Privacy Preserved Cervical Cancer Detection Using Convolutional Neural Networks Applied to Pap Smear Images.

Image processing has enabled faster and more accurate image classification. It has been of great benefit to the health industry. Manually examining medical images like MRI and X-rays can be very time-consuming, more prone to human error, and way more costly. One such examination is the Pap smear exam, where the cervical cells are examined in laboratory settings to distinguish healthy cervical cells from abnormal cells, thus indicating early signs of cervical cancer. In this paper, we propose a convolutional neural network- (CNN-) based cervical cell classification using the publicly available SIPaKMeD dataset having five cell categories: superficial-intermediate, parabasal, koilocytotic, metaplastic, and dyskeratotic. CNN distinguishes between healthy cervical cells, cells with precancerous abnormalities, and benign cells. Pap smear images were segmented, and a deep CNN using four convolutional layers was applied to the augmented images of cervical cells obtained from Pap smear slides. A simple yet efficient CNN is proposed that yields an accuracy of 0.9113% and can be successfully used to classify cervical cells. A simple architecture that yields a reasonably good accuracy can increase the speed of diagnosis and decrease the response time, reducing the computation cost. Future researchers can build upon this model to improve the model's accuracy to get a faster and more accurate prediction.

Diagnostic Accuracy of Cerebroplacental Ratio in Prediction of Postnatal Outcomes in Oligohydramnios.

BACKGROUND AND AIM: The evidence on isolated oligohydramnios (IO) patients and their postnatal outcomes are inconsistent. Recent research has clarified the connection between that IO and negative outcomes in the postnatal period. Our goal was to analyze the correlation between Doppler measurements and postnatal outcomes in oligohydramnios patients, with a focus on the cerebroplacental ratio (CPR). METHODOLOGY: A cohort study was conducted in the Radiology Department of Khan Research Laboratories (KRL) Hospital from October 2021 to July 2022. One hundred women were chosen as the sample size. For this study, we used the Raosoft sample size calculator with a 95% confidence interval and a 5% margin of error. Both the middle cerebral artery and the umbilical artery were imaged using ultrasound, and the systolic-to-diastolic ratio and peak systolic velocity are recorded. Pulsatility index (PI) and resistive index (RI) were also calculated. If the amniotic fluid index (AFI) is less than 5 cm, the condition is known as oligohydramnios. The newborn's APGAR score was taken immediately after birth as well as after 5 minutes. RESULTS: We have determined that, on average, mothers are 35.45 weeks/248.15 days pregnant. When compared to the reference standard, CPR diagnostic features showed a sensitivity of 92% and a specificity of 77.27. Overall diagnostic accuracy is predicted to be 93.0%, with a 93.50% positive prognosis and a 73.91% negative prognosis. The effect size for the change in APGAR scores before and after the test was -2.38 1.03, with a 95% confidence interval of -2.58 to -2.17 and a significance level of 0.00. CONCLUSION: This study concludes that CPR is an effective screening tool and that it can be used to predict postnatal outcomes in patients with oligohydramnios. Clinical prediction rules were found to be a more effective screening tool, with a sensitivity of 92%, a specificity of 77.27%, and a diagnostic accuracy of 92.3%.