Search

Background: Myocardial perfusion imaging (MPI) is a type of single-photon emission computed tomography (SPECT) used to evaluate patients with suspected or confirmed coronary artery disease (CAD). Detection and diagnosis of CAD are complex processes requiring precise and accurate image processing. Proper segmentation is critical for accurate diagnosis, but segmentation issues can pose significant challenges, leading to diagnostic difficulties. Machine learning (ML) algorithms have demonstrated superior performance in addressing segmentation problems., Methods: In this study, a deep learning (DL) algorithm, U-Net, was employed to enhance segmentation accuracy for image segmentation in MPI. Data were collected from 1100 patients who underwent MPI studies at Al-Jahra Hospital between 2015 and 2024. To train the U-Net model, 100 studies were segmented by nuclear medicine (NM) experts to create a ground truth (gold-standard coordinates). The dataset was divided into a training set ( n = 100 images) and a validation set ( n = 900 images). The performance of the U-Net model was evaluated using multiple cross-validation metrics, including accuracy, precision, intersection over union (IOU), recall, and F1 score., Result: A dataset of 4560 images and corresponding masks was generated. Both holdout and k-fold (k = 5) validation strategies were applied, utilizing cross-entropy and Dice score as evaluation metrics. The best results were achieved with the holdout split and cross-entropy loss function, yielding a test accuracy of 98.9%, a test IOU of 89.6%, and a test Dice coefficient of 94%. The k-fold validation scenario provided a more balanced true positive and false positive rate. The U-Net segmentation results were comparable to those produced by expert nuclear medicine technologists, with no significant difference ( p = 0.1)., Conclusions: The findings demonstrate that the U-Net model effectively addresses some segmentation challenges in MPI, facilitating improved diagnosis and analysis of mega data.

We sought to assess pre-vaccination and post-vaccination seroprevalences of anti-SARS-CoV-2 antibodies in Kuwait and to compare antibody levels between vaccine types. In phase 1 (pre-vaccination period, n = 19,363), blood samples were collected before the launch of COVID-19 vaccination in Kuwait between 1 September and 31 December 2020. Blood samples for phase 2 (post-vaccination period, n = 4973) were collected between 1 September and 30 November 2021. We tested subjects for anti-SARS-CoV-2 antibodies using the DiaSorin LIAISON ® SARS-CoV-2 IgM and Trimeric S IgG tests. In the pre-vaccination period, the prevalence of SARS-CoV-2 IgM and IgG was 14.50% (95% CI: 14.01-15.00) and 24.89% (95% CI: 24.29-25.50), respectively. The trend of seropositivity increased with age and was higher for females and non-Kuwaiti participants ( p < 0.0001). Interestingly, seroprevalence was significantly higher for those who had received one dose of BNT162b2 (95.21%) than those who had received one dose of ChAdOx1-nCov-19 (92.86%). In addition, those who reported receiving two doses had higher seroprevalence, 96.25%, 95.86%, and 94.93% for ChA-dOx1-nCov-19/AstraZeneca, mix-and-match, and BNT162b2 recipients, respectively. After the second dose, median spike-specific responses showed no significant difference between ChAdOx1-nCov-19 and BNT162b2. Furthermore, statistical analysis showed no significant difference between median anti-trimeric S antibody levels of vaccinated individuals according to sex, age, or nationality ( p > 0.05). In contrast, a negative correlation between age and anti-trimeric S IgG titers of BNT162b2-vaccinated subjects was observed (r = -0.062, p = 0.0009). Antibody levels decreased with time after vaccination with both vaccines. Our findings indicate that seroprevalence was very low during the pre-vaccination period (25%) in the general population and was greater than 95% in the vaccinated population in Kuwait. Furthermore, ChAdOx1-nCov-19 and BNT162b2 are effective in generating a similar humoral response.

Sex hormone disruptors (xenoestrogens) are a global concern due to their potential toxicity. However, to date, there has been no study to investigate the presence of xenoestrogen pollutants in the Jordanian water system. Samples in triplicates were collected from six locations in Jordan, including dams, surface water, tap or faucet water, and filtered water (drinking water-local company). Xenoestrogens were then extracted and evaluated with a yeast estrogen screen utilizing Saccharomyces cerevisiae. Later, possible pollutants were mined using ultrahigh-performance liquid chromatography (UPLC) coupled with a Bruker impact II Q-TOF-MS. Possible hits were identified using MetaboScape software (4000 compounds), which includes pesticide, pharmaceutical pollutant, veterinary drug, and toxic compound databases and a special library of 75 possible xenoestrogens. The presence of xenoestrogens in vegetable samples collected from two different locations was also investigated. The total estrogen equivalents according to the YES system were 2.9 ± 1.2, 9.5 ± 5, 2.5 ± 1.5, 1.4 ± 0.9 ng/L for King Talal Dam, As-Samra Wastewater Treatment Plant, King Abdullah Canal, and tap water, respectively. In Almujeb Dam and drinking water, the estrogenic activity was below the detection limit. Numbers of identified xenoestrogens were: As-Samra Wastewater Treatment Plant 27 pollutants, King Talal Dam 20 pollutants, Almujeb Dam 10 pollutants, King Abdullah Canal 16 pollutants, Irbid tap water 32 pollutants, Amman tap water 30 pollutants, drinking water 3 pollutants, and vegetables 7 pollutants. However, a large number of compounds remained unknown. Xenoestrogen pollutants were detected in all tested samples, but the total estrogenic capacities were within the acceptable range. The major source of xenoestrogen pollutants was agricultural resources. Risk evaluations for low xenoestrogen activity should be taken into account, and thorough pesticide monitoring systems and regular inspections should also be established.