Subject-specific atlas for automatic brain tissue segmentation of neonatal magnetic resonance images

• Published in: Scientific reports Vol. 14; no. 1; pp. 19114 - 14
• Main Authors: Noorizadeh, Negar, Kazemi, Kamran, Taji, Seyedeh Masoumeh, Danyali, Habibollah, Aarabi, Ardalan
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 18.08.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1564; 631/1647/245/1628; Accuracy; Atlases as Topic; Brain; Brain - diagnostic imaging; Brain tissue segmentation; Cerebrospinal fluid; Cognitive science; Expectation maximization; Female; Gestational age; Gray Matter - diagnostic imaging; Humanities and Social Sciences; Humans; Image processing; Image Processing, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Infant, Newborn; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Multi-atlas; multidisciplinary; Neonate; Neonates; Neuroimaging; Neuroscience; Random forest; Science; Science (multidisciplinary); Segmentation; Structural analysis; Subject-specific atlas; Substantia alba; Substantia grisea; Tissues; White Matter - diagnostic imaging; Multi-atlas; Expectation maximization; Brain tissue segmentation; Random forest; Neonate; Subject-specific atlas
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-69995-z

Developing advanced systems for 3D brain tissue segmentation from neonatal magnetic resonance (MR) images is vital for newborn structural analysis. However, automatic segmentation of neonatal brain tissues is challenging due to smaller head size and inverted T1/T2 tissue contrast compared to adults. In this work, a subject-specific atlas based technique is presented for segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from neonatal MR images. It involves atlas selection, subject-specific atlas creation using random forest (RF) classifier, and brain tissue segmentation using the expectation maximization-Markov random field (EM-MRF) method. To increase the segmentation accuracy, different tissue intensity- and gradient-based features were used. Evaluation on 40 neonatal MR images (gestational age of 37–44 weeks) demonstrated an overall accuracy of 94.3% and an average Dice similarity coefficient (DSC) of 0.945 (GM), 0.947 (WM), and 0.912 (CSF). Compared to multi-atlas segmentation methods like SEGMA and EM-MRF with multiple atlases, our method improved accuracy by up to 4%, particularly in complex tissue regions. Our proposed method allows accurate brain tissue segmentation, a crucial step in brain magnetic resonance imaging (MRI) applications including brain surface reconstruction and realistic head model creation in neonates.