Seyed Raein Hashemi

TL;DR: This paper developed a 3D fully convolutional densely connected network (FC-DenseNet) with large overlapping image patches as input and an asymmetric similarity loss layer based on Tversky index, which led to the lowest surface distance and the best lesion true positive rate.

TL;DR: In this paper, a 2D U-Net and autocontext based segmentation method was proposed to segment the fetal brain in real-time while the fetal MRI slices are being acquired.

TL;DR: A deep fully convolutional neural network based on 2D U-net and autocontext that can be used to segment the fetal brain in real-time while fetal MRI slices are being acquired and can enable real- time motion tracking, motion detection, and 3D reconstruction of fetal brain MRI.

TL;DR: This paper proposes Tversky loss function as a generalization of the Dice similarity coefficient and Fβ scores to effectively train deep neural networks and proposes a patch prediction fusion strategy based on B-spline weighted soft voting to take into account the uncertainty of prediction in patch borders.

TL;DR: A patch-wise 3D densely connected network with an asymmetric loss function, where large overlapping image patches for intrinsic and extrinsic data augmentation, a patch selection algorithm, and a patch prediction fusion strategy based on B-spline weighted soft voting to take into account the uncertainty of prediction in patch borders are developed.