3
|
Coupeau P, Fasquel JB, Mazerand E, Menei P, Montero-Menei CN, Dinomais M. Patch-based 3D U-Net and transfer learning for longitudinal piglet brain segmentation on MRI. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 214:106563. [PMID: 34890993 DOI: 10.1016/j.cmpb.2021.106563] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Revised: 11/26/2021] [Accepted: 11/26/2021] [Indexed: 06/13/2023]
Abstract
BACKGROUND AND OBJECTIVES In order to study neural plasticity in immature brain following early brain lesion, large animal model are needed. Because of its morphological similarities with the human developmental brain, piglet is a suitable but little used one. Its study from Magnetic Resonance Imaging (MRI) requires the development of automatic algorithms for the segmentation of the different structures and tissues. A crucial preliminary step consists in automatically segmenting the brain. METHODS We propose a fully automatic brain segmentation method applied to piglets by combining a 3D patch-based U-Net and a post-processing pipeline for spatial regularization and elimination of false positives. Our approach also integrates a transfer-learning strategy for managing an automated longitudinal monitoring evaluated for four developmental stages (2, 6, 10 and 18 weeks), facing the issue of MRI changes resulting from the rapid brain development. It is compared to a 2D approach and the Brain Extraction Tool (BET) as well as techniques adapted to other animals (rodents, macaques). The influence of training patches size and distribution is studied as well as the benefits of spatial regularization. RESULTS Results show that our approach is efficient in terms of average Dice score (0.952) and Hausdorff distance (8.51), outperforming the use of a 2D U-Net (Dice: 0.919, Hausdorff distance: 11.06) and BET (Dice: 0.764, Hausdorff distance: 25.91). The transfer-learning strategy achieves a good performance on older piglets (Dice of 0.934 at 6 weeks, 0.956 at 10 weeks and 0.958 at 18 weeks) compared to a standard training strategy with few data (Dice of 0.636 at 6 weeks, 0.907 at 10 weeks, not calculable at 18 weeks because of too few training piglets). CONCLUSIONS In conclusion, we provide a method for longitudinal MRI piglet brain segmentation based on 3D U-Net and transfer learning which can be used for future morphometric studies and applied to other animals.
Collapse
Affiliation(s)
- P Coupeau
- Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France.
| | - J-B Fasquel
- Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France
| | - E Mazerand
- CRCINA, UMR 1232, INSERM, Université de Nantes, Université d'Angers, F-49933 Angers, France; Département de neurochirurgie, Centre Hospitalier Universitaire d'Angers, France
| | - P Menei
- CRCINA, UMR 1232, INSERM, Université de Nantes, Université d'Angers, F-49933 Angers, France; Département de neurochirurgie, Centre Hospitalier Universitaire d'Angers, France
| | - C N Montero-Menei
- CRCINA, UMR 1232, INSERM, Université de Nantes, Université d'Angers, F-49933 Angers, France
| | - M Dinomais
- Université d'Angers, LARIS, SFR MATHSTIC, F-49000 Angers, France; Département de médecine physique et de réadaptation, Centre Hospitalier Universitaire d'Angers, France
| |
Collapse
|
4
|
Sepúlveda MM, Rojas GM, Faure E, Pardo CR, Las Heras F, Okuma C, Cordovez J, de la Iglesia-Vayá M, Molina-Mateo J, Gálvez M. Visual analysis of automated segmentation in the diagnosis of focal cortical dysplasias with magnetic resonance imaging. Epilepsy Behav 2020; 102:106684. [PMID: 31778880 DOI: 10.1016/j.yebeh.2019.106684] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/29/2019] [Revised: 10/12/2019] [Accepted: 11/02/2019] [Indexed: 01/19/2023]
Abstract
Focal cortical dysplasias (FCDs) are a frequent cause of epilepsy. It has been reported that up to 40% of them cannot be visualized with conventional magnetic resonance imaging (MRI). The main objective of this work was to evaluate by means of a retrospective descriptive observational study whether the automated brain segmentation is useful for detecting FCD. One hundred and fifty-five patients, who underwent surgery between the years 2009 and 2016, were reviewed. Twenty patients with FCD confirmed by histology and a preoperative segmentation study, with ages ranging from 3 to 43 years (14 men), were analyzed. Three expert neuroradiologists visually analyzed conventional and advanced MRI with automated segmentation. They were classified into positive and negative concerning visualization of FCD by consensus. Of the 20 patients evaluated with conventional MRI, 12 were positive for FCD. Of the negative studies for FCD with conventional MRI, 2 (25%) were positive when they were analyzed with automated segmentation. In 13 of the 20 patients (with positive segmentation for FCD), cortical thickening was observed in 5 (38.5%), while pseudothickening was observed in the rest of patients (8, 61.5%) in the anatomical region of the brain corresponding to the dysplasia. This work demonstrated that automated brain segmentation helps to increase detection of FCDs that are unable to be visualized in conventional MRI images.
Collapse
Affiliation(s)
| | - Gonzalo M Rojas
- Laboratory for Advanced Medical Image Processing, Department of Radiology, Clínica las Condes, Santiago, Chile; Health Innovation Center, Clínica las Condes, Santiago, Chile; Advanced Center for Epilepsy, Clínica la Condes, Santiago, Chile.
| | - Evelyng Faure
- Department of Radiology, Clínica las Condes, Santiago, Chile; Advanced Center for Epilepsy, Clínica la Condes, Santiago, Chile
| | - Claudio R Pardo
- Department of Radiology, Clínica las Condes, Santiago, Chile
| | - Facundo Las Heras
- Department of Pathological Anatomy, Clínica las Condes, Santiago, Chile
| | - Cecilia Okuma
- Department of Radiology, Clínica las Condes, Santiago, Chile
| | - Jorge Cordovez
- Department of Radiology, Clínica las Condes, Santiago, Chile
| | - María de la Iglesia-Vayá
- Regional Ministry of Health in Valencia Region, Valencia, Spain; Join Unit FISABIO-CIPF, Valencia, Spain
| | - José Molina-Mateo
- Center for Biomaterials and Tissue Engineering, Universitat Politècnica de València, Valencia, Spain
| | - Marcelo Gálvez
- Department of Radiology, Clínica las Condes, Santiago, Chile; Health Innovation Center, Clínica las Condes, Santiago, Chile; Advanced Center for Epilepsy, Clínica la Condes, Santiago, Chile; Academic Direction, Clinica Las Condes, Santiago, Chile
| |
Collapse
|
5
|
Hashempour N, Tuulari JJ, Merisaari H, Lidauer K, Luukkonen I, Saunavaara J, Parkkola R, Lähdesmäki T, Lehtola SJ, Keskinen M, Lewis JD, Scheinin NM, Karlsson L, Karlsson H. A Novel Approach for Manual Segmentation of the Amygdala and Hippocampus in Neonate MRI. Front Neurosci 2019; 13:1025. [PMID: 31616245 PMCID: PMC6768976 DOI: 10.3389/fnins.2019.01025] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2018] [Accepted: 09/09/2019] [Indexed: 12/16/2022] Open
Abstract
The gross anatomy of the infant brain at term is fairly similar to that of the adult brain, but structures are immature, and the brain undergoes rapid growth during the first 2 years of life. Neonate magnetic resonance (MR) images have different contrasts compared to adult images, and automated segmentation of brain magnetic resonance imaging (MRI) can thus be considered challenging as less software options are available. Despite this, most anatomical regions are identifiable and thus amenable to manual segmentation. In the current study, we developed a protocol for segmenting the amygdala and hippocampus in T2-weighted neonatal MR images. The participants were 31 healthy infants between 2 and 5 weeks of age. Intra-rater reliability was measured in 12 randomly selected MR images, where 6 MR images were segmented at 1-month intervals between the delineations, and another 6 MR images at 6-month intervals. The protocol was also tested by two independent raters in 20 randomly selected T2-weighted images, and finally with T1 images. Intraclass correlation coefficient (ICC) and Dice similarity coefficient (DSC) for intra-rater, inter-rater, and T1 vs. T2 comparisons were computed. Moreover, manual segmentations were compared to automated segmentations performed by iBEAT toolbox in 10 T2-weighted MR images. The intra-rater reliability was high ICC ≥ 0.91, DSC ≥ 0.89, the inter-rater reliabilities were satisfactory ICC ≥ 0.90, DSC ≥ 0.75 for hippocampus and DSC ≥ 0.52 for amygdalae. Segmentations for T1 vs. T2-weighted images showed high consistency ICC ≥ 0.90, DSC ≥ 0.74. The manual and iBEAT segmentations showed no agreement, DSC ≥ 0.39. In conclusion, there is a clear need to improve and develop the procedures for automated segmentation of infant brain MR images.
