Automatic Detection and Measurement of Structures in Fetal Head Ultrasound Volumes Using Sequential Estimation and Integrated Detection Network (IDN)

Abstract

Abstract-Routine ultrasound exam in the second and third trimesters of pregnancy involves manually measuring fetal head and brain structures in 2-D scans. The procedure requires a sonographer to find the standardized visualization planes with a probe and manually place measurement calipers on the structures of interest. The process is tedious, time consuming, and introduces user variability into the measurements. This paper proposes an automatic fetal head and brain (AFHB) system for automatically measuring anatomical structures from 3-D ultrasound volumes. The system searches the 3-D volume in a hierarchy of resolutions and by focusing on regions that are likely to be the measured anatomy. The output is a standardized visualization of the plane with correct orientation and centering as well as the biometric measurement of the anatomy. The system is based on a novel framework for detecting multiple structures in 3-D volumes. Since a joint model is difficult to obtain in most practical situations, the structures are detected in a sequence, one-by-one. The detection relies on Sequential Estimation techniques, frequently applied to visual tracking. The interdependence of structure poses and strong prior information embedded in our domain yields faster and more accurate results than detecting the objects individually. The posterior distribution of the structure pose is approximated at each step by sequential Monte Carlo. The samples are propagated within the sequence across multiple structures and hierarchical levels. The probabilistic model helps solve many challenges present in the ultrasound images of the fetus such as speckle noise, signal drop-out, shadows caused by bones, and appearance variations caused by the differences in the fetus gestational age. This is possible by discriminative learning on an extensive database of scans comprising more than two thousand volumes and more than thirteen thousand annotations. The average difference between ground truth and automatic measurements is below 2 mm with a running time of 6.9 s (GPU) or 14.7 s (CPU). The accuracy of the AFHB system is within inter-user variability and the running time is fast, which meets the requirements for clinical use.Index Terms-Fetal brain measurements, fetal head measurements, fetal utrasound, object detection, sequential sampling, three-dimensional (3-D) ultrasound.

Real-Time Ultrasound Segmentation, Analysis and Visualisation of Deep Cervical Muscle Structure

“…Machine learning, and in particular, deep learning methods [25], [35]- [37] are rapidly gaining a reputation as the state of the art in vision systems. We consider work on object detection within ultrasound, which demonstrates a remarkably robust solution to detecting features of fetal brains and computing measurements of fetal head structures, using a novel technique known as the Integrated Detection Network (IDN) [38]. This work proposes the use of an IDN for extracting features from training data, which are used in a sequential probabilistic object detection framework for hierarchical detection of object locations.…”

Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications

“…This algorithm was used in medical imaging to detect structures like vessels from brain, lung and other organs. An automatic fetal head and brain system for automatically measuring anatomical structures from 3-D ultrasound volumes was proposed in 2014 [48]. A review that investigates medical image segmentation techniques running on GPU was carried out in 2015.…”

Automatic image quality assessment and measurement of fetal head in two-dimensional ultrasound image

“…The standardized plane is detected using weighted Hough transform and an RF classifier. Sofka et al 24 proposed a system for automatic fetal head and brain measurements from 3-D US volumes. Several fetal head and brain anatomical structures are detected and measured while corresponding standardized planes are determined.…”