# CNN Cascades for Segmenting Whole Slide Images of the Kidney

arXiv: https://arxiv.org/abs/1708.00251 · HTML: https://mlsanity.com/paper/1708.00251/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2017.

## Built on by (most cited first, 10 of 10)

- [Omni-Seg: A Scale-aware Dynamic Network for Renal Pathological Image Segmentation](https://mlsanity.com/paper/2206.13632/) (2022)
- [Circle Representation for Medical Object Detection](https://mlsanity.com/paper/2110.12093/) (2021)
- [PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation](https://mlsanity.com/paper/2402.19286/) (2024)
- [Compound Figure Separation of Biomedical Images with Side Loss](https://mlsanity.com/paper/2107.08650/) (2021)
- [HoloHisto: End-to-end Gigapixel WSI Segmentation with 4K Resolution Sequential Tokenization](https://mlsanity.com/paper/2407.03307/) (2024)
- [Glo-In-One: Holistic Glomerular Detection, Segmentation, and Lesion Characterization with Large-scale Web Image Mining](https://mlsanity.com/paper/2206.00123/) (2022)
- [CircleSnake: Instance Segmentation with Circle Representation](https://mlsanity.com/paper/2211.01254/) (2022)
- [Circle Representation for Medical Instance Object Segmentation](https://mlsanity.com/paper/2403.11507/) (2024)
- [IRS: Incremental Relationship-guided Segmentation for Digital Pathology](https://mlsanity.com/paper/2505.22855/) (2025)
- [Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised Learning](https://mlsanity.com/paper/2208.14357/) (2022)

## Abstract (arXiv)

Due to the increasing availability of whole slide scanners facilitating digitization of histopathological tissue, there is a strong demand for the development of computer based image analysis systems. In this work, the focus is on the segmentation of the glomeruli constituting a highly relevant structure in renal histopathology, which has not been investigated before in combination with CNNs. We propose two different CNN cascades for segmentation applications with sparse objects. These approaches are applied to the problem of glomerulus segmentation and compared with conventional fully-convolutional networks. Overall, with the best performing cascade approach, single CNNs are outperformed and a pixel-level Dice similarity coefficient of 0.90 is obtained. Combined with qualitative and further object-level analyses the obtained results are assessed as excellent also compared to recent approaches. In conclusion, we can state that especially one of the proposed cascade networks proved to be a highly powerful tool for segmenting the renal glomeruli providing best segmentation accuracies and also keeping the computing time at a low level.