Advanced Cell Recognition and Clustering Based on Deep Learning
ISEF · 2017 Robotics and Intelligent Machines
Overview
Observing and analyzing a microbial population change is very important in many biological and medical experiments. Mostly, people count the number of microbes with their own eyes by observing them under a microscope. Since it is a time-consuming and very tough step, we developed a ‘Deep Clustering Library (DCL)’ based on deep learning to do this step automatically. And we confirmed that it is the outstanding method, compared to other methods which were established before. Based on the library, the computer could recognize the microbes automatically with high accuracy. It can also count the number of microbes with high speed and can distinguish the round and rod-shaped microbes. We also made it enabled to distinguish the color of microbes after gram staining and to cluster two, three or more microbes gathered together. Later, we will develop it more to make it possible to count other types of cells such as a tumor, animal cells, plant cells, etc.
Competition history
- ISEF 2017
Resources
Related projects
ISEF · 2019
Optimizing Cell Quantification in Biological Assays Using a Convolutional Neural Network
ISEF · 2018
Implementing Deep Learning Techniques to Detect Abnormal Cells
ISEF · 2019
Brain Cells Phenotyping via Unsupervised Machine Learning Using Autoencoder and Clustering
ISEF · 2022
A Novel Approach of Deep Learning on Detection and Classification of Leukemic Cells and BCR-ABL1 Gene
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair