Morphology-driven automatic segmentation of MR images of the neonatal brain |
| |
| Authors: | Laura Gui Radoslaw Lisowski Tamara Faundez Petra S Hüppi François Lazeyras Michel Kocher |
| |
| Institution: | 1. Division of Development and Growth, Department of Pediatrics, University of Geneva, Geneva, Switzerland;2. Department of Radiology and Medical Informatics, University of Geneva, Switzerland;3. Biomedical Imaging Group, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland;1. Division of Sports Medicine, Children''s Hospital Boston, Boston, Massachusetts, U.S.A.;2. Division of Sports Medicine, Stanford University, Redwood City, California, U.S.A.;3. Steadman Philippon Research Institute, Vail, Colorado, U.S.A.;4. Division of Sports Medicine, University of Michigan, Ann Arbor, Michigan, U.S.A.;5. Hospital for Special Surgery, New York, New York, U.S.A.;6. Nashville Sports Medicine Center, Nashville, Tennessee, U.S.A.;7. Southern California Orthopaedic Institute, Van Nuys, California, U.S.A.;8. The Hip Clinic, Oklahoma Sports Science and Orthopaedics, Oklahoma City, Oklahoma, U.S.A.;9. Washington University Orthopaedics, St Louis, Missouri, U.S.A.;10. Post Street Orthopaedics and Sports Medicine, San Francisco, California, U.S.A.;11. Minnesota Orthopedic Sports Medicine Institute, Minneapolis, Minnesota, U.S.A.;12. Massachusetts General Hospital, Boston, Massachusetts, U.S.A.;13. Division of Orthopaedic Surgery, University of Calgary, Calgary, Alberta, Canada;14. Orthopaedic Surgery Research Group, University of Warwick, Coventry, England;15. Hip Service, Schulthess Clinic, Zurich, Switzerland, U.S.A.;p. National Rehabilitation Institute of Mexico, Mexico City, Mexico;1. Department of Neurological Surgery, Weill Cornell Medical College, Cornell University, New York, New York, USA;2. Department of Neurosurgery, Kyoto University School of Medicine, Kyoto, Japan;1. Department of Oral and Maxillofacial Surgery, Hekinan Municipal Hospital, Aichi, Japan;2. Department of Maxillofacial Surgery, Aichi-Gakuin University School of Dentistry, Aichi, Japan;3. Department of Oral and Maxillofacial Surgery and Stomatology, Okazaki City Hospital, Aichi, Japan;1. Seattle Science Foundation, Seattle, WA 98122, USA;2. Department of Anatomical Sciences, St. George’s University, Grenada;3. Centre of Anatomy and Human Identification, University of Dundee, DD1 4HN, Scotland, UK;4. Saarland University Medical Center and Saarland University Faculty of Medicine, D66424 Homburg, Germany;5. Goodman Campbell Brain and Spine, Department of Neurological Surgery, Indiana University School of Medicine, 355 W. 16th Street, Suite #5100, Indianapolis, IN 46202, USA;6. California Brain Institute, Los Robles Hospital and Medical Center, Thousand Oaks, CA 91360, USA;1. PhD candidate, Department of Oral Diagnosis, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil;2. Postdoctoral Researcher, Department of Oral Diagnosis, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil;3. PhD candidate, Department of Oral Diagnosis, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil;4. PhD candidate, Department of Oral Diagnosis, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil;6. Professor, Department of Social Dentistry, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil;5. Professor, Department of Oral Diagnosis, Piracicaba Dental School, State University of Campinas, Piracicaba, SP, Brazil |
| |
| Abstract: | The segmentation of MR images of the neonatal brain is an essential step in the study and evaluation of infant brain development. State-of-the-art methods for adult brain MRI segmentation are not applicable to the neonatal brain, due to large differences in structure and tissue properties between newborn and adult brains. Existing newborn brain MRI segmentation methods either rely on manual interaction or require the use of atlases or templates, which unavoidably introduces a bias of the results towards the population that was used to derive the atlases. We propose a different approach for the segmentation of neonatal brain MRI, based on the infusion of high-level brain morphology knowledge, regarding relative tissue location, connectivity and structure. Our method does not require manual interaction, or the use of an atlas, and the generality of its priors makes it applicable to different neonatal populations, while avoiding atlas-related bias. The proposed algorithm segments the brain both globally (intracranial cavity, cerebellum, brainstem and the two hemispheres) and at tissue level (cortical and subcortical gray matter, myelinated and unmyelinated white matter, and cerebrospinal fluid). We validate our algorithm through visual inspection by medical experts, as well as by quantitative comparisons that demonstrate good agreement with expert manual segmentations. The algorithm’s robustness is verified by testing on variable quality images acquired on different machines, and on subjects with variable anatomy (enlarged ventricles, preterm- vs. term-born). |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
