Integration of local and global features for anatomical object detection in ultrasound.

The use of classifier-based object detection has found to be a promising approach in medical anatomy detection. In ultrasound images, the detection task is very challenging due to speckle, shadows and low contrast characteristic features. Typical detection algorithms that use purely intensity-based...

Cijeli opis

Bibliografski detalji
Glavni autori: Rahmatullah, B, Papageorghiou, A, Noble, J
Format: Conference item
Izdano: 2012
_version_ 1826292890171604992
author Rahmatullah, B
Papageorghiou, A
Noble, J
author_facet Rahmatullah, B
Papageorghiou, A
Noble, J
author_sort Rahmatullah, B
collection OXFORD
description The use of classifier-based object detection has found to be a promising approach in medical anatomy detection. In ultrasound images, the detection task is very challenging due to speckle, shadows and low contrast characteristic features. Typical detection algorithms that use purely intensity-based image features with an exhaustive scan of the image (sliding window approach) tend not to perform very well and incur a very high computational cost. The proposed approach in this paper achieves a significant improvement in detection rates while avoiding exhaustive scanning, thereby gaining a large increase in speed. Our approach uses the combination of local features from an intensity image and global features derived from a local phase-based image known as feature symmetry. The proposed approach has been applied to 2384 two-dimensional (2D) fetal ultrasound abdominal images for the detection of the stomach and the umbilical vein. The results presented show that it outperforms prior related work that uses only local or only global features.
first_indexed 2024-03-07T03:21:40Z
format Conference item
id oxford-uuid:b7a48cce-83e8-40c3-a465-e66e745e59d1
institution University of Oxford
last_indexed 2024-03-07T03:21:40Z
publishDate 2012
record_format dspace
spelling oxford-uuid:b7a48cce-83e8-40c3-a465-e66e745e59d12022-03-27T04:50:07ZIntegration of local and global features for anatomical object detection in ultrasound.Conference itemhttp://purl.org/coar/resource_type/c_5794uuid:b7a48cce-83e8-40c3-a465-e66e745e59d1Symplectic Elements at Oxford2012Rahmatullah, BPapageorghiou, ANoble, JThe use of classifier-based object detection has found to be a promising approach in medical anatomy detection. In ultrasound images, the detection task is very challenging due to speckle, shadows and low contrast characteristic features. Typical detection algorithms that use purely intensity-based image features with an exhaustive scan of the image (sliding window approach) tend not to perform very well and incur a very high computational cost. The proposed approach in this paper achieves a significant improvement in detection rates while avoiding exhaustive scanning, thereby gaining a large increase in speed. Our approach uses the combination of local features from an intensity image and global features derived from a local phase-based image known as feature symmetry. The proposed approach has been applied to 2384 two-dimensional (2D) fetal ultrasound abdominal images for the detection of the stomach and the umbilical vein. The results presented show that it outperforms prior related work that uses only local or only global features.
spellingShingle Rahmatullah, B
Papageorghiou, A
Noble, J
Integration of local and global features for anatomical object detection in ultrasound.
title Integration of local and global features for anatomical object detection in ultrasound.
title_full Integration of local and global features for anatomical object detection in ultrasound.
title_fullStr Integration of local and global features for anatomical object detection in ultrasound.
title_full_unstemmed Integration of local and global features for anatomical object detection in ultrasound.
title_short Integration of local and global features for anatomical object detection in ultrasound.
title_sort integration of local and global features for anatomical object detection in ultrasound
work_keys_str_mv AT rahmatullahb integrationoflocalandglobalfeaturesforanatomicalobjectdetectioninultrasound
AT papageorghioua integrationoflocalandglobalfeaturesforanatomicalobjectdetectioninultrasound
AT noblej integrationoflocalandglobalfeaturesforanatomicalobjectdetectioninultrasound