Regular article
Machine learning, computational pathology, and biophysical imaging
Deep-Learning–Driven Quantification of Interstitial Fibrosis in Digitized Kidney Biopsies

https://doi.org/10.1016/j.ajpath.2021.05.005Get rights and content
Under an Elsevier user license
open archive

Interstitial fibrosis and tubular atrophy (IFTA) on a renal biopsy are strong indicators of disease chronicity and prognosis. Techniques that are typically used for IFTA grading remain manual, leading to variability among pathologists. Accurate IFTA estimation using computational techniques can reduce this variability and provide quantitative assessment. Using trichrome-stained whole-slide images (WSIs) processed from human renal biopsies, we developed a deep-learning framework that captured finer pathologic structures at high resolution and overall context at the WSI level to predict IFTA grade. WSIs (n = 67) were obtained from The Ohio State University Wexner Medical Center. Five nephropathologists independently reviewed them and provided fibrosis scores that were converted to IFTA grades: ≤10% (none or minimal), 11% to 25% (mild), 26% to 50% (moderate), and >50% (severe). The model was developed by associating the WSIs with the IFTA grade determined by majority voting (reference estimate). Model performance was evaluated on WSIs (n = 28) obtained from the Kidney Precision Medicine Project. There was good agreement on the IFTA grading between the pathologists and the reference estimate (κ = 0.622 ± 0.071). The accuracy of the deep-learning model was 71.8% ± 5.3% on The Ohio State University Wexner Medical Center and 65.0% ± 4.2% on Kidney Precision Medicine Project data sets. Our approach to analyzing microscopic- and WSI-level changes in renal biopsies attempts to mimic the pathologist and provides a regional and contextual estimation of IFTA. Such methods can assist clinicopathologic diagnosis.

Cited by (0)

Supported by the Karen Toffler Charitable Trust grant (V.B.K.), the National Center for Advancing Translational Sciences grant (V.B.K.), the NIH, through Boston University Clinical & Translational Science Institute (BU-CTSI) grant 1UL1TR001430 (V.B.K.), a Scientist Development grant 17SDG33670323 (V.B.K.), an American Heart Association Strategically Focused Research Network Center grant 20SFRN35460031 (V.B.K.), a Hariri Research Award from the Hariri Institute for Computing and Computational Science and Engineering at Boston University (V.B.K.), and NIH grants R01-AG062109 and R21-CA253498 (V.B.K.); NIH grants R21-DK119740 and R01-HL132325 (V.C.C.); the German Research Foundation (DFG) SFB/TRR57 P25&P33, SFB/TRR219 Project-ID 322900939, BO3755/13-1 Project-ID 454024652 (P.B.), the German Federal Ministries of Education and Research STOP-FSGS-01GM1901A (P.B.), and Health (DEEP LIVER, ZMVI1-2520DAT111) and Economic Affairs and Energy (EMPAIA) (P.B.), the European Research Council (ERC) AIM.imaging.CKD No. 101001791 (P.B.); NIH grants R21-DK119751 and U01-DK085660 (S.S.W.); and National Science Foundation grants 1838193 and 1551572 (M.B.).

Disclosures: None declared.

The content of this article is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.