Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images
This work addresses the need for automated analysis to ease experts' work in a specific domain, but it appears incremental as it focuses on optimizations of existing autoencoder methods.
The paper tackles the problem of manual analysis of microscopic in situ hybridization images by proposing a deep-learning autoencoder framework to detect and classify areas with similar gene expression levels, achieving results validated against expert evaluation using mean-squared error.
Currently, analysis of microscopic In Situ Hybridization images is done manually by experts. Precise evaluation and classification of such microscopic images can ease experts' work and reveal further insights about the data. In this work, we propose a deep-learning framework to detect and classify areas of microscopic images with similar levels of gene expression. The data we analyze requires an unsupervised learning model for which we employ a type of Artificial Neural Network - Deep Learning Autoencoders. The model's performance is optimized by balancing the latent layers' length and complexity and fine-tuning hyperparameters. The results are validated by adapting the mean-squared error (MSE) metric, and comparison to expert's evaluation.