Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Apr 24:7:46769.
doi: 10.1038/srep46769.

PathoSpotter-K: A computational tool for the automatic identification of glomerular lesions in histological images of kidneys

George O Barros  1 , Brenda Navarro  2 , Angelo Duarte  1 , Washington L C Dos-Santos  2
Affiliations

PathoSpotter-K: A computational tool for the automatic identification of glomerular lesions in histological images of kidneys

George O Barros et al. Sci Rep. .

Abstract

PathoSpotter is a computational system designed to assist pathologists in teaching about and researching kidney diseases. PathoSpotter-K is the version that was developed to detect nephrological lesions in digital images of kidneys. Here, we present the results obtained using the first version of PathoSpotter-K, which uses classical image processing and pattern recognition methods to detect proliferative glomerular lesions with an accuracy of 88.3 ± 3.6%. Such performance is only achieved by similar systems if they use images of cell in contexts that are much less complex than the glomerular structure. The results indicate that the approach can be applied to the development of systems designed to train pathology students and to assist pathologists in determining large-scale clinicopathological correlations in morphological research.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing financial interests.

Figures

Figure 1
Figure 1. Two images of glomeruli.
(a) Glomerulus with a proliferative glomerulopathy. (b) Normal glomerulus. The enlarged areas (a’,b’) emphasize cell clusters and highlight proliferative vs non-proliferative areas, respectively. Stained with hematoxylin and eosin. Magnification bar = 60 μm.
Figure 2
Figure 2. Representative images from the dataset.
Images (a–d) represent glomeruli with proliferative lesions. Images (e–h) represent normal glomeruli. Stained with hematoxylin and eosin. Magnification bar = 60 μm.
Figure 3
Figure 3. PathoSpotter-K system architecture.
Figure 4
Figure 4
Operation for separating the hematoxylin information (b) from the original colored image (a).
Figure 5
Figure 5. Segmentation stages.
Figure 6
Figure 6. Distribution of the images into the feature space.
Figure 7
Figure 7. Error rates for the different kNN models tested.
The yellow dot indicates the better configuration (Manhattan with k = 11).
Figure 8
Figure 8. Organization of the datasets used to configure the kNN classifier.
The generalization set yielded 10 different subsets according to the k-fold method.
See this image and copyright information in PMC

References

    1. Churg J., Bernstein J. & Glassock R. J. Renal disease: classification and atlas of glomerular diseases. 2 edn (Igaku-Shoin, 1995).
    1. Walker P. D., Cavallo T. & Bonsib S. M. Practice guidelines for the renal biopsy. Mod Pathol 17, 1555–1563 (2004). - PubMed
    1. Fogo A. B. Approach to renal biopsy. Am J Kidney Dis 42, 826–836, doi: S0272638603010540 (2003). - PubMed
    1. Chang A. et al.. A position paper on standardizing the nonneoplastic kidney biopsy report. Hum Pathol, doi: 10.1016/j.humpath.2012.04.009 (2012). - DOI - PubMed
    1. Tolles W. E. The cytoanalyzer-an example of physics in medical research. Trans N Y Acad Sci 17, 250–256 (1955). - PubMed

Publication types

MeSH terms