Computational segmentation and classification of diabetic glomerulosclerosis

Brandon Ginley, Brendon Lutnick, Kuang Yu Jen, Agnes B. Fogo, Sanjay Jain, Avi Rosenberg, Vighnesh Walavalkar, Gregory Wilding, John E. Tomaszewski, Rabi Yacoub, Giovanni Maria Rossi, Pinaki Sarder

Research output: Contribution to journalArticlepeer-review

134 Scopus citations


Background Pathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation. Methods We developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures.We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification. Results Our digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen's kappa k = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with k150.68, 95% interval [0.50, 0.86] and k2=0.48, 95%interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classificationmethods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.9360.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity. Conclusions Computationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.

Original languageEnglish
Pages (from-to)1953-1967
Number of pages15
JournalJournal of the American Society of Nephrology
Issue number10
StatePublished - 2019


Dive into the research topics of 'Computational segmentation and classification of diabetic glomerulosclerosis'. Together they form a unique fingerprint.

Cite this