Irina Grigorescu

The paper introduces a deep learning pipeline for automated fetal brain segmentation and volumetry, showing reduced need for manual refinement and agreement with manual segmentations in clinical cases.

This paper proposes an automated pipeline for reconstructing fetal thorax MRI from motion-corrupted stacks across 21-36 weeks GA, using 3D CNNs and landmark-guided pose estimation.

This paper uses machine learning to predict neonatal brain age and clinical risk from structural connectomes, finding thalamocortical connections are key predictors of developmental outcomes.

The paper creates 3D MRI atlases of normal and abnormal fetal aortic arch anatomy and evaluates deep learning for automated multi-label segmentation.

This paper develops a multi-channel 4D atlas of neonatal brain development combining structural and diffusion MRI data, showing microstructural differences between term and preterm infants.

This paper applies unsupervised domain adaptation techniques to segment neonatal brain MRI data from a preterm population, improving segmentation accuracy and enabling analysis of cortical thickness and language outcomes.