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

Abstract

Background: Automated classification of glomerular pathological findings is potentially beneficial in establishing an efficient and objective diagnosis in renal pathology. While previous studies have verified the artificial intelligence (AI) models for the classification of global sclerosis and glomerular cell proliferation, there are several other glomerular pathological findings required for diagnosis, and the comprehensive models for the classification of these major findings have not yet been reported. Whether the cooperation between these AI models and clinicians improves diagnostic performance also remains unknown. Here, we developed AI models to classify glomerular images for major findings required for pathological diagnosis and investigated whether those models could improve the diagnostic performance of nephrologists. Methods: We used a dataset of 283 kidney biopsy cases comprising 15,888 glomerular images that were annotated by a total of 25 nephrologists. AI models to classify seven pathological findings: global sclerosis, segmental sclerosis, endocapillary proliferation, mesangial matrix accumulation, mesangial cell proliferation, crescent, and basement membrane structural changes, were constructed using deep learning by fine-tuning of InceptionV3 convolutional neural network. Subsequently, we compared the agreement to truth labels between majority decision among nephrologists with or without the AI model as a voter. Results: Our model for global sclerosis showed high performance (area under the curve: periodic acid-Schiff, 0.986; periodic acid methenamine silver, 0.983); the models for the other findings also showed performance close to those of nephrologists. By adding the AI model output to majority decision among nephrologists, out of the 14 constructed models, the results of the majority decision showed improvement in sensitivity for 10 models (four of them were statistically significant) and specificity for eight models (five significant). Conclusion: Our study showed a proof-of-concept for the classification of multiple glomerular findings in a comprehensive method of deep learning and suggested its potential effectiveness in improving diagnostic accuracy of clinicians.

Deep-Learning–Driven Quantification of Interstitial Fibrosis in Digitized Kidney Biopsies

“…Nevertheless, by identifying WSI regions using CAMs that are highly indicative of a class label, our approach provides a quantitative basis by which to interpret the model-based predictions rather than viewing DL methods as black-box approaches. As such, our approach stands in contrast to other methods that rely on expert-driven annotations and segmentation algorithms that attempt to quantify histological regions and derive information for pathologic assessment (12,(15)(16)(17)(18).…”

“…Specifically, DL techniques such as convolutional neural networks have been widely used for the analysis of histopathological images. In the context of kidney diseases, researchers have been able to produce highly accurate methods to evaluate disease grade, segment various kidney structures, as well as predict clinical phenotypes (10)(11)(12)(13)(14)(15)(16)(17)(18).…”

Identification of Gastritis Subtypes by Convolutional Neuronal Networks on Histological Images of Antrum and Corpus Biopsies

“…Various CNNs are available for the classification of images. Commonly used CNNs for histological and cytological images are VGG16 [ 16 , 26 , 27 ], InceptionV3 [ 28 , 29 ], and InceptionResNetV2 [ 30 ]. Some of these CNNs are rather large (VGG16, InceptionResNetV2) and achieve high accuracies with large training datasets.…”

Deep-learning-based membranous nephropathy classification and Monte-Carlo dropout uncertainty estimation

“…Particularly for MN classification, the already reported experimental results in the literature [Uchino et al, 2020, Chen et al, 2020 have generally relied on extremely limited and highly unbalanced data sets, which impinges the construction of effective generalized predictive models. Such constrained experimental settings avoid a rigorous validation of the models and reduce the extent and reliability of the findings.…”

“…Such constrained experimental settings avoid a rigorous validation of the models and reduce the extent and reliability of the findings. In terms of the underlying learning infrastructure, just a few deep networks have been assessed, notably the U-Net (for glomeruli segmentation [Chen et al, 2020]) and just a few mainstream convolutional and residual networks such as InceptionV3 [Uchino et al, 2020] and ResNet [Chen et al, 2020].…”