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 the fuzzy cycle generative adversarial network (FCGAN) with transfer learning utilizing knowledge gained by parasitologists that Toxoplasma is banana or crescent shaped. Our approach aims to build connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves 93.1% and 94.0% detection accuracy for ×400 and ×1,000 Toxoplasma microscopic images, respectively. We showed the high accuracy and effectiveness of our approach in newly collected unlabeled Toxoplasma microscopic images, compared to other currently 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 solutions, potentially enabling broader clinical access in developing countries. IMPORTANCE 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. Artificial intelligence (AI) could provide accurate and rapid diagnosis in fighting Toxoplasma. So far, none of the previously reported deep learning methods have attempted to explore the advantages of transfer learning for Toxoplasma detection. The knowledge from parasitologists is that the Toxoplasma parasite is generally banana or crescent shaped. Based on this, we built connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves high accuracy and effectiveness in ×400 and ×1,000 Toxoplasma microscopic images.
The promotion of CO oxidization and inhibition of NO formation by gaseous iron species were analyzed using the Sandia SENKIN program. It is shown that the relative ratio of CO oxidization dramatically varies with combustion time at early burning stage in the presence of iron species, and all peak values are greater than 2.4. The relative ratio of CO oxidization decreases with the increase of air stoichiometric ratio and CO concentration in off-gas. The circulation reactions of Fe-FeO/FeO 2 -Fe achieve the catalytic effect on CO oxidization. Gaseous iron species can greatly inhibit NO formation, NO reduction ratio can reach above 70% at T = 2073 and 2273 K, and gaseous iron species can effectively inhibit NO formation when combustion temperature is not higher than 2273 K during the off-gas combustion. There are O 2 competitive reactions between thermal NO formation and Fe oxidization, and high chemical activity of iron species inhibits thermal-NO formation. INTRODUCTIONA large amount of high-temperature off-gas is produced during oxygen converter steelmaking, the major compositions of off-gas are CO and CO 2 , CO concentration varies from 15 to 70%, and off-gas temperature can reach 1900 K. 1 In the meantime, off-gas entrains a large amount of fine dusts (Fe, FeO, Fe 2 O 3 , etc.) and the amount of the dusts entrained by off-gas is about 80-150 g/m 3 . 2 The high-temperature off-gas is a precious valuable fuel. It is often discharged into the cooling stack to be combusted, and the peak temperature of flame can reach above 2000°C where CO 2 may decompose and NO x is significantly formed. 3 CO emission concentration can reach above 2000 mg/m 3 which is always over emission standards (300 mg/m 3 in China). 4,5 CO is a toxic gas which is dangerous to human health. High CO emission results in not only atmospheric pollutant but also fuel loss. NO x is a known precursor to the formation of ozone and acid rain, and it can react with volatile organic compounds to form photochemical smog. 6 Iron oxide catalyst is widely used either as single metal oxide or as a mixed oxide in industrial processes, and iron oxide exhibits intermediate activity in the complete oxidation of methane and carbon monoxide. 7-9 NO reduction by iron species has been studied in fluidized bed, and the results indicate that iron or its oxides cause a chemical reduction of NO in the presence of CO. 10 It has been discovered that injection of iron-containing compounds into the combustion and reburning zones of conventional gas-and coal-fired combustors can increase the efficiency of NO x reduction by up to 20% in comparison with that which can be achieved by basic reburning. 11 During the combustion of high-temperature off-gas entraining a large amount of dust containing iron and iron oxides, gaseous iron species is present at T > 2073 K, and it has effects on CO oxidization and NO formation. A detailed chemical kinetic mechanism for gaseous iron-species inhibition of flames, iron pentacarbonyl (Fe(CO) 5 ) mechanism, has been introduced, 12 and modeling ...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.