METHODS: This study applies radiomics and deep learning in the diagnosis of lung cancer to help clinicians accurately analyze the images and thereby provide the appropriate treatment planning. 86 patients were recruited from Bach Mai Hospital, and 1012 patients were collected from an open-source database. First, deep learning has been applied in the process of segmentation by U-NET and cancer classification via the use of the DenseNet model. Second, the radiomics were applied for measuring and calculating diameter, surface area, and volume. Finally, the hardware also was designed by connecting between Arduino Nano and MFRC522 module for reading data from the tag. In addition, the displayed interface was created on a web platform using Python through Streamlit.
RESULTS: The applied segmentation model yielded a validation loss of 0.498, a train loss of 0.27, a cancer classification validation loss of 0.78, and a training accuracy of 0.98. The outcomes of the diagnostic capabilities of lung cancer (recognition and classification of lung cancer from chest CT scans) were quite successful.
CONCLUSIONS: The model provided means for storing and updating patients' data directly on the interface which allowed the results to be readily available for the health care providers. The developed system will improve clinical communication and information exchange. Moreover, it can manage efforts by generating correlated and coherent summaries of cancer diagnoses.
MATERIAL AND METHODS: This was a prospective cohort study conducted in a tertiary referral hospital in Sydney, Australia. In all, 212 women with a low-risk pregnancy or with gestational diabetes were recruited including 158 nulliparous and 54 parous women. Maternal demographic, clinical and ultrasound characteristics were collected at 37 weeks of gestation. Semi-Bayesian logistic regression and Markov chain Monte Carlo simulation were used to assess the relation between cervical length and cesarean section in labor.
RESULTS: Rates of cesarean section were 5% (2/55) for cervical length ≤20 mm, 17% (17/101) for cervical length 20-32 mm, and 27% (13/56) for cervical length >32 mm. These rates were 4, 22 and 33%, respectively, in nulliparous women. In the semi-Bayesian analysis, the odds ratio for cesarean section was 6.2 (95% confidence interval 2.2-43) for cervical length 20-32 mm and 10 (95% confidence interval 4.8-74) for cervical length >32 mm compared with the lowest quartile of cervical length, after adjusting for maternal age, parity, height, prepregnancy body mass index, gestational diabetes, induction of labor, neonatal sex and birthweight centile.
CONCLUSIONS: Cervical length at 37 weeks of gestation is associated with intrapartum cesarean section.
METHODS: A competitive enzyme-linked immunosorbent assay (cELISA) using a monoclonal antibody (mAb) and recombinant NiV glycoprotein (G) was developed and laboratory evaluated using sera from experimental pigs, mini pigs and nonhuman primates. The test depends on competition between specific antibodies in positive sera and a virus-specific mAb for binding to NiV-G.
RESULTS: Based on 1,199 negative and 71 NiV positive serum test results, the cutoff value was determined as 35% inhibition. The diagnostic sensitivity and specificity of the NiV cELISA was 98.58 and 99.92%, respectively. When testing sera from animals experimentally infected with NiV Malaysia, the cELISA detected antibodies from 14 days post-infection (dpi) and remained positive until the end of the experiment (28 dpi). Comparisons using the Kappa coefficient showed strong agreement (100%) between the cELISA and a plaque reduction neutralization test (PRNT).
DISCUSSION: Because our cELISA is simpler, faster, and gives comparable or better results than PRNT, it would be an adequate screening test for suspect NiV and HeV cases, and it would also be useful for epidemiological surveillance of Henipavirus infections in different animal species without changing reagents.