Rapid fully automatic segmentation of subcortical brain structures by shape-constrained surface adaptation

• Published in: Medical image analysis Vol. 46; pp. 146 - 161
• Main Authors: Wenzel, Fabian, Meyer, Carsten, Stehle, Thomas, Peters, Jochen, Siemonsen, Susanne, Thaler, Christian, Zagorchev, Lyubomir
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.05.2018; Elsevier BV
• Subjects: Adaptation; Algorithms; Automation; Brain; Brain - anatomy & histology; Brain - diagnostic imaging; Brain Diseases - diagnostic imaging; Deformation; Formability; Hippocampus; Hippocampus - diagnostic imaging; Humans; Image processing; Image Processing, Computer-Assisted - methods; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Mental disorders; Model-based segmentation; MP-RAGE; Multiple sclerosis; Neurological disorders; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated; Reproducibility of Results; Segmentation; Shape-constrained deformable models; Subcortical brain segmentation; T1-weighted MRI; Therapeutic applications; Volume quantification; Volume quantification; Shape-constrained deformable models; T1-weighted MRI; MP-RAGE; Subcortical brain segmentation; Model-based segmentation; Hippocampus
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2018.03.001

•Rapid segmentation of clinically relevant sub-cortical brain structures is proposed.•Proposed approach does not require pre-processing, such as bias-field correction, and requires about 30 s per scan.•Extensive evaluation demonstrates superior performance (accuracy, reproducibility) of the proposed approach over FSL FIRST or FreeSurfer.•Segmentation results of hippocampus highly coincide with ADNI-EANM ground truth. [Display omitted] This work presents a novel approach for the rapid segmentation of clinically relevant subcortical brain structures in T1-weighted MRI by utilizing a shape-constrained deformable surface model. In contrast to other approaches for segmenting brain structures, its design allows for parallel segmentation of individual brain structures within a flexible and robust hierarchical framework such that accurate adaptation and volume computation can be achieved within a minute of processing time. Furthermore, adaptation is driven by local and not global contrast, potentially relaxing requirements with respect to preprocessing steps such as bias-field correction. Detailed evaluation experiments on more than 1000 subjects, including comparisons to FSL FIRST and FreeSurfer as well as a clinical assessment, demonstrate high accuracy and test-retest consistency of the presented segmentation approach, leading, for example, to an average segmentation error of less than 0.5 mm. The presented approach might be useful in both, research as well as clinical routine, for automated segmentation and volume quantification of subcortical brain structures in order to increase confidence in the diagnosis of neuro-degenerative disorders, such as Alzheimer’s disease, Parkinson’s disease, Multiple Sclerosis, or clinical applications for other neurologic and psychiatric diseases.