End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation
This study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK F...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2022
|
| _version_ | 1797107608492965888 |
|---|---|
| author | Yasrab, R Fu, Z Drukker, L Lee, LH Zhao, H Papageorghiou, AT Noble, J |
| author_facet | Yasrab, R Fu, Z Drukker, L Lee, LH Zhao, H Papageorghiou, AT Noble, J |
| author_sort | Yasrab, R |
| collection | OXFORD |
| description | This study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK Fetal Abnormality Screening Programme. A Nested Hourglass (NHG) based network performs semantic pixel-wise segmentation to extract NT and CRL structures. Our results show that the NHG network is faster (19.52% < GFlops than FCN32) and offers high pixel agreement (meanIoU=80.74) with expert manual annotations. |
| first_indexed | 2024-03-07T07:16:51Z |
| format | Conference item |
| id | oxford-uuid:7601378d-8a92-4bb9-b135-2085bcc4ddc3 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:16:51Z |
| publishDate | 2022 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:7601378d-8a92-4bb9-b135-2085bcc4ddc32022-08-26T09:43:27ZEnd-to-end first trimester fetal ultrasound video automated CRL and NT segmentationConference itemhttp://purl.org/coar/resource_type/c_5794uuid:7601378d-8a92-4bb9-b135-2085bcc4ddc3EnglishSymplectic ElementsIEEE2022Yasrab, RFu, ZDrukker, LLee, LHZhao, HPapageorghiou, ATNoble, JThis study presents a novel approach to automatic detection and segmentation of the Crown Rump Length (CRL) and Nuchal Translucency (NT), two essential measurements in the first trimester US scan. The proposed method automatically localises a standard plane within a video clip as defined by the UK Fetal Abnormality Screening Programme. A Nested Hourglass (NHG) based network performs semantic pixel-wise segmentation to extract NT and CRL structures. Our results show that the NHG network is faster (19.52% < GFlops than FCN32) and offers high pixel agreement (meanIoU=80.74) with expert manual annotations. |
| spellingShingle | Yasrab, R Fu, Z Drukker, L Lee, LH Zhao, H Papageorghiou, AT Noble, J End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title | End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title_full | End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title_fullStr | End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title_full_unstemmed | End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title_short | End-to-end first trimester fetal ultrasound video automated CRL and NT segmentation |
| title_sort | end to end first trimester fetal ultrasound video automated crl and nt segmentation |
| work_keys_str_mv | AT yasrabr endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT fuz endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT drukkerl endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT leelh endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT zhaoh endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT papageorghiouat endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation AT noblej endtoendfirsttrimesterfetalultrasoundvideoautomatedcrlandntsegmentation |