Wet Poster Session

2019 Biomedical Engineering  
Digital light microscopy techniques are among the most widely used methods in cell biology and medical research. Despite that, automated classification of objects such as cells or specific parts of tissues is difficult. We present an approach to classify confluent cells in microscopy images by learnt deep correlation features using deep neural networks. These deep correlation features are generated through the use of gram-based correlation features and given to a neural network for learning the
more » ... correlation between them. This approach has proven to be suitable for the classification of artworks in respect of their artistic period. The method generates images that contain recognizable characteristics of a specific cell type, for example the average size and the ordered pattern, but lack in artifacts that occur randomly in the original image. An advantage of our approach is the achieved robustness as well as transfer the learned deep correlation features to similar cell types where not much ground data is available.
doi:10.1515/bmt-2019-6023 fatcat:mxp5r64yufccjg7dwe4orqjssa