Deep Learning Guided Partitioned Shape Model for Anterior Visual Pathway Segmentation

• Published in: IEEE transactions on medical imaging Vol. 35; no. 8; pp. 1856 - 1865
• Main Authors: Mansoor, Awais, Cerrolaza, Juan J., Idrees, Rabia, Biggs, Elijah, Alsharid, Mohammad A., Avery, Robert A., Linguraru, Marius George
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anterior visual pathway; Automation; Biomedical optical imaging; Humans; intensity normalization; Learning; Machine learning; Magnetic Resonance Imaging; Manuals; Models, Statistical; MRI; Nerves; Optical imaging; partitioned statistical model; Pathology; Pathways; Reproducibility of Results; Robustness; Segmentation; Shape; shape model; Similarity; sparse learning; Visual; Visual Pathways
• DOI: 10.1109/TMI.2016.2535222
• ISSN: 0278-0062; 1558-254X

Analysis of cranial nerve systems, such as the anterior visual pathway (AVP), from MRI sequences is challenging due to their thin long architecture, structural variations along the path, and low contrast with adjacent anatomic structures. Segmentation of a pathologic AVP (e.g., with low-grade gliomas) poses additional challenges. In this work, we propose a fully automated partitioned shape model segmentation mechanism for AVP steered by multiple MRI sequences and deep learning features. Employing deep learning feature representation, this framework presents a joint partitioned statistical shape model able to deal with healthy and pathological AVP. The deep learning assistance is particularly useful in the poor contrast regions, such as optic tracts and pathological areas. Our main contributions are: 1) a fast and robust shape localization method using conditional space deep learning, 2) a volumetric multiscale curvelet transform-based intensity normalization method for robust statistical model, and 3) optimally partitioned statistical shape and appearance models based on regional shape variations for greater local flexibility. Our method was evaluated on MRI sequences obtained from 165 pediatric subjects. A mean Dice similarity coefficient of 0.779 was obtained for the segmentation of the entire AVP (optic nerve only =0.791) using the leave-one-out validation. Results demonstrated that the proposed localized shape and sparse appearance-based learning approach significantly outperforms current state-of-the-art segmentation approaches and is as robust as the manual segmentation.