Intestinal parasitic infections (IPIs) caused by protozoan and helminth parasites are among the most common infections in humans in low-and-middle-income countries. IPIs affect not only the health status of a country, but also the economic sector. Over the last decade, pattern recognition and image processing techniques have been developed to automatically identify parasitic eggs in microscopic images. Existing identification techniques are still suffering from diagnosis errors and low sensitivity. Therefore, more accurate and faster solution is still required to recognize parasitic eggs and classify them into several categories. A novel Chula-ParasiteEgg dataset including 11,000 microscopic images proposed in ICIP2022 was utilized to train various methods such as convolutional neural network (CNN) based models and convolution and attention (CoAtNet) based models. The experiments conducted show high recognition performance of the proposed CoAtNet that was tuned with microscopic images of parasitic eggs. The CoAtNet produced an average accuracy of 93%, and an average F1 score of 93%. The finding opens door to integrate the proposed solution in automated parasitological diagnosis.
The present study was conducted to determine the occurrence of Schistosoma spindale ova and its associated risk factors in Malaysian cattle through a coprological survey. A total of 266 rectal fecal samples were collected from six farms in Peninsular Malaysia. The overall infection rate of S. spindale was 6% (16 of 266). Schistosoma spindale infection was observed in two farms, with a prevalence of 5.4% and 51.9%, respectively. This trematode was more likely to co-occur with other gastro-intestinal parasites (i.e., Dicrocoelium spp., Paramphistomum spp., strongyle, Eimeria spp. and Entamoeba spp.). Chi-square analysis revealed that female cattle are less likely to get S. spindale infection as compared to male cattle (OR = 0.3; 95% CI = 0.08-1.06; p < 0.05), and cattle weighing lower than 200 kg, were significantly at higher risk than those higher than 200 kg (OR = 5; 95% CI = 1.07-24.79; p < 0.05) to the infection. Multivariate analysis confirmed that among the cattle in Malaysia, the age (cattle with two year old and higher: OR = 21; 95% CI = 2.48-179.44; p < 0.05) and weight (weighing 200 kg and lower: OR = 17; 95% CI = 3.38-87.19; p < 0.05) were risk factors for S. spindale infection among Malaysian cattle.
Soil contaminated with helminth eggs and protozoan cysts is a potential source of infection and poses a threat to the public, especially to young children frequenting playgrounds. The present study determines the levels of infection of helminth eggs in soil samples from urban and suburban playgrounds in five states in Peninsular Malaysia and identifies one source of contamination via faecal screening from stray animals. Three hundred soil samples from 60 playgrounds in five states in Peninsular Malaysia were screened using the centrifugal flotation technique to identify and determine egg/cyst counts per gram (EPG) for each parasite. All playgrounds, especially those in Penang, were found to be contaminated with eggs from four nematode genera, with Toxocara eggs (95.7%) the highest, followed by Ascaris (93.3%), Ancylostoma (88.3%) and Trichuris (77.0%). In addition, faeces from animal shelters were found to contain both helminth eggs and protozoan cysts, with overall infection rates being 54% and 57% for feline and canine samples, respectively. The most frequently occurring parasite in feline samples was Toxocara cati (37%; EPG, 42.47 ± 156.08), while in dog faeces it was Ancylostoma sp. (54%; EPG, 197.16 ± 383.28). Infection levels also tended to be influenced by season, type of park/playground and the texture of soil/faeces. The occurrence of Toxocara, Ancylostoma and Trichuris eggs in soil samples highlights the risk of transmission to the human population, especially children, while the presence of Ascaris eggs suggests a human source of contamination and raises the issue of hygiene standards and public health risks at sites under investigation.