Related Experiment Video
Updated: May 13, 2025
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
Rapid diagnosis of membranous nephropathy based on kidney tissue Raman spectroscopy and deep learning
Guoqiang Zhu1, Halinuer Shadekejiang1, Xueqin Zhang2
1The First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830054, China.
Abstract:
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.
Insights
Diagnosing membranous nephropathy (MN) is challenging. This study introduces a rapid method using Raman spectroscopy and AI for accurate MN diagnosis from kidney tissue, improving upon current diagnostic limitations.
Area of Science:
- Nephrology
- Biomedical Engineering
- Computational Pathology
Background:
- Membranous nephropathy (MN) is a leading cause of glomerular disease.
- Current diagnostics, including anti-PLA2R antibodies, have limitations in sensitivity.
- Renal biopsy, the gold standard, is complex and time-consuming.
Purpose of the Study:
- To develop a rapid, accurate diagnostic method for MN.
- To overcome the limitations of traditional renal biopsy analysis.
- To explore the utility of Raman spectroscopy combined with deep learning for MN pathology.
Main Methods:
- Utilized Raman spectroscopy on mouse kidney tissue samples.
- Developed and applied a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) deep learning model.
- Validated the model's diagnostic performance for MN.
Main Results:
- The CNN-BiLSTM model achieved 98% accuracy in diagnosing MN.
- The model demonstrated high sensitivity (98.3%) and specificity (98.3%).
- Raman spectroscopy combined with AI offers a promising rapid diagnostic approach.
Conclusions:
- A novel method combining Raman spectroscopy and deep learning provides a rapid auxiliary tool for MN diagnosis.
- This approach can potentially streamline pathological diagnosis and improve patient management.
- Further research may validate this technique for clinical application in human samples.
