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
. 2019 Feb:10956:1095608.
doi: 10.1117/12.2513598. Epub 2019 Mar 18.

Examining Structural Patterns and Causality in Diabetic Nephropathy using inter-Glomerular Distance and Bayesian Graphical Models

Aurijoy Majumdar  1 , Kuang-Yu Jen  2 , Sanjay Jain  3 , John E Tomaszewski  1 , Pinaki Sarder  1
Affiliations

Examining Structural Patterns and Causality in Diabetic Nephropathy using inter-Glomerular Distance and Bayesian Graphical Models

Aurijoy Majumdar et al. Proc SPIE Int Soc Opt Eng. 2019 Feb.

Abstract

In diabetic nephropathy (DN), hyperglycemia drives a progressive thickening of glomerular filtration surfaces, increased cell proliferation as well as mesangial expansion and a constriction of capillary lumens. This leads to progressive structural changes inside the Glomeruli. In this work, we make a study of structural glomerular changes in DN from a graph-theoretic standpoint, using features extracted from Minimal Spanning Trees (MSTs) constructed over intercellular distances in order to classify the "packing signatures" of different DN stages. We further investigate the significance of the competing effects of Volume change measured here in 2Dimensional Pixel span area (Area) on one hand and increased cell proliferation on the other in determining the packing patterns. Towards that we formulate the problem as Dynamic Bayesian Network (DBN). From our preliminary results we do postulate that volume expansion caused by internal pressure as capillary lumens constriction has perhaps has a greater effect in the early stages.

Keywords: Diabetic nephropathy; Dynamic Bayesian Network; Graphical Models; Medical Image processing; Minimum Spanning Tree; Support Vector Machine; whole slide image analysis.

PubMed Disclaimer

Figures

None
Fig 1a Minimum Spanning Tree constructed from Glomeruli. Fig 1b MST connecting the centroids of the nuclei.
None
Fig 2a and Fig 2b show the Distribution of Glom Area which is the most relevant support vector in 1 vs 2 case and 1 vs 3 case. Fig 2c represents precision vs recall value for all the SVM experiments. Preliminary results show that area, cellularity and k-clusters are the most important support vectors.
None
Fig3 represents an example of a candidate Dynamic Bayesian network where the letter and corresponding parameters are respectively: A: Area & ƟA :Distribution in Area within that time slice. B: Cellularity & ƟB: Distribution of Cellularity within time slice. C: Packing Distribution & ƟC: Distribution of Packing Distribution within that time slice. D: Clusters and ƟD: Distribution of cluster coefficient within time slice. E: MST edge length and ƟE: Distribution of MST edge length within a time slice. The time t−1, t, t+1 slices themselves represent Disease stages 1, 2 and 3. The inter time slice connections are transition weights which will remain stationary for simplicity.
None
Fig 4 describes the relative edge weight in the three stages.
See this image and copyright information in PMC

References

    1. Magee C, Grieve DJ, Watson CJ et al., “Diabetic Nephropathy: a Tangled Web to Unweave,” Cardiovasc Drugs Ther, 31(5-6), 579–592 (2017). - PMC - PubMed
    1. Liu ZZ, Bullen A, Li Y et al., “Renal Oxygenation in the Pathophysiology of Chronic KidneyDisease,” Front Physiol, 8, 385 (2017). - PMC - PubMed
    1. Zeni L, Norden AGW, Cancarini G et al., “A more tubulocentric view of diabetic kidney disease,” J Nephrol, 30(6), 701–717 (2017). - PMC - PubMed
    1. National Chronic Kidney Disease Fact Sheet, 2014. Available from: https://www.cdc.gov/diabetes/pubs/pdf/kidney_factsheet.pdf
    1. Papadopoulou-Marketou N, Chrousos GP and Kanaka-Gantenbein C, “Diabetic nephropathy in type 1 diabetes: a review of early natural history, pathogenesis, and diagnosis,” Diabetes/Metabolism Research and Reviews, 33(2), e2841–5 (2017). - PubMed