Two common obstacles limiting the performance of data-driven algorithms in digital histopathology classification tasks are the lack of expert annotations and the narrow diversity of datasets. Multi-instance learning (MIL) can be used to address the former challenge for the analysis of whole slide images (WSI) but performance is often inferior to full supervision. We show that the inclusion of weak annotations can bring significant benefits to MIL while keeping the approach scalable. An analysis workflow was developed to process periodic acid-Schiff (PAS) and Sirius Red (SR) slides. The workflow segments tissues into coarse tissue classes. Handcrafted and deep features were extracted from these tissues and combined using a soft attention model to predict several slide-level labels: delayed graft function (DGF), acute tubular injury (ATI), and Remuzzi grade components. A tissue segmentation quality metric was also developed to reduce the noisy impact of poorly segmented instances. The soft attention model was trained using 5-fold cross-validation on a mixed dataset and tested on the QUOD dataset containing n=373 PAS and n=195 SR biopsies. The average ROC-AUC over different prediction tasks was found to be 0.598±0.011, significantly higher than using only ResNet50 (0.545±0.012), only handcrafted features (0.542±0.011), and the baseline (0.532±0.012) of state-of-the-art performance. Weighting tissues by segmentation quality in conjunction with the soft attention has led to further improvement (AUC=0.618±0.010). Using an intuitive visualisation scheme, we show that our workflow may also be used for high-precision diagnostics as it allows pinpointing individual tissues relevant to the predictions.

The authors have declared no competing interest.

KHT is funded by the EPSRC and MRC grant number EP/L016052/1. JR is supported by the Oxford NIHR Biomedical Research Centre and the PathLAKE consortium (Innovate UK App. Nr. 18181). JK is supported by the Dutch Kidney Foundation (Grant No. 17OKG23) and the Human(e) AI Research Priority Area by the University of Amsterdam.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Use of QUOD samples: NHS Health Authority, National Research Ethics Service, gave ethical approval for this work (IRAS project ID: 87824; Quality in Organ Donation (QUOD) (NW/18/0187), sponsored by University of Oxford.) Use of native biopsies: Research Ethics Committee of Oxford University Hospital - NHS Foundation Trust Research and Governance gave ethical approval for this work. (19/WM/0215) Use of NMP dataset: The National Ethics Review Committee (East of England) of the United Kingdom gave ethical approval for this work. (REC reference (12/EE/0273), IRAS project ID 106793)

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.

Yes

All data produced in the present study are available upon reasonable request to the authors.