Objectives: To determine the distribution of Plasmodium (P) species including Plas-modium knowlesi and to compare the specificity and sensitivity of microscopy with nested PCR in malaria diagnosis. Methods: The study was conducted in Kawthaung, southern Myanmar. Ninety clinically suspected malaria patients were screened for malaria by Giemsa stained microscopy and confirmed by nested PCR. Results: Among the participants, 57 (63.3％) were positive and 33 (36.7％) were negative by microscopy. Of positive samples, 39 (68.4％) were Plasmodium falciparum, 17 (29.8％) Plasmodium vivax and 1 (1.8％) Plasmodium malariae, whereas 59-amplified by PCR were 40 (67.8％), 18 (30.5％) and 1 (1.7％) respectively. PCR amplified 2 mi-croscopy negative samples. Two samples of P. falciparum detected by microscopy were amplified as P. vivax and vice versa. All samples were negative for Plasmodium ovale, P. knowlesi and mixed infections. Microscopy had a very good measure of agreement (k= 0.95) compared to nested PCR. Sensitivity and specificity of microscopy for diag-nosis of P. falciparum were 92.5％(95％CI:79.6–98.4) and 96.0％(95％CI:86.3–99.5) respectively, whereas for P. vivax were 83.3％(95％CI:58.6–96.4) and 97.2％(95％CI:90.3–99.7). Conclusions: P. knowlesi was not detected by both microscopy and PCR. Giemsa stained microscopy can still be applied as primary method for malaria diagnosis and is considered as gold standard. As to the lower sensitivity of microscopy for vivax malaria, those with previous history of malaria and relapse cases should be diagnosed by RDT or PCR combined with microscopy. Inaccuracy of species diagnosis highlighted the requirement of training and refresher courses for microscopists.

Objectives To determine the distribution of Plasmodium (P) species including Plasmodium knowlesi and to compare the specificity and sensitivity of microscopy with nested PCR in malaria diagnosis. Methods The study was conducted in Kawthaung, southern Myanmar. Ninety clinically suspected malaria patients were screened for malaria by Giemsa stained microscopy and confirmed by nested PCR. Results Among the participants, 57 (63.3%) were positive and 33 (36.7%) were negative by microscopy. Of positive samples, 39 (68.4%) were Plasmodium falciparum, 17 (29.8%) Plasmodium vivax and 1 (1.8%) Plasmodium malariae, whereas 59-amplified by PCR were 40 (67.8%), 18 (30.5%) and 1 (1.7%) respectively. PCR amplified 2 microscopy negative samples. Two samples of P. falciparum detected by microscopy were amplified as P. vivax and vice versa. All samples were negative for Plasmodium ovale, P. knowlesi and mixed infections. Microscopy had a very good measure of agreement (κ = 0.95) compared to nested PCR. Sensitivity and specificity of microscopy for diagnosis of P. falciparum were 92.5% (95% CI: 79.6–98.4) and 96.0% (95% CI: 86.3–99.5) respectively, whereas for P. vivax were 83.3% (95% CI: 58.6–96.4) and 97.2% (95% CI: 90.3–99.7). Conclusions P. knowlesi was not detected by both microscopy and PCR. Giemsa stained microscopy can still be applied as primary method for malaria diagnosis and is considered as gold standard. As to the lower sensitivity of microscopy for vivax malaria, those with previous history of malaria and relapse cases should be diagnosed by RDT or PCR combined with microscopy. Inaccuracy of species diagnosis highlighted the requirement of training and refresher courses for microscopists.

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.