Stem Cell Classification
Abstract: Machine learning and neural networks have recently become hot topics in many research areas. They have already proved to be useful in the fields of medicine and biotechnology. In these areas, they can be used to facilitate complicated and time consuming analysis processes. An important application is image recognition of cells, tumours etc., which also is the focus of this paper.Our project was to construct both Fully Connected Neural Networks and Convolutional Neural Networks with the ability to recognize pictures of muscular stem cells (MuSCs). We wanted to investigate if the intensity values in each pixel of the images were sufficient to use as indata for classification.By optimizing the structure of our networks, we obtained good results. Using only the pixel values as input, the pictures were correctly classified with up to 95.1% accuracy. If the image size was added to the indata, the accuracy was as best 97.9 %.The conclusion was that it is sensible and practical to use pixel intensity values as indata to classification programs. Important relationships exist and by adding some other easily accessible characteristics, the success rate can be compared to a human’s ability to classify these cells.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)