Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database

Abstract

Accurate extraction of brain tissues from magnetic resonance (MR) images is important in neuroradiology. However, brain extraction is more difficult for pediatric brains than for adult brains due to several factors including smaller brain sizes and lower tissue contrasts. In this work, we propose a brain extraction technique that utilizes dual frame (DF) 3D U‐net deep learning architecture and the human connectome project (HCP) database for multislice 2D pediatric T2‐weighted MR images with diseases. To improve segmentation accuracy in small pediatric brains with detailed boundary regions, DF 3D U‐net architecture was used. We pretrained networks with the HCP database to compensate for the limited amount of MR images and manual segmentation masks of pediatric patients. For quantitative analysis, we compared the brain extraction results of brain extraction tool, DF, and conventional 3D U‐net using the dice similarity coefficient (DSC), intersection of union (IoU), and boundary F1 (BF) scores; each deep learning architecture was evaluated with and without pretraining using the HCP. This study included 10 patients with diseases and all images were acquired using a PROPELLER MR sequence. Pretraining using the HCP database enhanced segmentation performance of the network, and the skip connections in the DF 3D U‐net could enhance the contour similarity of segmentation results. Experimental results showed that the proposed method increased the DSC, IoU, and BF scores by 0.8%, 1.6%, and 1.5%, respectively, compared with those of the conventional 3D U‐net without pretraining.

A brain extraction algorithm for infant T2 weighted magnetic resonance images based on fuzzy c-means thresholding

“…In addition, a pre-trained deep learning brain extraction method (PARIETAL) performed successfully with T1-weighted adult brains on three different scanners 19 and the convolutional neural network (CNN) was also successfully adopted to extract the brain regions, trained by T1-wighted healthy or diseased adult images, and the fetal T2-weighted images scanned at a gestational age between 19 and 39 weeks 20 . However, the segmentation performance of the deep-learning based approaches largely depend on the characteristics of the training and target datasets, which is limitation of many machine-learning based image processing techniques 18 , 21 , 22 .…”