Explainability of a Deep Learning-Based Classification Model for Antineutrophil Cytoplasmic Autoantibody–Associated Glomerulonephritis

Kidney International Reports, vol. 10, pp. 457–465

Abstract

Introduction: The histopathological classification for antineutrophil cytoplasmic autoantibody (ANCA)-associated glomerulonephritis (ANCA-GN) is a well-established tool to reflect the variety of patterns and severity of lesions that can occur in kidney biopsies. It was demonstrated previously that deep learning (DL) approaches can aid in identifying histopathological classes of kidney diseases; for example, of diabetic kidney disease. These models can potentially be used as decision support tools for kidney pathologists. Although they reach high prediction accuracies, their "black box" structure makes them nontransparent. Explainable (X) artificial intelligence (AI) techniques can be used to make the AI model decisions accessible for human experts. We have developed a DL-based model, which detects and classifies the glomerular lesions according to the Berden classification. Methods: Kidney biopsy slides of 80 patients with ANCA-GN from 3 European centers, who underwent a diagnostic kidney biopsy between 1991 and 2011, were included. We also investigated the explainability of our model using Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps. These maps were analyzed by pathologists to compare the decision-making criteria of humans and the DL model and assess the impact of different training settings. Results: The DL model shows a prediction accuracy of 93% for classifying lesions. The heatmaps from our trained DL models showed that the most predictive areas in the image correlated well with the areas deemed to be important by the pathologist. Conclusion: We present the first DL-based computational pipeline for classifying ANCA-GN kidney biopsies as per the Berden classification. XAI techniques helped us to make the decision-making criteria of the DL accessible for renal pathologists, potentially improving clinical decision-making.

Authors 12

1. Maria A.C. Wester Trejo Aachen Department of Pathology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands

2. Maryam Sadeghi

   Innsbruck Medical University · Universität Innsbruck

   Affiliation as printed

   Department of Medical Statistics, Informatics and Health Economics, Medical University of Innsbruck, Innsbruck, Austria

3. Shivam Singh

   Innsbruck Medical University · Universität Innsbruck

   Affiliation as printed

   Department of Medical Statistics, Informatics and Health Economics, Medical University of Innsbruck, Innsbruck, Austria

4. Naghmeh Mahmoodian

   Otto-von-Guericke-Universität Magdeburg

   Affiliation as printed

   Faculty of Computer Science, Otto von Guericke University, Magdeburg, Germany

5. Samir Sharifli

   Innsbruck Medical University · Universität Innsbruck

   Affiliation as printed

   Department of Internal Medicine IV, Nephrology and Hypertension, Medical University of Innsbruck, Innsbruck, Austria

6. Zdenka Hrušková

   Charles University · General University Hospital in Prague

   Affiliation as printed

   Department of Nephrology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, Czechia

7. Vladimı́r Tesař

   Charles University · General University Hospital in Prague

   Affiliation as printed

   Department of Nephrology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, Czechia

8. Xavier Puéchal

   Hôpital Cochin · Assistance Publique – Hôpitaux de Paris

   Affiliation as printed

   Department of Internal Medicine, Hôpital Cochin, AP-HP, Paris, France

9. JAN ANTHONIE BRUIJN Aachen Department of Pathology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands

10. Georg Göbel

    Innsbruck Medical University · Universität Innsbruck

    Affiliation as printed

    Department of Medical Statistics, Informatics and Health Economics, Medical University of Innsbruck, Innsbruck, Austria

11. Ingeborg M. Bajema corresponding

    University Medical Center Groningen

    Affiliation as printed

    Department of Pathology and Medical Biology, University Medical Center Groningen, Groningen, The Netherlands

12. Andreas Kronbichler corresponding

    Innsbruck Medical University · Universität Innsbruck

    Affiliation as printed

    Department of Internal Medicine IV, Nephrology and Hypertension, Medical University of Innsbruck, Innsbruck, Austria