Deep learning could diagnose diabetic nephropathy with renal pathological immunofluorescent images
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
These three methods performed better in PD diagnosis by correctly analyzing the absorption of 123 I-Ioflupane in the dopamine depletion region of SPECT of PD patients.
“These three methods performed better in PD diagnosis by correctly analyzing the absorption of 123 I-Ioflupane in the dopamine depletion region of single-photon emission computed tomography (SPECT) of PD patients.”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [114]
DeepLIFT and SHAP produced second best explanations by distinguishing between features of healthy and PD patients.
“DeepLIFT and SHAP produced second best explanations by distinguishing between features of healthy and PD patients.”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [114]
GBP produced best explanations among all other methods for Parkinson's disease detection.
“The GBP produced best explanations among all other methods.”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [114]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293 · see citing works
A clinically applicable approach to continuous prediction of future acute kidney injury
Tomašev, N., Glorot, X., Rae, J. W., Zielinski, M., Askham, H., Saraiva, A., Mottram, A., Meyer, C., Ravuri, S., Protsyuk, I., et al. (2019) · Nature · doi:10.1038/s41586-019-1390-1 · Cited by 1,086 · see citing works
Pesapane, F., Volonté, C., Codari, M., & Sardanelli, F. (2018) · Insights into Imaging · doi:10.1007/s13244-018-0645-y · Cited by 479 · see citing works
Machine learning: applications of artificial intelligence to imaging and diagnosis
Nichols, J., Chan, H. H., & Baker, M. A. B. (2018) · Biophysical Reviews · doi:10.1007/s12551-018-0449-9 · Cited by 458 · see citing works
Kuo, C., Chang, C.-M., Liu, K., Lin, W.-K., Chiang, H., Chung, C.-W., Ho, M.-R., Sun, P.-R., Yang, R.-L., & Chen, K.-T. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0104-2 · Cited by 227 · see citing works
Computational Segmentation and Classification of Diabetic Glomerulosclerosis
Ginley, B. G., Lutnick, B. R., Jen, K., Fogo, A. B., Jain, S. R., Rosenberg, A. Z., Walavalkar, V., Wilding, G. E., Tomaszewski, J. E., Yacoub, R., et al. (2019) · Journal of the American Society of Nephrology · doi:10.1681/asn.2018121259 · Cited by 205 · see citing works
Artificial Intelligence in Drug Discovery
Sellwood, M. A., Ahmed, M., Segler, M., & Brown, N. (2018) · Future Medicinal Chemistry · doi:10.4155/fmc-2018-0212 · Cited by 174 · see citing works
Application of artificial intelligence in ophthalmology
Du, X., Li, W., & Hu, B. (2018) · International Journal of Ophthalmology · doi:10.18240/ijo.2018.09.21 · Cited by 100 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Explainable, trustworthy, and ethical machine learning for healthcare: A survey
Rasheed, K., Qayyum, A., Ghaly, M., Al-Fuqaha, A., Razi, A., & Qadir, J. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106043 · Cited by 372 · see citing works
- Authors
- Kitamura, S., Takahashi, K., Sang, Y., Fukushima, K., Tsuji, K., & Wada, J.
- Affiliations
- Okayama University (JP)
- Corresponding author
- Kitamura, Shinji
- Venue
- Diagnostics
- Publisher
- MDPI AG
- Published
- 2020-07-09
- Volume
- 10
- Issue
- 7
- Pages
- 466
- ISSN
- 2075-4418 (ISSN-L)
- PMC
- PMC7400564
- OpenAlex
- W3040848521
- Cited by
- 35
- References
- 8
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 7 · 2023: 4 · 2022: 9 · 2021: 7
- FWCI
- 1.97
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Diagnostics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Institutional Repositories DataBase (IRDB) (submittedVersion, cc-by)
- Okayama University Scientific Achievement Repository (Okayama University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Yukiko Ishibashi Memorial foundation (No number)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- diabetic nephropathy, renal biopsy, deep learning diagnosis, glomerular lesions, IgG, IgA, IgM, complement C3, C1q, fibrinogen, local interpretable model-agnostic explanations
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
