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

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.