Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning
The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, spec...
| Päätekijät: | , , , , , , |
|---|---|
| Muut tekijät: | |
| Aineistotyyppi: | Journal article |
| Kieli: | English |
| Julkaistu: |
Elsevier
2022
|
| _version_ | 1826307502379106304 |
|---|---|
| author | Hesse, LS Aliasi, M Moser, F Haak, MC Xie, W Jenkinson, M Namburete, AIL |
| author2 | INTERGROWTH-21st Consortium |
| author_facet | INTERGROWTH-21st Consortium Hesse, LS Aliasi, M Moser, F Haak, MC Xie, W Jenkinson, M Namburete, AIL |
| author_sort | Hesse, LS |
| collection | OXFORD |
| description | The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, speckle and shadowing artifacts. For this reason, we developed a convolutional neural network (CNN) for the automated segmentation of the choroid plexus (CP), lateral posterior ventricle horns (LPVH), cavum septum pellucidum et vergae (CSPV), and cerebellum (CB) from 3D ultrasound. As ground-truth labels are scarce and expensive to obtain, we applied few-shot learning, in which only a small number of manual annotations (n = 9) are used to train a CNN. We compared training a CNN with only a few individually annotated volumes versus many weakly labelled volumes obtained from atlas-based segmentations. This showed that segmentation performance close to intra-observer variability can be obtained with only a handful of manual annotations. Finally, the trained models were applied to a large number (n = 278) of ultrasound image volumes of a diverse, healthy population, obtaining novel US-specific growth curves of the respective structures during the second trimester of gestation. |
| first_indexed | 2024-03-07T07:04:02Z |
| format | Journal article |
| id | oxford-uuid:f4fbf2f1-bb75-4df4-92e5-c6ca1762dfdc |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:04:02Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:f4fbf2f1-bb75-4df4-92e5-c6ca1762dfdc2022-03-31T15:59:09ZSubcortical segmentation of the fetal brain in 3D ultrasound using deep learningJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:f4fbf2f1-bb75-4df4-92e5-c6ca1762dfdcEnglishSymplectic ElementsElsevier2022Hesse, LSAliasi, MMoser, FHaak, MCXie, WJenkinson, MNamburete, AILINTERGROWTH-21st ConsortiumThe quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, speckle and shadowing artifacts. For this reason, we developed a convolutional neural network (CNN) for the automated segmentation of the choroid plexus (CP), lateral posterior ventricle horns (LPVH), cavum septum pellucidum et vergae (CSPV), and cerebellum (CB) from 3D ultrasound. As ground-truth labels are scarce and expensive to obtain, we applied few-shot learning, in which only a small number of manual annotations (n = 9) are used to train a CNN. We compared training a CNN with only a few individually annotated volumes versus many weakly labelled volumes obtained from atlas-based segmentations. This showed that segmentation performance close to intra-observer variability can be obtained with only a handful of manual annotations. Finally, the trained models were applied to a large number (n = 278) of ultrasound image volumes of a diverse, healthy population, obtaining novel US-specific growth curves of the respective structures during the second trimester of gestation. |
| spellingShingle | Hesse, LS Aliasi, M Moser, F Haak, MC Xie, W Jenkinson, M Namburete, AIL Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title | Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title_full | Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title_fullStr | Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title_full_unstemmed | Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title_short | Subcortical segmentation of the fetal brain in 3D ultrasound using deep learning |
| title_sort | subcortical segmentation of the fetal brain in 3d ultrasound using deep learning |
| work_keys_str_mv | AT hessels subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT aliasim subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT moserf subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT haakmc subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT xiew subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT jenkinsonm subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning AT nambureteail subcorticalsegmentationofthefetalbrainin3dultrasoundusingdeeplearning |