IDENTIFICATION OF THE SUBTLE, NOVEL, AND EARLY RENAL PATHOLOGICAL CHANGES IN DIABETIC NEPHROPHATHY USING CLUSTERING WITH DEEP LEARNING

Certificate Output Instructions

For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".

To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".

Presented the abstract " "
(Abstract co-author(s): )

Back

E-Poster Presentation

During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.

Preparing your E-Poster

Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.

E-Poster Submission Deadline

Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.

E-Poster Format Requirements

PDF file
Layout: Portrait (vertical orientation)
One page only (Dim A4: 210 x 297mm or PPT)
E-Poster can be prepared in PowerPoint (one (1) PowerPoint slide) but must be saved and submitted as PDF file.
File Size: Maximum file size is 2 Megabytes (2 MB)
No hyperlinks, animated images, animations, and slide transitions
Language: English
Include your abstract number
E-posters can include QR codes, tables and photos

E-Poster

https://storage.unitedwebnetwork.com/files/1099/a25514b2773db8554006951c5c462523.pdf

Abstract Title *

IDENTIFICATION OF THE SUBTLE, NOVEL, AND EARLY RENAL PATHOLOGICAL CHANGES IN DIABETIC NEPHROPHATHY USING CLUSTERING WITH DEEP LEARNING

Please follow the instructions below to input your abstract title.

Abstract titles should be brief and reflect the content of the abstract.

The title will not be accepted if it exceeds 25 words.
Type in CAPITAL LETTERS.
Lowercase may be used for abbreviations only, for example, mRNA.

Co-author 1

Tomohisa Yabe t-yabe@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan *

Co-author 2

Sho Kumano kumano@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 3

Keiichiro Okada k-okada@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 4

Kazuaki Okino taro1985@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 5

Norifumi Hayashi nori924@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 6

Keiji Fujimoto k-2210@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 7

Hitoshi Yokoyama h-yoko@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 8

Kengo Furuichi furuichi@kanazawa-med.ac.jp Kanazawa Medical University Nephrology Uchinada Japan -

Co-author 9

Co-author 10

Co-author 11

Co-author 12

Co-author 13

Co-author 14

Co-author 15

Introduction

Early diagnosis of diabetic kidney disease (DKD) is essential for reducing the prevalence of chronic kidney disease (CKD). However, the pathological alterations that occur during the early stages of diabetic nephropathy remain incompletely characterized.

Methods

Nephrectomy specimens (partial or total) obtained at Kanazawa Medical University between 1998 and 2019 were analyzed. Glomerular images were extracted from both HE- and PAS-stained kidney sections from patients with and without diabetes. The invariant information clustering (IIC) algorithm was applied to perform unsupervised classification of morphological features in glomerular images. Visualization methods, including gradient-weighted class activation mapping (Grad-CAM) and generative adversarial networks (GAN), were employed to detect and illustrate subtle, previously unrecognized pathological changes under light microscopy.

Results

A total of 19,243 glomerular images (11,996 from diabetic cases and 7,247 from non-diabetic cases) obtained from 45 patients were classified into 10 clusters using IIC. The t-distributed stochastic neighbor embedding (t-SNE) analysis demonstrated distinct diabetic clusters (Clusters 0 and 1) predominantly composed of glomeruli from diabetic patients, and a non-diabetic cluster (Cluster 9) largely consisting of glomeruli from non-diabetic patients. Grad-CAM visualization indicated that the outer portions of glomerular capillary tufts within diabetic clusters exhibited characteristic lesions, consistently observed in both HE- and PAS-stained images.

Conclusion

Unsupervised deep learning identified the subtle and previously unrecognized morphological features in diabetic glomeruli that may represent early pathological changes of diabetic nephropathy. These findings provide new histopathological insights that could facilitate earlier diagnosis and contribute to the prevention of CKD progression in diabetic individuals.

Kewords