In:
Journal of the American Society of Nephrology, Ovid Technologies (Wolters Kluwer Health), Vol. 30, No. 10 ( 2019-10), p. 1953-1967
Abstract:
Pathologists usually classify diabetic nephropathy on the basis of a visual assessment of glomerular pathology. Although diagnostic guidelines are well established, results may vary among pathologists. Modern machine learning has the potential to automate and augment accurate and precise classification of diabetic nephropathy. Digital algorithms may also be able to extract novel features relevant to disease progression and prognosis. The authors used image analysis and machine learning algorithms to digitally classify biopsy samples from 54 patients with diabetic nephropathy and found substantial agreement between digital classifications and those by three different pathologists. The study demonstrates that digital processing of renal tissue may provide useful information that may augment traditional clinical diagnostics. 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 κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ 1 = 0.68, 95% interval [0.50, 0.86] and κ 2 = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 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.
Type of Medium:
Online Resource
ISSN:
1046-6673
,
1533-3450
DOI:
10.1681/ASN.2018121259
Language:
English
Publisher:
Ovid Technologies (Wolters Kluwer Health)
Publication Date:
2019
detail.hit.zdb_id:
2029124-3
Permalink