Object Detection for Cell Classification

The human body is an incredibly complex system with deeply interconnected functions. To understand this behaviour requires the knowledge of the genes expressed by every cell in a region of the tissue. As a direct consequence of the complexity of biological tissues the analysis of such images is extremely complex. The objective of this work is to use techniques of object detection and instance segmentation to help with the analysis of the image, by identifying both the location and shapes of the cells and their content. In addition to the work’s original objective, a methodology is outlined for dividing the cells in the image, rather than just identifying their positions, based on the application of Voronoi diagrams.