Deep learning could diagnose diabetic nephropathy with renal pathological immunofluorescent images

Shinji Kitamura, Kensaku Takahashi, Yizhen Sang, Kazuhiko Fukushima, Kenji Tsuji, Jun Wada

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)


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.

Original languageEnglish
Article number466
Issue number7
Publication statusPublished - Jul 2020


  • Artificial intelligence
  • Deep learning
  • Diabetic nephropathy
  • Immunofluorescent image
  • Renal pathology

ASJC Scopus subject areas

  • Clinical Biochemistry


Dive into the research topics of 'Deep learning could diagnose diabetic nephropathy with renal pathological immunofluorescent images'. Together they form a unique fingerprint.

Cite this