Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases
Abstract Background Chronic kidney disease (CKD) causes progressive and irreversible damage to the kidneys. Renal biopsies are essential for diagnosing the etiology and prognosis of CKD, while accurate quantification of tubulo-interstitial injuries from whole slide images (WSIs) of renal biopsy spec...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Communications Medicine |
| Online Access: | https://doi.org/10.1038/s43856-024-00708-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559159447748608 |
|---|---|
| author | Nonoka Suzuki Kaname Kojima Silvia Malvica Kenshi Yamasaki Yoichiro Chikamatsu Yuji Oe Tasuku Nagasawa Ekyu Kondo Satoru Sanada Setsuya Aiba Hiroshi Sato Mariko Miyazaki Sadayoshi Ito Mitsuhiro Sato Tetsuhiro Tanaka Kengo Kinoshita Yoshihide Asano Avi Z. Rosenberg Koji Okamoto Kosuke Shido |
| author_facet | Nonoka Suzuki Kaname Kojima Silvia Malvica Kenshi Yamasaki Yoichiro Chikamatsu Yuji Oe Tasuku Nagasawa Ekyu Kondo Satoru Sanada Setsuya Aiba Hiroshi Sato Mariko Miyazaki Sadayoshi Ito Mitsuhiro Sato Tetsuhiro Tanaka Kengo Kinoshita Yoshihide Asano Avi Z. Rosenberg Koji Okamoto Kosuke Shido |
| author_sort | Nonoka Suzuki |
| collection | DOAJ |
| description | Abstract Background Chronic kidney disease (CKD) causes progressive and irreversible damage to the kidneys. Renal biopsies are essential for diagnosing the etiology and prognosis of CKD, while accurate quantification of tubulo-interstitial injuries from whole slide images (WSIs) of renal biopsy specimens is challenging with visual inspection alone. Methods We develop a deep learning-based method named DLRS to quantify interstitial fibrosis and inflammatory cell infiltration as tubulo-interstitial injury scores, from WSIs of renal biopsy specimens. DLRS segments WSIs into non-tissue areas, glomeruli, tubules, interstitium, and arteries, and detects interstitial nuclei. It then quantifies these tubulo-interstitial injury scores using the segmented tissues and detected nuclei. Results Applied to WSIs from 71 Japanese CKD patients with diabetic nephropathy or benign nephrosclerosis, DLRS-derived scores show concordance with nephrologists’ evaluations. Notably, the DLRS-derived fibrosis score has a higher correlation with the estimated glomerular filtration rate (eGFR) at biopsy than scores from nephrologists’ evaluations. Validated on WSIs from 28 Japanese tubulointerstitial nephritis patients and 49 European-ancestry patients with nephrosclerosis, DLRS-derived scores show a significant correlation with eGFR. In an expanded analysis of 238 Japanese CKD patients, including 167 from another hospital, deviations in eGFR from expected values based on DLRS-derived scores correlate with annual eGFR decline after biopsy. Inclusion of these deviations and DLRS-derived fibrosis scores improve predictions of the annual eGFR decline. Conclusions DLRS-derived tubulo-interstitial injury scores are concordant with nephrologists’ evaluations and correlated with eGFR across different populations and institutions. The effectiveness of DLRS-derived scores for predicting annual eGFR decline highlights the potential of DLRS as a predictor of renal prognosis. |
| format | Article |
| id | doaj-art-9d3841887be24f4d8d896846096c96ed |
| institution | Kabale University |
| issn | 2730-664X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Medicine |
| spelling | doaj-art-9d3841887be24f4d8d896846096c96ed2025-01-05T12:44:12ZengNature PortfolioCommunications Medicine2730-664X2025-01-015111510.1038/s43856-024-00708-3Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseasesNonoka Suzuki0Kaname Kojima1Silvia Malvica2Kenshi Yamasaki3Yoichiro Chikamatsu4Yuji Oe5Tasuku Nagasawa6Ekyu Kondo7Satoru Sanada8Setsuya Aiba9Hiroshi Sato10Mariko Miyazaki11Sadayoshi Ito12Mitsuhiro Sato13Tetsuhiro Tanaka14Kengo Kinoshita15Yoshihide Asano16Avi Z. Rosenberg17Koji Okamoto18Kosuke Shido19Division of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityTohoku Medical Megabank Organization, Tohoku UniversityJohns Hopkins University School of MedicineDepartment of Dermatology, Graduate School of Medicine, Tohoku UniversityDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityGraduate School of Information Sciences, Tohoku UniversityDepartment of Nephrology, Japan Community Health Care Organization Sendai HospitalDepartment of Dermatology, Graduate School of Medicine, Tohoku UniversityJR Sendai HospitalDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityDepartment of Nephrology, Japan Community Health Care Organization Sendai HospitalDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityTohoku Medical Megabank Organization, Tohoku UniversityDepartment of Dermatology, Graduate