RT Journal Article
SR Electronic
T1 A Novel Transfer Learning Approach for Toxoplasma Gondii Microscopic Image Recognition by Fuzzy Cycle Generative Adversarial Network
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 567891
DO 10.1101/567891
A1 Sen Li
A1 Aijia Li
A1 Diego Alejandro Molina Lara
A1 Jorge Enrique Gómez Marín
A1 Mario Juhas
A1 Yang Zhang
YR 2019
UL http://biorxiv.org/content/early/2019/07/16/567891.abstract
AB Toxoplasma gondii, one of the world’s most common parasites, can infect all types of warm-blooded animals, including one-third of the world’s human population. Most current routine diagnostic methods are costly, time-consuming, and labor-intensive. Although T.gondii can be directly observed under the microscope in tissue or spinal fluid samples, this form of identification is difficult and requires well trained professionals. Nevertheless, the traditional identification of parasites under the microscope is still performed by a large number of laboratories. Novel, efficient and reliable methods of T.gondii identification are therefore needed, particularly in developing countries. To this end, we developed a novel transfer learning based microscopic image recognition method for T.gondii identification. This approach employs Fuzzy Cycle Generative Adversarial Network (FCGAN) with transfer learning utilizing knowledge gained by the parasitologists that Toxoplasma is in banana or crescent shaped form. Our approach aims to build connection between micro and macro associated objects by embedding fuzzy C-means cluster algorithm into Cycle Generative Adversarial Network (Cycle GAN). Our approach achieves 93.1% and 94.0% detection accuracy for 400X and 1000X Toxoplasma microscopic images respectively. We show the high accuracy and effectiveness of our approach in the newly collected unlabeled Toxoplasma microscopic images, comparing to other current available deep learning methods. This novel method for Toxoplasma microscopic image recognition will open a new window for developing cost-effective and scalable deep learning based diagnostic solution, potentially enabling broader clinical access in developing countries.