Automatic glomerular identification and quantification of histological phenotypes using image analysis and machine learning

Abstract

Current methods of scoring histological kidney samples, specifically glomeruli, do not allow for collection of quantitative data in a high-throughput and consistent manner. Neither untrained individuals nor computers are presently capable of identifying glomerular features, so expert pathologists must do the identification and score using a categorical matrix, complicating statistical analysis. Critical information regarding overall health and physiology is encoded in these samples. Rapid comprehensive histological scoring could be used, in combination with other physiological measures, to significantly advance renal research. Therefore, we used machine learning to develop a high-throughput method to automatically identify and collect quantitative data from glomeruli. Our method requires minimal human interaction between steps and provides quantifiable data independent of user bias. The method uses free existing software and is usable without extensive image analysis training. Validation of the classifier and feature scores in mice is highlighted in this work and shows the power of applying this method in murine research. Preliminary results indicate that the method can be applied to data sets from different species after training on relevant data, allowing for fast glomerular identification and quantitative measurements of glomerular features. Validation of the classifier and feature scores are highlighted in this work and show the power of applying this method. The resulting data are free from user bias. Continuous data, such that statistical analysis can be performed, allows for more precise and comprehensive interrogation of samples. These data can then be combined with other physiological data to broaden our overall understanding of renal function.

Classification of glomerular pathological findings using deep learning and nephrologist–AI collective intelligence approach

“…While some studies have validated DL models analyzing the structures other than the glomeruli, such as the tubules, blood vessels, and interstitium [7][8][9][10], many studies have focused on the glomeruli, which present various histological findings essential for diagnosis. As a first step in the automation of this diagnostic procedure, detection of a glomerulus in a whole slide image (WSI) of renal tissue specimens has been recently attempted in many studies with the use of methods to define various features [11][12][13][14][15][16][17][18][19][20][21][22][23][24] or using convolutional neural networks (CNNs) [25], such as InceptionV3 [26], AlexNet [27], U-Net [28], R-CNN [29,30], or DeepLab V2 ResNet [31].…”

Detection and Classification of Novel Renal Histologic Phenotypes Using Deep Neural Networks

“…The Far2 KO animals are known to have less MME at 12 months of age compared with wild-type controls, 9 but the traditional scoring system for MME is a subjective ordinal scale. 12 In contrast, the SVM model developed using DNN signatures transformed the categorical distinction between genotypes (WT and KO) into a quantitative glomerular score that strongly correlated with standard MME scores when tested on HET glomeruli. Intuitively, this model asserts that the more similar a HET glomerulus is to a KO glomerulus, the more likely it is to have little MME, and vice versa.…”

“…Mesangial matrix expansion was assessed in the glomeruli, as previously described. 12 Briefly, renal pathologists evaluated 50 glomeruli per animal to score the mesangial matrix [0 indicates no MME; 1, increase in extracellular material (mesangial matrix) and/or cellularity (mesangioproliferation) such that the width of the intercapillary space exceeds two mesangial cell nuclei but does not exceed the mean area of the glomerular capillary lumen; 2, the expanded mesangial area exceeds the mean area of a capillary lumen and Glomeruli are typically larger than the 227 Â 227-pixel squared input for AlexNet. To obtain features for classifying glomeruli by genotype, feature vectors obtained by taking nine image patches sampled in a grid around the center-of-mass pixel (center red dot) of the glomerulus were averaged.…”

Segmentação de Núcleos em Imagens Histológicas Renais

“…No trabalho de Sheehan e Korstanje [Sheehan and Korstanje 2018], um método semi-automático foi desenvolvido para identificar e coletar informações quantitativas do glomérulo. Os autores usaram realce de contraste e borramento gaussiano, seguido por um filtro para identificar regiões de interesse que correspondem ao glomérulo.…”

“…Os testes foram realizados utilizando duas bases de dados, sendo elas: 1) A base do The Jackson Laboratory (TJK) [Sheehan 2018…”