliced from 100 slides. We then extracted whole-slide abnormality features from 2431 kidneys, and correlated with pathologists scores and transplant outcomes. Finally, a Kidney Donor Quality Score (KDQS) incorporating digital features and the Kidney Donor Profile Index (KDPI) was derived and used in combination with recipient demographic and peri-transplant characteristics to predict graft loss or assist organ utilization. ResultsOur model accurately identified 96% and 91% of normal/sclerotic glomeruli respectively; 94% of arteries/arterial intimal fibrosis regions; 90% of tubules. Three whole-slide features (Sclerotic Glomeruli%, Arterial Intimal Fibrosis%, and Interstitial Fibrosis%) demonstrated strong correlations with corresponding pathologists scores (n=2431), but had superior associations with post-transplant eGFR (n=2033) and graft loss (n=1560). The combination of KDQS and other factors predicted 1- and 4-year graft loss (discovery: n=520, validation: n=1040). Finally, by matching 398 discarded kidneys due to "biopsy findings" to transplanted population, the matched transplants from discarded KDQS<4 group (110/398, 27.6%) showed similar graft survival rate to unmatched transplanted kidneys (2-, 5-year survival rate: 97%, 86%). KDQS [≥] 7 (37/398, 9.3%) and 1-year survival model score [≥] 0.55 were determined to identify possible discards (PPV=0.92). ConclusionThis deep-learning based approach provides automatic and reliable pathological assessment of procurement kidney biopsies, which could facilitate graft loss risk stratification and organ utilization. Translational StatementThis deep-learning based approach provides rapid but more objective, sensitive and reliable assessment of deceased-donor kidneys before transplantation, and improves the prognostic value of procurement biopsies, thus could potentially reduce inappropriate discard and stratify patients needing monitoring or preventative measures after transplantation. The pipeline can be integrated into various types of scanners and conveniently generates report after slide scanning. Such report can be used in conjunction with pathologists report or independently for centers lacking renal pathologists.

Explore related subjects

bioinformatics Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Yi, Z., Xi, C., Menon, M. C., Cravedi, P., Tedla, F., Soto, A., Sun, Z., Liu, K., Zhang, J., Wei, C., Chen, M., Wang, W., Veremis, B., Garcia-barros, M., Kumar, A., Haakinson, D., Brody, R., Gallon, L., O'Connell, P., Naesens, M., Shapiro, R., Colvin, R., Ward, S., Salem, F., Zhang, W.. 2023-06-04. Deep-learning Based Pathological Assessment of Frozen Procurement Kidney Biopsies Predicts Graft Loss and Guides Organ Utilization: A Large-scale Retrospective Study. https://doi.org/10.1101/2023.05.31.543098

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

mFrag: Integrating External DNA Methylation References Improves Lung Cancer Early Detection by Fragmentomics

Fragmentomics analyzes features of circulating cell-free DNA fragments (e.g., fragment length or end motifs) derived from whole-genome sequencing of liquid biopsy samples (blood or other body fluids), enabling non-invasive early cancer detection. Here we present mFrag, a framework that integrates external methylation reference atlases with fragmentomic features for lung cancer detection. mFrag comprises two complementary methods: mFrag-Weight, which uses DNA methylation information to weight fragmentomic features, and mFrag-Net, which integrates fragmentomic features and external DNA methylation data through neural networks. We average the output probabilities of the two methods to obtain a final prediction score. The mFrag model was trained using 287 individuals at risk for lung cancer. In an independent case-control testing set comprising 385 non-cancer controls and 46 cancers (28 stage I, 12 stage II, and 6 stage III or IV), mFrag outperforms a DELFI-style fragmentomic approach, improving PR-AUC from 0.455 to 0.720 and sensitivity at 99% specificity from 0.043 to 0.478, with ROC-AUC from 0.871 to 0.908. For stage I lung cancer, mFrag raises PR-AUC from 0.314 to 0.558 and ROC-AUC from 0.855 to 0.894. Applied to end 4-mer motif features, mFrag likewise improved over an unweighted baseline, with gains contributed by both mFrag-Weight and mFrag-Net. In summary, mFrag improves the accuracy of fragmentomics-based lung cancer detection through integrating external DNA methylation data and the complementarity of its two component models, without incurring any additional data-generating cost.

