Project DetailsProf. Daphne Weihs lab researches the probability of metastasis in cancer cells by checking the level of penetration that these cells exhibit on a gel substrate. This project is aimed at performing an automatic analysis of the gel, photographed using DIC microscopy. Using these images, and additional images of nucleus staining of the cells, we were tasked with creating an algorithm for morphological recognition of the cells by use of segmentation. With this algorithm, the researchers in the lab can learn the number of cells, their areas, and their liveliness automatically, promptly and accurately.
The world of computer vision can be (reductively) broken down into 2 categories; classic image processing, popular and widespread until now, and algorithms that employ Deep Learning, which most of the academic literature in the last half-decade or so focuses on. After a broad literature review, and testing the different options, we embraced, and are very satisfied with, a hybrid option that takes a DL method and improves its accuracy and suitability for our use-case using classic methods.
