| 研究実績の概要 |
Induced pluripotent stem (iPS) cells have shown a huge potential for the development of regenerative medicine. However, since a large number of undifferentiated human iPS cells must be prepared for use as a renewable source of replacement cells for regenerative medicine, the development of an automated culture system for iPS cells is considered very important. In such a system, detecting the anomalies which can arise during the culture process is considered to be crucial. In this research project we have designed a novel machine learning based method for automatic detection of Good (undifferentiated) vs. Bad (differentiated) colonies of iPS cells directly from images, which makes possible the automation of the cell harvesting process.
The proposed method is based on deep learning using a Convolutional Neural Network (CNN) with a modified architecture which is better able to capture the relevant structural information regarding the spatial distribution of class probabilities. Additionally, the training can be accomplished using only a small labeled training dataset. Experimental results show that very good accuracy can be achieved by the proposed method, outperforming other current state-of-the-art algorithms for biomedical image analysis.
|
