CluSA: Clustering-based Spatial Analysis framework through Graph Neural Network for Chronic Kidney Disease Prediction using Histopathology Images

Abstract

Machine learning applied to digital pathology has been increasingly used to assess kidney function and diagnose the underlying cause of chronic kidney disease (CKD). We developed a novel computational framework, Clustering-based Spatial Analysis (CluSA), that leverages unsupervised learning to learn spatial relationships between local visual patterns in kidney tissue. This framework minimizes the need for time-consuming and impractical expert annotations. To incorporate spatial information over the clustered image patterns on the biopsy sample, we spatially encoded clustered patterns with colors and performed spatial analysis through graph neural network. A random forest classifier with various groups of features were used to predict CKD. For predicting high/low eGFR at the biopsy, we achieved a sensitivity of 0.97, specificity of 0.90, and accuracy of 0.95. AUC was 0.96. For predicting eGFR changes in one-year, we achieved a sensitivity of 0.83, specificity of 0.85, and accuracy of 0.84. AUC was 0.85. This study presents the first spatial analysis based on unsupervised machine learning algorithms. Without expert annotation, CluSA framework can not only accurately classify and predict the degree of kidney function at the biopsy and in one year, but also identify novel predictors of kidney function and renal prognosis.

A Systematic Review of Graph Neural Network in Healthcare-Based Applications: Recent Advances, Trends, and Future Directions

“…Despite facing computational challenges and limitations in handling dynamic graphs, Spectral-GNN contributes to insightful structural analysis. A notable trend emerges with the widespread utilization of spatial convolutional networks (S-GNN) [59], [60], [63], [69], [72], [74], [75], [78], [101], [102], [123][124][125][126][127][128], underscoring their prominence and effectiveness in various medical graph applications, showcasing their adaptability to diverse healthcare research scenarios.…”

“…In clinically interpretable pathway-level biomarkers discovery [62], MLA-GNN leverages graph classification for state-of-the-art performance in survival prediction, histological grading, and Covid-19 diagnosis. Chronic kidney disease prediction [63] involves graph classification using DeepLab V3+ and DGCNN, achieving high sensitivity and specificity for predicting eGFR levels. The prediction of Covid-19 cases [64] utilizes various graph-based models, including GNN, demonstrating their effectiveness in forecasting.…”

Deep learning applications for kidney histology analysis

“…Unsupervised learning methods aim at learning patterns, relationships, and structures from unlabeled data. Notable examples are clustering [5 ▪ ], dimensionality reduction methods [6 ▪▪ ], and anomaly detection [7].…”