Deep learning-based multi-model approach on electron microscopy image of renal biopsy classification

Electron microscopy is important in the diagnosis of renal disease. For immune-mediated renal disease diagnosis, whether the electron-dense granule is present in the electron microscope image is of vital importance. Deep learning methods perform well at feature extraction and assessment of histologic images. However, few studies on deep learning methods for electron microscopy images of renal biopsy have been published. This study aimed to develop a deep learning-based multi-model to automatically detect whether the electron-dense granule is present in the TEM image of renal biopsy, and then help diagnose immune-mediated renal disease.

Three deep learning models are trained to classify whether the electron-dense granule is present using 910 electron microscopy images of renal biopsies. We proposed two novel methods to improve the model accuracy. One model uses the pre-trained ResNet convolutional layers for feature extraction with transfer learning which was firstly improved with skip architecture, then uses Support Vector Machine as the classifier. We developed a multi-model to combine the traditional ResNet model with the improved one to further improve the accuracy.

Deep learning-based multi-model has the highest model accuracy, and the average accuracy is about 88%. The improved ReseNet + SVM model performance is much better than the traditional ResNet model. The average accuracy of the improved ResNet + SVM model is 83%, while the traditional ResNet model accuracy is only 58%.

This study presents the first models for electron microscopy image classification of Renal Biopsy. Identifying whether the electron-dense granule is present plays an important role in the diagnosis of immune complex nephropathy. This study made it possible for Artificial Intelligence models assist to analyze complex electron microscopy images for disease diagnosis.