BEAN: brain extraction and alignment network for 3D fetal neurosonography
Brain extraction (masking of extra-cranial tissue) and alignment are fundamental first steps of most neuroimage analysis pipelines. The lack of automated solutions for 3D ultrasound (US) has therefore limited its potential as a neuroimaging modality for studying fetal brain development using routine...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2022
|
| _version_ | 1826308700480995328 |
|---|---|
| author | Moser, F Huang, R Papież, BW Namburete, AIL |
| author2 | Intergrowth-21st Consortium |
| author_facet | Intergrowth-21st Consortium Moser, F Huang, R Papież, BW Namburete, AIL |
| author_sort | Moser, F |
| collection | OXFORD |
| description | Brain extraction (masking of extra-cranial tissue) and alignment are fundamental first steps of most neuroimage analysis pipelines. The lack of automated solutions for 3D ultrasound (US) has therefore limited its potential as a neuroimaging modality for studying fetal brain development using routinely acquired scans. In this work, we propose a convolutional neural network (CNN) that accurately and consistently aligns and extracts the fetal brain from minimally pre-processed 3D US scans. Our multi-task CNN, Brain Extraction and Alignment Network (BEAN), consists of two independent branches: 1) a fully-convolutional encoder-decoder branch for brain extraction of unaligned scans, and 2) a two-step regression-based branch for similarity alignment of the brain to a common coordinate space. BEAN was tested on 356 fetal head scans spanning the gestational range of 14 to 30 weeks, significantly outperforming all current alternatives for fetal brain extraction and alignment. BEAN achieved state-of-the-art performance for both tasks, with a mean Dice Similarity Coefficient (DSC) of 0.94 for the brain extraction masks, and a mean DSC of 0.93 for the alignment of the target brain masks. The presented experimental results show that brain structures such as the thalamus, choroid plexus, cavum septum pellucidum, and Sylvian fissure, are consistently aligned throughout the dataset and remain clearly visible when the scans are averaged together. The BEAN implementation and related code can be found under www.github.com/felipemoser/kelluwen |
| first_indexed | 2024-03-07T07:23:15Z |
| format | Journal article |
| id | oxford-uuid:ab67ec16-ac10-4f40-9cd3-ebd66470fc03 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:23:15Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:ab67ec16-ac10-4f40-9cd3-ebd66470fc032022-11-08T10:41:32ZBEAN: brain extraction and alignment network for 3D fetal neurosonographyJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:ab67ec16-ac10-4f40-9cd3-ebd66470fc03EnglishSymplectic ElementsElsevier2022Moser, FHuang, RPapież, BWNamburete, AILIntergrowth-21st ConsortiumBrain extraction (masking of extra-cranial tissue) and alignment are fundamental first steps of most neuroimage analysis pipelines. The lack of automated solutions for 3D ultrasound (US) has therefore limited its potential as a neuroimaging modality for studying fetal brain development using routinely acquired scans. In this work, we propose a convolutional neural network (CNN) that accurately and consistently aligns and extracts the fetal brain from minimally pre-processed 3D US scans. Our multi-task CNN, Brain Extraction and Alignment Network (BEAN), consists of two independent branches: 1) a fully-convolutional encoder-decoder branch for brain extraction of unaligned scans, and 2) a two-step regression-based branch for similarity alignment of the brain to a common coordinate space. BEAN was tested on 356 fetal head scans spanning the gestational range of 14 to 30 weeks, significantly outperforming all current alternatives for fetal brain extraction and alignment. BEAN achieved state-of-the-art performance for both tasks, with a mean Dice Similarity Coefficient (DSC) of 0.94 for the brain extraction masks, and a mean DSC of 0.93 for the alignment of the target brain masks. The presented experimental results show that brain structures such as the thalamus, choroid plexus, cavum septum pellucidum, and Sylvian fissure, are consistently aligned throughout the dataset and remain clearly visible when the scans are averaged together. The BEAN implementation and related code can be found under www.github.com/felipemoser/kelluwen |
| spellingShingle | Moser, F Huang, R Papież, BW Namburete, AIL BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title | BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title_full | BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title_fullStr | BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title_full_unstemmed | BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title_short | BEAN: brain extraction and alignment network for 3D fetal neurosonography |
| title_sort | bean brain extraction and alignment network for 3d fetal neurosonography |
| work_keys_str_mv | AT moserf beanbrainextractionandalignmentnetworkfor3dfetalneurosonography AT huangr beanbrainextractionandalignmentnetworkfor3dfetalneurosonography AT papiezbw beanbrainextractionandalignmentnetworkfor3dfetalneurosonography AT nambureteail beanbrainextractionandalignmentnetworkfor3dfetalneurosonography |