An Autoencoder based Technique for DNA Microarray Image Denoising
| Autor: | P. S. Sathidevi, Arya Mohandas, Steffy Maria Joseph |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
021110 strategic
defence & security studies Noise measurement Computer science business.industry Noise reduction 0211 other engineering and technologies Pattern recognition 02 engineering and technology Image segmentation Autoencoder Reduction (complexity) Segmentation Noise (video) Artificial intelligence DNA microarray business |
| Zdroj: | 2020 International Conference on Communication and Signal Processing (ICCSP). |
| DOI: | 10.1109/iccsp48568.2020.9182265 |
| Popis: | DNA Microarray is one of the proven tools for genomics. It can be used to detect all the gene expression variations between two different types of cells in a single experiment. The microarray image is a rectangular grid with many subgrids, and each subgrid has organized gene samples called spots, the number of which varies with the manufacturer. The spot intensity information is the most important parameter for gene expression analysis, disease diagnosis, and drug discovery. But, obtaining the spot intensity of DNA microarray images (MAI) is highly challenging as the image is of low contrast and noisy. The various steps involved in obtaining the intensity of the spot are Image enhancement, Gridding, Spot segmentation and Extraction of intensity. Out of these steps, image enhancement is of utmost importance as it can affect the accuracy of the extraction of spot intensity. In this paper, we propose an autoencoder based image denoising for enhancing the DNA MAI. It is a stochastic extension to classic autoencoder. The method is tested on SIB and Derisi datasets. The experimental results indicate that there is a considerable reduction in noise when compared with other recent related methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|