Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods
Abstract Membranous nephropathy is the main cause of nephrotic syndrome, which has an insidious onset and may progress to end-stage renal disease with a high mortality rate, such as renal failure and uremia. At present, the diagnosis of membranous nephropathy mainly relies on the clinical manifestat...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-02-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-22204-1 |
_version_ | 1797864885742206976 |
---|---|
author | Xueqin Zhang Xue Song Wenjing Li Cheng Chen Miriban Wusiman Li Zhang Jiahui Zhang Jinyu Lu Chen Lu Xiaoyi Lv |
author_facet | Xueqin Zhang Xue Song Wenjing Li Cheng Chen Miriban Wusiman Li Zhang Jiahui Zhang Jinyu Lu Chen Lu Xiaoyi Lv |
author_sort | Xueqin Zhang |
collection | DOAJ |
description | Abstract Membranous nephropathy is the main cause of nephrotic syndrome, which has an insidious onset and may progress to end-stage renal disease with a high mortality rate, such as renal failure and uremia. At present, the diagnosis of membranous nephropathy mainly relies on the clinical manifestations of patients and pathological examination of kidney biopsy, which are expensive, time-consuming, and have certain chance and other disadvantages. Therefore, there is an urgent need to find a rapid, accurate and non-invasive diagnostic technique for the diagnosis of membranous nephropathy. In this study, Raman spectra of serum and urine were combined with deep learning methods to diagnose membranous nephropathy. After baseline correction and smoothing of the data, Gaussian white noise of different decibels was added to the training set for data amplification, and the amplified data were imported into ResNet, AlexNet and GoogleNet models to obtain the evaluation results of the models for membranous nephropathy. The experimental results showed that the three deep learning models achieved an accuracy of 1 for the classification of serum data of patients with membranous nephropathy and control group, and the discrimination of urine data was above 0.85, among which AlexNet was the best classification model for both samples. The above experimental results illustrate the great potential of serum- and urine-based Raman spectroscopy combined with deep learning methods for rapid and accurate identification of patients with membranous nephropathy. |
first_indexed | 2024-04-09T22:59:08Z |
format | Article |
id | doaj.art-1e33e4be8f49429298ccb4d96d551395 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-09T22:59:08Z |
publishDate | 2023-02-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-1e33e4be8f49429298ccb4d96d5513952023-03-22T11:02:49ZengNature PortfolioScientific Reports2045-23222023-02-0113111010.1038/s41598-022-22204-1Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methodsXueqin Zhang0Xue Song1Wenjing Li2Cheng Chen3Miriban Wusiman4Li Zhang5Jiahui Zhang6Jinyu Lu7Chen Lu8Xiaoyi Lv9People’s Hospital of Xinjiang Uygur Autonomous RegionPeople’s Hospital of Xinjiang Uygur Autonomous RegionCollege of Software, Xinjiang UniversityCollege of Software, Xinjiang UniversityXinjiang Medical UniversityThe First Affiliated Hospital of Xinjiang Medical UniversityXinjiang Medical UniversityPeople’s Hospital of Xinjiang Uygur Autonomous RegionThe First Affiliated Hospital of Xinjiang Medical UniversityCollege of Software, Xinjiang UniversityAbstract Membranous nephropathy is the main cause of nephrotic syndrome, which has an insidious onset and may progress to end-stage renal disease with a high mortality rate, such as renal failure and uremia. At present, the diagnosis of membranous nephropathy mainly relies on the clinical manifestations of patients and pathological examination of kidney biopsy, which are expensive, time-consuming, and have certain chance and other disadvantages. Therefore, there is an urgent need to find a rapid, accurate and non-invasive diagnostic technique for the diagnosis of membranous nephropathy. In this study, Raman spectra of serum and urine were combined with deep learning methods to diagnose membranous nephropathy. After baseline correction and smoothing of the data, Gaussian white noise of different decibels was added to the training set for data amplification, and the amplified data were imported into ResNet, AlexNet and GoogleNet models to obtain the evaluation results of the models for membranous nephropathy. The experimental results showed that the three deep learning models achieved an accuracy of 1 for the classification of serum data of patients with membranous nephropathy and control group, and the discrimination of urine data was above 0.85, among which AlexNet was the best classification model for both samples. The above experimental results illustrate the great potential of serum- and urine-based Raman spectroscopy combined with deep learning methods for rapid and accurate identification of patients with membranous nephropathy.https://doi.org/10.1038/s41598-022-22204-1 |
spellingShingle | Xueqin Zhang Xue Song Wenjing Li Cheng Chen Miriban Wusiman Li Zhang Jiahui Zhang Jinyu Lu Chen Lu Xiaoyi Lv Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods Scientific Reports |
title | Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods |
title_full | Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods |
title_fullStr | Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods |
title_full_unstemmed | Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods |
title_short | Rapid diagnosis of membranous nephropathy based on serum and urine Raman spectroscopy combined with deep learning methods |
title_sort | rapid diagnosis of membranous nephropathy based on serum and urine raman spectroscopy combined with deep learning methods |
url | https://doi.org/10.1038/s41598-022-22204-1 |
work_keys_str_mv | AT xueqinzhang rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT xuesong rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT wenjingli rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT chengchen rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT miribanwusiman rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT lizhang rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT jiahuizhang rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT jinyulu rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT chenlu rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods AT xiaoyilv rapiddiagnosisofmembranousnephropathybasedonserumandurineramanspectroscopycombinedwithdeeplearningmethods |