Unsupervised convolutional variational autoencoder deep embedding clustering for Raman spectra.

Unsupervised deep learning methods place increased emphasis on the process of cluster analysis of unknown samples without requiring sample labels. Clustering algorithms based on deep embedding networks have been recently developed and are widely used in data mining, speech processing and image recognition, but barely any of them have been used on spectra data. This study presents an unsupervised clustering algorithm for Raman spectra, called the convolutional variational autoencoder deep embedding clustering method (CVDE). It improves the network structure of the multi-layer perception (MLP) that is commonly used in other methods based on the VAE-GMM model, like VaDE, by replacing the hidden fully connected layer in the MLP with three convolution layers and two pooling layers for better clustering on the Raman spectra. The three convolution layers extend vertical channels to learn features, while pooling layers directly reduce the horizontal coding dimensions to prevent gradient explosion and overfitting. Furthermore, such network structures can easily incorporate the gradient-weighted class activation mapping (Grad-Cam) method to visualise the importance of spectral features for clustering, facilitating network tuning and spectral difference analysis. Moreover, through comparative experiments, CVDE has proven that it affords better clustering performance than current advanced clustering methods on not only the MNIST dataset but also two sets of Raman spectra: soybean oil Raman spectra with very small Raman feature differences and drug Raman spectra with a small data size. The clustering accuracies of these three datasets reach 94.48%, 90.43% and 98.70% respectively. Thus, CVDE is suitable for applications in static spectra, such as Raman spectra and LIBS spectra, and is more versatile than supervised methods in the spectral and chemical analysis fields.

Effects of electroacupuncture combined with stem cell transplantation on anal sphincter injury-induced faecal incontinence in a rat model.

BACKGROUND: Bone marrow mesenchymal stem cells (BMSCs) and acupuncture are known to mitigate tissue damage. This study aimed to investigate the therapeutic effects of combined electroacupuncture (EA) stimulation and BMSC injection in a rat model of anal sphincter injury-induced faecal incontinence (FI). METHODS: 60 Sprague-Dawley rats were randomly divided into five groups: sham-operated control, FI, FI+EA, FI+BMSC, and FI+BMSC+EA. The anorectal tissues were collected on days 1, 3, 7 and 14. Repair of the injured anal sphincter was compared using haematoxylin and eosin (HE) and immunocytochemiscal analyses with sarcomeric α actinin. The expression of stromal cell derived factor-1 (SDF-1) and monocyte chemoattractant protein-3 (MCP-3) was detected by quantitative reverse transcription PCR to evaluate the effects of EA on the homing of BMSCs. RESULTS: The therapeutic effect of combined EA+BMSCs on damaged tissue was the strongest among all the groups as indicated by HE and immunohistochemical staining. The expression of SDF-1 and MCP-3 was significantly increased by combined EA and BMSC treatment when compared with the other groups (P=0.01 to P<0.05), suggesting promotive effects of EA on the homing of BMSCs. CONCLUSION: The combination of EA and BMSC transplantation effectively repaired the impaired anal sphincters. The underlying mechanism might be associated with apparent promotive effects of EA on the homing of BMSCs. Our study provides a theoretical basis for the development of a non-surgical treatment method for FI secondary to muscle impairment.