Deep Learning Could Diagnose Diabetic Nephropathy with Renal Pathological Immunofluorescent Images
Open Access
- 9 July 2020
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 10 (7) , 466
Abstract
Artificial Intelligence (AI) imaging diagnosis is developing, making enormous steps forward in medical fields. Regarding diabetic nephropathy (DN), medical doctors diagnose them with clinical course, clinical laboratory data and renal pathology, mainly evaluate with light microscopy images rather than immunofluorescent images because there are no characteristic findings in immunofluorescent images for DN diagnosis. Here, we examined the possibility of whether AI could diagnose DN from immunofluorescent images. We collected renal immunofluorescent images from 885 renal biopsy patients in our hospital, and we created a dataset that contains six types of immunofluorescent images of IgG, IgA, IgM, C3, C1q and Fibrinogen for each patient. Using the dataset, 39 programs worked without errors (Area under the curve (AUC): 0.93). Five programs diagnosed DN completely with immunofluorescent images (AUC: 1.00). By analyzing with Local interpretable model-agnostic explanations (Lime), the AI focused on the peripheral lesion of DN glomeruli. On the other hand, the nephrologist diagnostic ratio (AUC: 0.75833) was slightly inferior to AI diagnosis. These findings suggest that DN could be diagnosed only by immunofluorescent images by deep learning. AI could diagnose DN and identify classified unknown parts with the immunofluorescent images that nephrologists usually do not use for DN diagnosis.Keywords
Funding Information
- Yukiko Ishibashi Foundation (No number)
This publication has 8 references indexed in Scilit:
- Computational Segmentation and Classification of Diabetic GlomerulosclerosisJournal of the American Society of Nephrology, 2019
- A clinically applicable approach to continuous prediction of future acute kidney injuryNature, 2019
- Automation of the kidney function prediction and classification through ultrasound-based kidney imaging using deep learningnpj Digital Medicine, 2019
- Application of artificial intelligence in ophthalmologyInternational Journal of Ophthalmology, 2018
- Machine learning: applications of artificial intelligence to imaging and diagnosisBiophysical Reviews, 2018
- Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United StatesInsights into Imaging, 2018
- Artificial Intelligence in Drug DiscoveryFuture Medicinal Chemistry, 2018
- Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast CancerJAMA, 2017