Publications by authors named "Ori Ben-Zvi"
Article Synopsis
- The study aims to develop an automated method to quantitatively assess fetal brain gyrification using standard 2D MR imaging, instead of relying on subjective visual assessments.
- It involves analyzing imaging data of 162 fetuses—134 controls and 28 with lissencephaly or polymicrogyria—to calculate various gyrification parameters and differentiate between normal and abnormal conditions.
- Results indicate significant changes in gyrification with gestational age for normal fetuses, as well as reductions in lissencephaly and polymicrogyria cases, with machine learning algorithms effectively classifying these conditions.
Article Synopsis
- In-utero fetal MRI is becoming a crucial method for diagnosing and analyzing the developing brain, but manually segmenting cerebral structures is slow and error-prone.
- The Fetal Tissue Annotation (FeTA) Challenge was established in 2021 to promote the creation of automatic segmentation algorithms, utilizing a dataset with seven segmented fetal brain tissue types.
- The challenge saw 20 international teams submit algorithms, primarily based on deep learning techniques like U-Nets, with one team's asymmetrical U-Net architecture significantly outperforming others, establishing a benchmark for future segmentation efforts.
Automatic linear measurements of the fetal brain on MRI with deep neural networks.
Int J Comput Assist Radiol Surg
September 2021
Purpose: Timely, accurate and reliable assessment of fetal brain development is essential to reduce short and long-term risks to fetus and mother. Fetal MRI is increasingly used for fetal brain assessment. Three key biometric linear measurements important for fetal brain evaluation are cerebral biparietal diameter (CBD), bone biparietal diameter (BBD), and trans-cerebellum diameter (TCD), obtained manually by expert radiologists on reference slices, which is time consuming and prone to human error.
View Article and Find Full Text PDF