School of Medicine, Tohoku UniversityJohns Hopkins University School of MedicineDivision of Nephrology, Endocrinology and Vascular Medicine, Graduate School of Medicine, Tohoku UniversityDepartment of Dermatology, Graduate School of Medicine, Tohoku UniversityAbstract Background Chronic kidney disease (CKD) causes progressive and irreversible damage to the kidneys. Renal biopsies are essential for diagnosing the etiology and prognosis of CKD, while accurate quantification of tubulo-interstitial injuries from whole slide images (WSIs) of renal biopsy specimens is challenging with visual inspection alone. Methods We develop a deep learning-based method named DLRS to quantify interstitial fibrosis and inflammatory cell infiltration as tubulo-interstitial injury scores, from WSIs of renal biopsy specimens. DLRS segments WSIs into non-tissue areas, glomeruli, tubules, interstitium, and arteries, and detects interstitial nuclei. It then quantifies these tubulo-interstitial injury scores using the segmented tissues and detected nuclei. Results Applied to WSIs from 71 Japanese CKD patients with diabetic nephropathy or benign nephrosclerosis, DLRS-derived scores show concordance with nephrologists’ evaluations. Notably, the DLRS-derived fibrosis score has a higher correlation with the estimated glomerular filtration rate (eGFR) at biopsy than scores from nephrologists’ evaluations. Validated on WSIs from 28 Japanese tubulointerstitial nephritis patients and 49 European-ancestry patients with nephrosclerosis, DLRS-derived scores show a significant correlation with eGFR. In an expanded analysis of 238 Japanese CKD patients, including 167 from another hospital, deviations in eGFR from expected values based on DLRS-derived scores correlate with annual eGFR decline after biopsy. Inclusion of these deviations and DLRS-derived fibrosis scores improve predictions of the annual eGFR decline. Conclusions DLRS-derived tubulo-interstitial injury scores are concordant with nephrologists’ evaluations and correlated with eGFR across different populations and institutions. The effectiveness of DLRS-derived scores for predicting annual eGFR decline highlights the potential of DLRS as a predictor of renal prognosis.https://doi.org/10.1038/s43856-024-00708-3 |
| spellingShingle | Nonoka Suzuki Kaname Kojima Silvia Malvica Kenshi Yamasaki Yoichiro Chikamatsu Yuji Oe Tasuku Nagasawa Ekyu Kondo Satoru Sanada Setsuya Aiba Hiroshi Sato Mariko Miyazaki Sadayoshi Ito Mitsuhiro Sato Tetsuhiro Tanaka Kengo Kinoshita Yoshihide Asano Avi Z. Rosenberg Koji Okamoto Kosuke Shido Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases Communications Medicine |
| title | Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases |
| title_full | Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases |
| title_fullStr | Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases |
| title_full_unstemmed | Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases |
| title_short | Deep learning-based histopathological assessment of tubulo-interstitial injury in chronic kidney diseases |
| title_sort | deep learning based histopathological assessment of tubulo interstitial injury in chronic kidney diseases |
| url | https://doi.org/10.1038/s43856-024-00708-3 |
| work_keys_str_mv | AT nonokasuzuki deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT kanamekojima deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT silviamalvica deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT kenshiyamasaki deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT yoichirochikamatsu deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT yujioe deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT tasukunagasawa deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT ekyukondo deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT satorusanada deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT setsuyaaiba deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT hiroshisato deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT marikomiyazaki deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT sadayoshiito deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT mitsuhirosato deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT tetsuhirotanaka deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT kengokinoshita deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT yoshihideasano deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT avizrosenberg deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT kojiokamoto deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases AT kosukeshido deeplearningbasedhistopathologicalassessmentoftubulointerstitialinjuryinchronickidneydiseases |