start-ver=1.4
cd-journal=joma
no-vol=10
cd-vols=
no-issue=7
article-no=
start-page=466
end-page=
dt-received=
dt-revised=
dt-accepted=
dt-pub-year=2020
dt-pub=20200709
dt-online=
en-article=
kn-article=
en-subject=
kn-subject=
en-title=
kn-title=Deep Learning Could Diagnose Diabetic Nephropathy with Renal Pathological Immunofluorescent Images
en-subtitle=
kn-subtitle=
en-abstract=
kn-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.
en-copyright=
kn-copyright=

en-aut-name=KitamuraShinji
en-aut-sei=Kitamura
en-aut-mei=Shinji
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=1
ORCID=

en-aut-name=TakahashiKensaku
en-aut-sei=Takahashi
en-aut-mei=Kensaku
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=2
ORCID=

en-aut-name=SangYizhen
en-aut-sei=Sang
en-aut-mei=Yizhen
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=3
ORCID=

en-aut-name=FukushimaKazuhiko
en-aut-sei=Fukushima
en-aut-mei=Kazuhiko
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=4
ORCID=

en-aut-name=TsujiKenji
en-aut-sei=Tsuji
en-aut-mei=Kenji
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=5
ORCID=

en-aut-name=WadaJun
en-aut-sei=Wada
en-aut-mei=Jun
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=6
ORCID=

affil-num=1
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=

affil-num=2
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=

affil-num=3
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=

affil-num=4
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=

affil-num=5
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=

affil-num=6
en-affil=Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences
kn-affil=
en-keyword=immunofluorescent image
kn-keyword=immunofluorescent image
en-keyword=renal pathology
kn-keyword=renal pathology
en-keyword=artificial intelligence
kn-keyword=artificial intelligence
en-keyword=deep learning
kn-keyword=deep learning
en-keyword=diabetic nephropathy
kn-keyword=diabetic nephropathy
END