Collapse
Affiliation(s)
- Niloofar Hashempour
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland.,Department of Psychiatry, Turku University Hospital, University of Turku, Turku, Finland
| | - Jetro J Tuulari
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland.,Department of Psychiatry, Turku University Hospital, University of Turku, Turku, Finland.,Turku Collegium for Science and Medicine, University of Turku, Turku, Finland
| | - Harri Merisaari
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
| | - Kristian Lidauer
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland
| | - Iiris Luukkonen
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland
| | - Jani Saunavaara
- Department of Medical Physics, Turku University Hospital, Turku, Finland
| | - Riitta Parkkola
- Department of Radiology, Turku University Hospital, University of Turku, Turku, Finland
| | - Tuire Lähdesmäki
- Department of Pediatric Neurology, Turku University Hospital, University of Turku, Turku, Finland
| | - Satu J Lehtola
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland
| | - Maria Keskinen
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland
| | - John D Lewis
- Montreal Neurological Institute, McGill University, Montreal, QC, Canada
| | - Noora M Scheinin
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland.,Department of Psychiatry, Turku University Hospital, University of Turku, Turku, Finland.,Turku PET Centre, University of Turku, Turku, Finland
| | - Linnea Karlsson
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland.,Department of Child Psychiatry, Turku University Hospital, University of Turku, Turku, Finland
| | - Hasse Karlsson
- FinnBrain Birth Cohort Study, Turku Brain and Mind Center, Institute of Clinical Medicine, University of Turku, Turku, Finland.,Department of Psychiatry, Turku University Hospital, University of Turku, Turku, Finland
| |
Collapse
|
6
|
Quantitative assessment of myelination patterns in preterm neonates using T2-weighted MRI. Sci Rep 2019; 9:12938. [PMID: 31506514 PMCID: PMC6736873 DOI: 10.1038/s41598-019-49350-3] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2019] [Accepted: 08/14/2019] [Indexed: 11/08/2022] Open
Abstract
Myelination is considered to be an important developmental process during human brain maturation and closely correlated with gestational age. Quantitative assessment of the myelination status requires dedicated imaging, but the conventional T2-weighted scans routinely acquired during clinical imaging of neonates carry signatures that are thought to be associated with myelination. In this work, we develop a quatitative marker of progressing myelination for assessment preterm neonatal brain maturation based on novel automatic segmentation method for myelin-like signals on T2-weighted magnetic resonance images. Firstly we define a segmentation protocol for myelin-like signals. We then develop an expectation-maximization framework to obtain the automatic segmentations of myelin-like signals with explicit class for partial volume voxels whose locations are configured in relation to the composing pure tissues via second-order Markov random fields. The proposed segmentation achieves high Dice overlaps of 0.83 with manual annotations. The automatic segmentations are then used to track volumes of myelinated tissues in the regions of the central brain structures and brainstem. Finally, we construct a spatio-temporal growth models for myelin-like signals, which allows us to predict gestational age at scan in preterm infants with root mean squared error 1.41 weeks.
Collapse
|