Michal Marianne Amitai

Michal Marianne Amitai

Auto-generated profile, based on publicly available information

Michal Marianne Amitai

Department of Obstetrics and Gynecology, and Department of Diagnostic Radiology (M.-M.A.), Chaim Sheba Medical Center, Tel-Hashomer, Israel

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 September 2020 in American Journal of Neuroradiology
Verified
Journal Article
Closed access
PDF file
EZE. Zvi
E. Zvi
ASAsaf Shemer
Asaf Shemer
STShlomi Toussia-Cohen
Shlomi Toussia-Cohen
EZElad Zvi
Elad Zvi
YBY. Bashan
Y. Bashan
EKEldad Katorza
Eldad Katorza
BACKGROUND AND PURPOSE: Very few studies have investigated long-term neurodevelopment of children exposed to MR imaging antenatally. Thus, the purpose of our study was to evaluate long-term neurodevelopmental outcomes of children exposed to MR imaging during pregnancy. MATERIALS AND METHODS: We conducted a historical prospective cohort study in a single tertiary medical center. Women exposed to 1.5T noncontrast MR imaging for maternal or fetal indications were matched to unexposed controls. Long-term neurodevelopmental outcomes were evaluated of their children, 2.5 to 6 years of age, according to the Vineland-II Adaptive Behavior Scale. The Vineland-II Adaptive Behavior Scale assesses communication, daily living skills, socialization, and motor skills. A composite score summarizes these 4 domains. RESULTS: A total of 131 exposed women matched our inclusion criteria and were included in the study group, and 771 unexposed women, in the control group. No difference was identified in the Vineland-II Adaptive Behavior Scale composite score between the children of the study and control groups (mean, 110.79 versus 108.18; P = .098). Differences were also not observed between the children of the 2 groups in 3 of the 4 questionnaire domains: communication (108.84 versus 109.10; P = .888), daily living skills (109.51 versus 108.28; P = .437), and motor skills (105.09 versus 104.42; P = .642). However, the socialization score was favorable for the study group (112.98 versus 106.47; P < .001). CONCLUSIONS: Exposure to 1.5T noncontrast MR imaging during pregnancy had no harmful effects on long-term neurodevelopmental outcomes. This study contributes to understanding the safety of MR imaging during pregnancy.

1 April 2018
Verified
Conference Paper
Open access
ABAvi Ben-Cohen
Avi Ben-Cohen
EKEyal Klang
Eyal Klang
MAMichal Marianne Amitai
Michal Marianne Amitai
JGJacob Goldberger
Jacob Goldberger
HGHayit Greenspan
Hayit Greenspan
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network. The extended labeled data is used to train a U-net network for a pixel-wise classification into different hepatic lesions and normal liver tissues. Our dataset contains CT examinations from 140 patients with 333 CT images annotated by an expert radiologist. We tested our approach and compared it to the conventional training process. Results indicate superiority of our method. Using the anatomical data augmentation we achieved an improvement of 3% in the success rate, 5% in the classification accuracy, and 4% in Dice.