Transformer-based multiclass segmentation pipeline for basic kidney histology

medRxiv

Abstract

Abstract Multiclass segmentation of microanatomy in kidney biopsies is an important and non-trivial task in computational renal pathology. In a multicenter study, we densely annotated basic anatomical objects (glomeruli, tubules, and vessels) in 261 regions of interest of 147 kidney biopsy WSIs sourced from the archives of hospitals in Amsterdam, Utrecht, and Leiden (Netherlands). And we trained multiple UNet- and Mask2Former-based models on WSI-level and patch-level splitting methods, and compared their performance across training strategies. Test performance was assessed on 24 annotated renal WSIs from Leuven (Belgium) with sensitivity analysis on the extent of fibrosis and inflammation. At the patch-level, UNet-ResNet18 achieved comparable performances to M2F-Swin-B with average Intersection over Union of all classes (A-IoU, 0.84 vs 0.94), as well as per-class IoU. However, at the WSI-level, M2F-Swin-B significantly surpassed UNet-ResNet18 with large margins on A-IoU (0.84 vs 0.48), with similar observed in per-class IoU. Notably, M2F-Swin-B outperformed UNet-ResNet18 in scenarios characterized by a higher degree of fibrosis and inflammation (A-IoU, 0.76 vs 0.66). Furthermore, at the WSI-level, M2F-Swin-B achieved IoU score of arteries to 0.58, whereas UNet-ResNet18 only achieved 0.33. In this study, we found that the attention mechanism in Mask2Former enables visibly crisper and more uniform segmentation, particularly when data is inadequate. Mask2Former-based models outperform UNet-based models in challenging areas from inflamed and fibrotic renal biopsies.

Authors 14

1. Junling He Aachen Department of Pathology, LUMC

   Leiden University Medical Center

   Affiliation as printed

   Department of Pathology, LUMC, Leiden, Netherlands

2. P. Valkema Aachen Department of Pathology, LUMC

   Leiden University Medical Center · Amsterdam University Medical Centers

   Affiliation as printed

   Department of Pathology, Amsterdam UMC, Amsterdam, Netherlands

   Department of Pathology, LUMC, Leiden, Netherlands

3. Jingmin Long Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands

4. Li-Jia Li Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands

5. Sandrine Florquin

   Amsterdam University Medical Centers

   Affiliation as printed

   Department of Pathology, Amsterdam UMC, Amsterdam, Netherlands

6. Maarten Naesens

   KU Leuven

   Affiliation as printed

   Department of Nephrology and Transplantation, KU Leuven, Leuven, Belgium

7. Priyanka Joseph Koshy

   KU Leuven

   Affiliation as printed

   Department of Microbiology, Immunology and Transplantation, KU Leuven, Leuven, Belgium

8. Tri Quang Nguyen

   University Medical Center Utrecht

   Affiliation as printed

   Department of Pathology, UMC Utrecht, Utrecht Netherlands

9. Soufian Meziyerh Aachen Division of Nephrology Department of Medicine, LUMC Leiden Transplant Center

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Division of Nephrology, Department of Medicine, LUMC, Leiden, Netherlands

   Leiden Transplant Center, LUMC and Leiden University, Leiden, Netherlands

10. Aiko P. J. de Vries Aachen Division of Nephrology Department of Medicine, LUMC Leiden Transplant Center

    Leiden University · Leiden University Medical Center

    Affiliation as printed

    Division of Nephrology, Department of Medicine, LUMC, Leiden, Netherlands

    Leiden Transplant Center, LUMC and Leiden University, Leiden, Netherlands

11. Onno J. de Boer

    Amsterdam University Medical Centers

    Affiliation as printed

    Department of Pathology, Amsterdam UMC, Amsterdam, Netherlands

12. Verbeek Fons J Aachen Leiden Institute of Advanced Computer Science

    Leiden University

    Affiliation as printed

    Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands

13. Zhan Xiong Aachen Leiden Institute of Advanced Computer Science

    Leiden University

    Affiliation as printed

    Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands

14. Jesper Kers corresponding Aachen Department of Pathology, LUMC Leiden Transplant Center

    Leiden University · Leiden University Medical Center · Amsterdam University Medical Centers · University of Amsterdam

    Affiliation as printed

    Department of Pathology, Amsterdam UMC, Amsterdam, Netherlands

    Department of Pathology, LUMC, Leiden, Netherlands

    HIMS, University of Amsterdam, Amsterdam, Netherlands

    Leiden Transplant Center, LUMC and Leiden University, Leiden, Netherlands