Artificial Intelligence in Diagnostic Medical Parasitology: The State of the Art | ||||
| مجلة سوهاج لشباب الباحثين | ||||
| Volume 4, Issue 1, March 2024, Page 1-11 PDF (667.07 K) | ||||
| Document Type: المقالة الأصلية | ||||
| DOI: 10.21608/sjyr.2024.291657.1436 | ||||
 View on SCiNiTO | ||||
| Author | ||||
Eman Fathi  
| ||||
| Sohag | ||||
| Abstract | ||||
| Parasitic infections pose a significant public health concern, particu-larly in resource-limited settings. Even now, microscopy is still the “gold standard” diagnostic method. Despite the non-microscopic ad-vances, including antigen and molecular detection of human para-sites, they have not yet been integrated into routine laboratory work due to their high infrastructure requirements. Artificial intelligence (AI) using deep learning (DL) and convolutional neural networks (CNNs) is increasingly becoming an important component of clinical parasitology diagnostics. DL has shown extraordinary performance in biomedical image analysis, including various parasite diagnoses, in the past few years. AI and microscopy represent the state-of-the-art in clinical parasitology diagnostics. This review aimed to concisely high-light the recent advances in the use of AI in parasite detection in clin-ical samples. The article focuses on recently published proof-of-con-cept studies on schistosomiasis, intestinal parasitic infections, ma-laria, and leishmaniasis. In the end, we summarise the challenges and future trends that DL confronts in the field of parasite diagnostics. | ||||
| Keywords | ||||
| Artificial intelligence؛ Deep learning؛ Parasite; and Diagnosis | ||||
|
Statistics Article View: 187 PDF Download: 226 |
||||