bioinformatics↗

bioRxiv2026

AOPTK: Open-Source Software for AI-Assisted Toxicological Literature Analysis

Motivation: Toxicologists today face a challenge: although vast amounts of data describing how chemicals affect human health are available across scientific publications and regulatory reports, much of this information remains underutilized because extracting and interpreting evidence across thousands of studies is impractical to perform manually. Recent advances in artificial intelligence (AI), particularly in large language models (LLMs), provide new opportunities to automate toxicological literature analysis. Results: Herein, we present the Adverse Outcome Pathway Toolkit (AOPTK), an open-source Python package for AI-enhanced analysis of toxicological and biomedical literature. AOPTK supports (i) automated literature retrieval from databases such as PubMed Central and Europe PMC, (ii) direct processing of full-text articles in PDF format, and (iii) LLM-assisted analysis tools to identify chemicals and extract their relationships to biological effects under user-defined conditions. We demonstrate its utilities through a case-study identifying potential non-genotoxic carcinogens based on their ability to inhibit gap junction intercellular communication (GJIC). The LLM-enhanced analysis achieves 81% agreement with an expert-curated inhibitor list and 95% accuracy in predicting inhibition versus no inhibition when analysing the same subset of 86 publications. Automated retrieval and analysis of 1 124 publications from PubMed Central further demonstrated the feasibility of applying AOPTK to large-scale literature analyses. Availability: The package is developed open source on GitHub, disseminated through PyPI and Bioconda and releases are archived on Zenodo. Individual tools are available in the Galaxy platform for accessible data analysis with user-friendly, findable, accessible, interoperable, and reusable (FAIR) and end-to-end workflows provided via WorkflowHub. The tools are available on usegalaxy.eu and usegalaxy.cz and are developed open source on GitHub.

bioinformatics↗

bioRxiv2026

MELD: Mutation Effect Learning through Differential embeddings

We introduce MELD (Mutation Effect Learning through Differential Embeddings), a compact model for predicting the functional consequences of single nucleotide variants (SNVs) by training directly on the wild-type (WT) versus mutant differential. Interpreting SNVs is central to clinical genomics, yet experimental characterization cannot scale to millions of observed variants. Leading sequence-to-function models (Enformer, Borzoi, AlphaGenome) are trained on absolute genomic tracks and score variants post hoc through in-silico mutagenesis (ISM), so the WT-mutant difference never enters the training loss. MELD instead places the logit difference {Delta}z = zmut - zwt inside the supervised objective. It combines a shared CNN-Transformer encoder, a mutant-specific mutation-mask boost, multiscale mutation-centered pooling, and a learned adaptive amplification factor . On ClinVar (1.57M variants), MELD (1.9M parameters) reached an AUROC of 0.986 versus 0.800 for a same-data, same-backbone ISM baseline, with ablations confirming the contribution of each component. On a shared benchmark, it outperformed frozen foundation models with 3-1,300x more parameters (AUROC 0.967 vs. 0.924 for AlphaGenome and 0.936 for Nucleotide Transformer). With only 50, 000 training variants, it exceeded the ISM baseline trained on all 1.48M (AUROC 0.903 vs. 0.796) variants. On BRCA1 saturation genome editing, frozen MELD achieved a Spearman {rho} of 0.42, above Borzoi (0.40), and ClinVar transfer raised it to 0.45. These results demonstrate that direct differential supervision is a compact, data-efficient alternative to post-hoc ISM scoring with substantially larger pretrained models.

bioinformatics↗