Journal of Isfahan Medical School
Year:2023 | Volume:41 | Issue:708|Papers Count:3

Background: Infection with various viruses during pregnancy may affect the baby's hearing. The results regarding the mother's infection with COVID-19 during pregnancy are contradictory. The purpose of this study is to compare the hearing status of infants whose mothers had a history of COVID-19 disease in the third trimester of pregnancy with the control group. Methods: This descriptive-analytical study was conducted in 1400 in Isfahan province. 35 babies belonged to the group whose mothers had a history of COVID-19 during the 3rd trimester of the recent pregnancy, and 35 babies were in the control group. The results of newborn hearing screening tests were asked from the mothers and recorded. In the first stage, the Transient Otoacoustic Emissions (TOAEs) test was recorded for both groups, and for infants who had a failed response at this stage, the results of the next tests (TEOAE) and Automated Auditory Brainstem Response (AABR) that were conducted 15 days after the first evaluation were recorded, and in case of failed again, the results of the Auditory Brainstem Response (ABR) test were recorded to know the hearing status of infants. Findings: 19 infants in the COVID-19 group and 13 infants in the control group had screening tests with a referral result. In the second assessment, in the COVID-19 group only one infant had a referral result. In the diagnostic assessment, this infant's hearing turned out to be normal. All the infants in the Control Group had acceptable results in the second test (P = 0. 314). Conclusion: The analysis of results shows that infliction with COVID-19 in the third trimester of pregnancy does not increase the risk of hearing loss among infants.

Background: Due to the limitations of CT imaging, it is necessary to use magnetic resonance imaging (MRI) as a complementary method in the treatment planning process. This study aimed to compare contouring and treatment planning based on MRI/CT images with contouring and treatment planning based on CT images in the treatment of rectal cancer using helical tomotherapy. Methods: In this prospective study, 12 patients with rectal cancer underwent MRI diagnostic imaging and CT imaging was also performed at an interval of one day. The contouring process was performed for each patient based on both methods. After that, a dose of 45 Gy was delivered to the planning target volume (PTV). Finally, the size of the treatment volumes and the parameters Dmean, V45, HI, CI, and D98% were extracted and compared from the treatment planning system. Findings: CT-based contouring method compared to MRI/CT-based method showed higher averages for treatment volumes. In addition, in CT-based plans compared to MRI/CT-based plans, the average CI, V45, and D98% were significantly lower and the average HI was significantly higher. Conclusion: The results of this study show that contouring based on MRI/CT images can estimate the size of treatment volumes smaller than contouring based on CT. Also, treatment plans based on MRI/CT images can provide more appropriate dose coverage for PTV.

Background: This study was conducted in order to investigate the power and efficiency of transfer learning in solving the problem of deep learning data volumes for automatic segmentation of the treatment target area in glioma cancer patients. Methods: In this study, T1, T2 and Flair images of one hundred patients whose glioma cancer was confirmed were used. After quality review, all images were normalized and resized. Then the images were given to a model in two modes with and without transfer learning and their performance was evaluated with the degree of similarity, overlap, sensitivity and accuracy. Findings: The results of our study show that transfer learning can increase the efficiency of automatic segmentation and increase the similarity of automatic segmentation with manual segmentation to more than 76% in Flair images. Also, this method has increased the speed of reaching the desired result in T2 images that could not improve the results. Conclusion: Deep learning in automatic segmentation can overcome the limitations caused by data volume in glioma patients and improve their performance.