Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning
Abstract To decrease the number of chronic kidney disease (CKD), early diagnosis of diabetic kidney disease is required. We performed invariant information clustering (IIC)-based clustering on glomerular images obtained from nephrectomized kidneys of patients with and without diabetes. We also used...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84588-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594752591101952 |
|---|---|
| author | Tomohisa Yabe Yuko Tsuruyama Kazutoshi Nomura Ai Fujii Yuto Matsuda Keiichiro Okada Shogo Yamakoshi Yuya Hamabe Shogo Omote Akihiro Shioya Norifumi Hayashi Keiji Fujimoto Yuki Todo Tatsuro Tanaka Sohsuke Yamada Akira Shimizu Katsuhito Miyazawa Hitoshi Yokoyama Kengo Furuichi |
| author_facet | Tomohisa Yabe Yuko Tsuruyama Kazutoshi Nomura Ai Fujii Yuto Matsuda Keiichiro Okada Shogo Yamakoshi Yuya Hamabe Shogo Omote Akihiro Shioya Norifumi Hayashi Keiji Fujimoto Yuki Todo Tatsuro Tanaka Sohsuke Yamada Akira Shimizu Katsuhito Miyazawa Hitoshi Yokoyama Kengo Furuichi |
| author_sort | Tomohisa Yabe |
| collection | DOAJ |
| description | Abstract To decrease the number of chronic kidney disease (CKD), early diagnosis of diabetic kidney disease is required. We performed invariant information clustering (IIC)-based clustering on glomerular images obtained from nephrectomized kidneys of patients with and without diabetes. We also used visualizing techniques (gradient-weighted class activation mapping (Grad-CAM) and generative adversarial networks (GAN)) to identify the novel and early pathological changes on light microscopy in diabetic nephropathy. Overall, 13,251 glomerular images (7,799 images from diabetes cases and 5,542 images from non-diabetes cases) obtained from 45 patients in Kanazawa Medical University were clustered into 10 clusters by IIC. Diabetic clusters that mainly contained glomerular images from diabetes cases (Clusters 0, 1, and 2) and non-diabetic clusters that mainly contained glomerular images from non-diabetes cases (Clusters 8 and 9) were distinguished in the t-distributed stochastic neighbor embedding (t-SNE) analysis. Grad-CAM demonstrated that the outer portions of glomerular capillaries in diabetic clusters had characteristic lesions. Cycle-GAN showed that compared to Bowman’s space, smaller glomerular tufts was a characteristic lesion of diabetic clusters. These findings might be the subtle and novel pathological changes on light microscopy in diabetic nephropathy. |
| format | Article |
| id | doaj-art-3bac3bab3cad4e0fafe85efe44394d87 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3bac3bab3cad4e0fafe85efe44394d872025-01-19T12:21:54ZengNature PortfolioScientific Reports2045-23222025-01-0115111010.1038/s41598-024-84588-6Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learningTomohisa Yabe0Yuko Tsuruyama1Kazutoshi Nomura2Ai Fujii3Yuto Matsuda4Keiichiro Okada5Shogo Yamakoshi6Yuya Hamabe7Shogo Omote8Akihiro Shioya9Norifumi Hayashi10Keiji Fujimoto11Yuki Todo12Tatsuro Tanaka13Sohsuke Yamada14Akira Shimizu15Katsuhito Miyazawa16Hitoshi Yokoyama17Kengo Furuichi18Department of Nephrology, Kanazawa Medical UniversityDepartment of Internal medicine, Futatsuya HospitalDepartment of Nephrology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityDivision of Electrical, Information and Communication Engineering, Kanazawa UniversityDivision of Electrical, Information and Communication Engineering, Kanazawa UniversityDivision of Electrical, Information and Communication Engineering, Kanazawa UniversityDepartment of Pathology and Laboratory Medicine, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityFaculty of Electrical, Information and Communication Engineering, Kanazawa UniversityDepartment of Urology, Kanazawa Medical UniversityDepartment of Pathology and Laboratory Medicine, Kanazawa Medical UniversityDepartment of Analytic human pathology, Nippon Medical SchoolDepartment of Urology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityDepartment of Nephrology, Kanazawa Medical UniversityAbstract To decrease the number of chronic kidney disease (CKD), early diagnosis of diabetic kidney disease is required. We performed invariant information clustering (IIC)-based clustering on glomerular images obtained from nephrectomized kidneys of patients with and without diabetes. We also used visualizing techniques (gradient-weighted class activation mapping (Grad-CAM) and generative adversarial networks (GAN)) to identify the novel and early pathological changes on light microscopy in diabetic nephropathy. Overall, 13,251 glomerular images (7,799 images from diabetes cases and 5,542 images from non-diabetes cases) obtained from 45 patients in Kanazawa Medical University were clustered into 10 clusters by IIC. Diabetic clusters that mainly contained glomerular images from diabetes cases (Clusters 0, 1, and 2) and non-diabetic clusters that mainly contained glomerular images from non-diabetes cases (Clusters 8 and 9) were distinguished in the t-distributed stochastic neighbor embedding (t-SNE) analysis. Grad-CAM demonstrated that the outer portions of glomerular capillaries in diabetic clusters had characteristic lesions. Cycle-GAN showed that compared to Bowman’s space, smaller glomerular tufts was a characteristic lesion of diabetic clusters. These findings might be the subtle and novel pathological changes on light microscopy in diabetic nephropathy.https://doi.org/10.1038/s41598-024-84588-6Diabetic nephropathyNovel pathological changesLight microscopyDeep learningInvariant information clustering (IIC) |
| spellingShingle | Tomohisa Yabe Yuko Tsuruyama Kazutoshi Nomura Ai Fujii Yuto Matsuda Keiichiro Okada Shogo Yamakoshi Yuya Hamabe Shogo Omote Akihiro Shioya Norifumi Hayashi Keiji Fujimoto Yuki Todo Tatsuro Tanaka Sohsuke Yamada Akira Shimizu Katsuhito Miyazawa Hitoshi Yokoyama Kengo Furuichi Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning Scientific Reports Diabetic nephropathy Novel pathological changes Light microscopy Deep learning Invariant information clustering (IIC) |
| title | Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| title_full | Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| title_fullStr | Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| title_full_unstemmed | Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| title_short | Exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| title_sort | exploring the subtle and novel renal pathological changes in diabetic nephropathy using clustering analysis with deep learning |
| topic | Diabetic nephropathy Novel pathological changes Light microscopy Deep learning Invariant information clustering (IIC) |
| url | https://doi.org/10.1038/s41598-024-84588-6 |
| work_keys_str_mv | AT tomohisayabe exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT yukotsuruyama exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT kazutoshinomura exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT aifujii exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT yutomatsuda exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT keiichirookada exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT shogoyamakoshi exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT yuyahamabe exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT shogoomote exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT akihiroshioya exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT norifumihayashi exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT keijifujimoto exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT yukitodo exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT tatsurotanaka exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT sohsukeyamada exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT akirashimizu exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT katsuhitomiyazawa exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT hitoshiyokoyama exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning AT kengofuruichi exploringthesubtleandnovelrenalpathologicalchangesindiabeticnephropathyusingclusteringanalysiswithdeeplearning |