Skip to main content
construction release_alert
Scholars@Duke will be undergoing maintenance April 11-15. Some features may be unavailable during this time.
cancel

Deep learning segmentation of glomeruli on kidney donor frozen sections.

Publication ,  Journal Article
Li, X; Davis, RC; Xu, Y; Wang, Z; Souma, N; Sotolongo, G; Bell, J; Ellis, M; Howell, D; Shen, X; Lafata, KJ; Barisoni, L
Published in: J Med Imaging (Bellingham)
November 2021

Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution ( n = 123 ) and at external institutions ( n = 135 ) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic ( n = 22767 ) and sclerotic ( n = 1366 ) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F 1 , recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

J Med Imaging (Bellingham)

DOI

ISSN

2329-4302

Publication Date

November 2021

Volume

8

Issue

6

Start / End Page

067501

Location

United States

Related Subject Headings

  • 4003 Biomedical engineering
  • 3202 Clinical sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Li, X., Davis, R. C., Xu, Y., Wang, Z., Souma, N., Sotolongo, G., … Barisoni, L. (2021). Deep learning segmentation of glomeruli on kidney donor frozen sections. J Med Imaging (Bellingham), 8(6), 067501. https://doi.org/10.1117/1.JMI.8.6.067501
Li, Xiang, Richard C. Davis, Yuemei Xu, Zehan Wang, Nao Souma, Gina Sotolongo, Jonathan Bell, et al. “Deep learning segmentation of glomeruli on kidney donor frozen sections.J Med Imaging (Bellingham) 8, no. 6 (November 2021): 067501. https://doi.org/10.1117/1.JMI.8.6.067501.
Li X, Davis RC, Xu Y, Wang Z, Souma N, Sotolongo G, et al. Deep learning segmentation of glomeruli on kidney donor frozen sections. J Med Imaging (Bellingham). 2021 Nov;8(6):067501.
Li, Xiang, et al. “Deep learning segmentation of glomeruli on kidney donor frozen sections.J Med Imaging (Bellingham), vol. 8, no. 6, Nov. 2021, p. 067501. Pubmed, doi:10.1117/1.JMI.8.6.067501.
Li X, Davis RC, Xu Y, Wang Z, Souma N, Sotolongo G, Bell J, Ellis M, Howell D, Shen X, Lafata KJ, Barisoni L. Deep learning segmentation of glomeruli on kidney donor frozen sections. J Med Imaging (Bellingham). 2021 Nov;8(6):067501.

Published In

J Med Imaging (Bellingham)

DOI

ISSN

2329-4302

Publication Date

November 2021

Volume

8

Issue

6

Start / End Page

067501

Location

United States

Related Subject Headings

  • 4003 Biomedical engineering
  • 3202 Clinical sciences