Deep Learning Could Diagnose Diabetic Nephropathy with Renal Pathological Immunofluorescent Images
Deep Learning Could Diagnose Diabetic Nephropathy with Renal Pathological Immunofluorescent Images
复制标题
DOI：
10.3390/diagnostics10070466
复制
发表时间：
2020-07-01
期刊：
影响因子：
3.6
通讯作者：
Wada, Jun
中科院分区：
文献类型：
--
作者：
Kitamura, Shinji;Takahashi, Kensaku;Wada, Jun
人工智能（AI）影像诊断正在发展，使医疗领域向前迈出了巨大的步伐。对于糖尿病肾病（DN），医生根据临床病程、临床实验室数据和肾脏病理来诊断，主要通过光学显微镜图像而不是免疫荧光图像来评估，因为免疫荧光图像对DN诊断没有特征性发现。在这里，我们研究了AI是否可以从免疫荧光图像诊断DN的可能性。我们收集了我院885例肾活检患者的肾脏免疫荧光图像，并创建了一个数据集，其中包含每个患者的IgG，伊加，IgM，C3，C1q和纤维蛋白原的六种免疫荧光图像。使用该数据集，39个程序无错误地工作（曲线下面积（AUC）：0.93）。5个程序免疫荧光图像完全诊断DN（AUC：1.00）。通过局部可解释模型不可知解释（Lime）分析，AI集中在DN肾小球的外周病变。另一方面，肾脏科医生诊断率（AUC：0.75833）略劣于AI诊断。这些发现表明，DN只能通过深度学习的免疫荧光图像来诊断。AI可以诊断DN，并通过免疫荧光图像识别肾脏科医生通常不用于DN诊断的分类未知部分。
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.