Rapid diagnosis of membranous nephropathy based on kidney tissue Raman spectroscopy and deep learning

被引：0

作者：

Guoqiang Zhu ^{[1
]}

Halinuer Shadekejiang ^{[1
]}

Xueqin Zhang ^{[2
]}

Cheng Chen ^{[3
]}

Mingjie Su ^{[1
]}

Shuo Wu ^{[1
]}

Gulizere Aimaijiang ^{[4
]}

Li Zhang ^{[1
]}

Shun Wang ^{[1
]}

Wenjun Yang ^{[1
]}

Chen Lu ^{[1
]}

机构：

[1] The First Affiliated Hospital of Xinjiang Medical University, Urumqi

[2] People’s Hospital of Xinjiang Uygur Autonomous Region, Urumqi

[3] College of Software, Xinjiang University, Urumqi

[4] Shihezi University, Shihezi

来源：

Scientific Reports | / 15卷 / 1期

关键词：

Deep learning; Early diagnosis; Membranous nephropathy; Raman spectroscopy;

D O I：

10.1038/s41598-025-97351-2

中图分类号：

学科分类号：

摘要：

Membranous nephropathy (MN) is one of the most common glomerular diseases. Although the diagnostic method based on serum PLA2R antibodies has gradually been applied in clinical practice, only 52–86% of PLA2R-associated MN patients show positive anti-PLA2R antibodies. Therefore, renal biopsy remains the gold standard for diagnosing MN. However, the renal biopsy procedure is highly complex and involves multiple steps, including tissue sampling, fixation, dehydration, embedding, sectioning, PAS staining, Masson trichrome staining, and silver staining. Each step requires precise technique from laboratory personnel, as any error can affect the quality of the final tissue sections and, consequently, the diagnosis. As a result, there is an urgent need to develop a method that enables rapid diagnosis after renal biopsy. Previous studies have shown that Raman spectroscopy offers promising results for diagnosing MN, exhibiting high sensitivity and specificity when applied to human serum and urine samples. In this study, we propose a rapid diagnostic method combining Raman spectroscopy of mouse kidney tissue with a CNN-BiLSTM deep learning model. The model achieved 98% accuracy, with specificity and sensitivity of 98.3%, providing a novel auxiliary tool for the pathological diagnosis of MN. © The Author(s) 2025.

引用

共 28 条

[1] Duan Y., Et al., Analysis of pathological data and epidemiological characteristics of 10 684 cases of renal biopsy in Xinjiang Uygur autonomous region, Chin. J. Nephrol, 37, pp. 490-498, (2021)
[2] Cravedi P., Et al., Immune-monitoring disease activity in primary membranous nephropathy, Front. Med, 6, (2019)
[3] Couser W.G., Primary membranous nephropathy, Clin. J. Am. Soc. Nephrol. CJASN, 12, pp. 983-997, (2017)
[4] Feng Z., Et al., How does herbal medicine treat idiopathic membranous nephropathy?, Front. Pharmacol, 11, (2020)
[5] Zhang X., Et al., Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods, Sci. Rep, 13, (2023)
[6] Devitt G., Howard K., Mudher A., Mahajan S., Raman spectroscopy: an emerging tool in neurodegenerative disease research and diagnosis, ACS Chem. Neurosci, 9, pp. 404-420, (2018)
[7] Bakator M., Radosav D., Deep learning and medical diagnosis: a review of literature, Multimodal Technol. Interact, 2, (2018)
[8] Wu H.H., Chen C.J., Lin P.Y., Liu Y.H., Involvement of prohibitin 1 and prohibitin 2 upregulation in cBSA-induced podocyte cytotoxicity, J. Food Drug Anal, 28, pp. 183-194, (2020)
[9] Chen J.S., Et al., Mouse model of membranous nephropathy induced by cationic bovine serum albumin: antigen dose-response relations and strain differences, Nephrol. Dial Transpl. Off Publ Eur. Dial Transpl. Assoc. Eur. Ren. Assoc, 19, pp. 2721-2728, (2004)
[10] Yvon H.J., Raman spectroscopy for analysis and monitoring, Horiba Jobin Yvon Raman Appl. Note, 1, 2, (2017)

← 1 2 3 →