Object Classification in an Ultrasound Video Using LP-SIFT Features

Maraci, Mohammad Ali; Napolitano, R.; Papageorghiou, Aris T.; Noble, Jessica

doi:10.1007/978-3-319-13972-2_7

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rahmatullah et al [15] and Patwardhan [24] used feature symmetry to find candidate 'blobs' for detection of the stomach and umbilical vein in ultrasound. Maraci et al [25] used histograms of keypoints based on dense SIFT descriptors calculated on a local phase image in order to recognise different views in an ultrasound video of the fetus. Bridge and Noble [14] incorporated various monogenic signal-based image representations into a rotation invariant sliding window object detection framework in order to localise the fetal heart in ultrasound videos.…”

Section: Symmetry Asymmetrymentioning

confidence: 99%

Introduction To The Monogenic Signal

Bridge

2017

Preprint

View full text Add to dashboard Cite

Section: Symmetry Asymmetrymentioning

confidence: 99%

Introduction To The Monogenic Signal

Bridge

2017

Preprint

View full text Add to dashboard Cite

“…Acquisition of fetal US standard planes and anatomical structure classification has received significant attention in the recent literature [2]- [4]. Bridge et al [5] identified the fetal heart from every frame of the US scan videos by applying a particle-filtering-based method.…”

Section: Introductionmentioning

confidence: 99%

COMFormer: Classification of Maternal–Fetal and Brain Anatomy Using a Residual Cross-Covariance Attention Guided Transformer in Ultrasound

Sarker,

Singh,

Alsharid

et al. 2023

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Monitoring the healthy development of a fetus requires accurate and timely identification of different maternalfetal structures as they grow. To facilitate this objective in an automated fashion, we propose a deep-learning-based image classification architecture called the COMFormer to classify maternal-fetal and brain anatomical structures present in twodimensional fetal ultrasound images. The proposed architecture classifies the two subcategories separately: maternal-fetal (abdomen, brain, femur, thorax, mother's cervix, and others) and brain anatomical structures (trans-thalamic, trans-cerebellum, trans-ventricular, and non-brain). Our proposed architecture relies on a transformer-based approach that leverages spatial and global features by using a newly designed residual cross-variance attention (R-XCA) block. This block introduces an advanced cross-covariance attention mechanism to capture a long-range representation from the input using spatial (e.g., shape, texture, intensity) and global features. To build COMFormer, we used a large publicly available dataset (BCNatal) consisting of 12, 400 images from 1,792 subjects. Experimental results prove that COMFormer outperforms the recent CNN and transformer-based models by achieving 95.64% and 96.33% classification accuracy on maternal-fetal and brain anatomy, respectively.

show abstract